lkeab / bcnet Goto Github PK

Deep Occlusion-Aware Instance Segmentation with Overlapping BiLayers [CVPR 2021]

Home Page: https://arxiv.org/abs/2103.12340

License: MIT License

Python 89.95% C++ 3.56% Cuda 6.42% Shell 0.07%

instance-segmentation occlusion-handling bcnet cvpr2021 cvpr detection segmentation object-detection occlusion non-local

bcnet's Introduction

Deep Occlusion-Aware Instance Segmentation with Overlapping BiLayers [BCNet, CVPR 2021]

This is the official pytorch implementation of BCNet built on the open-source detectron2.

Deep Occlusion-Aware Instance Segmentation with Overlapping BiLayers
Lei Ke, Yu-Wing Tai, Chi-Keung Tang
CVPR 2021

Highlights

BCNet: Two/one-stage (detect-then-segment) instance segmentation with state-of-the-art performance.
Novelty: A new mask head design, explicit occlusion modeling with bilayer decouple (object boundary and mask) for the occluder and occludee in the same RoI.
Efficacy: Large improvements both the FCOS (anchor-free) and Faster R-CNN (anchor-based) detectors.
Simple: Small additional computation burden and easy to use.

Visualization of Occluded Objects

Qualitative instance segmentation results of our BCNet, using ResNet-101-FPN and Faster R-CNN detector. The bottom row visualizes squared heatmap of object contour and mask predictions by the two GCN layers for the occluder and occludee in the same ROI region specified by the red bounding box, which also makes the final segmentation result of BCNet more explainable than previous methods. The heatmap visualization of GCN-1 in fourth column example shows that BCNet handles multiple occluders with in the same RoI by grouping them together. See our paper for more visual examples and comparisons.

Qualitative instance segmentation results of our BCNet, using ResNet-101-FPN and FCOS detector.

Results on COCO test-dev

(Check Table 8 of the paper for full results, all methods are trained on COCO train2017)

Detector(Two-stage)	Backbone	Method	mAP(mask)
Faster R-CNN	Res-R50-FPN	Mask R-CNN (ICCV'17)	34.2
Faster R-CNN	Res-R50-FPN	PANet (CVPR'18)	36.6
Faster R-CNN	Res-R50-FPN	MS R-CNN (CVPR'19)	35.6
Faster R-CNN	Res-R50-FPN	PointRend (1x CVPR'20)	36.3
Faster R-CNN	Res-R50-FPN	BCNet (CVPR'21)	38.4
Faster R-CNN	Res-R101-FPN	Mask R-CNN (ICCV'17)	36.1
Faster R-CNN	Res-R101-FPN	MS R-CNN (CVPR'19)	38.3
Faster R-CNN	Res-R101-FPN	BMask R-CNN (ECCV'20)	37.7
Box-free	Res-R101-FPN	SOLOv2 (NeurIPS'20)	39.7
Faster R-CNN	Res-R101-FPN	BCNet (CVPR'21)	39.8

Detector(One-stage)	Backbone	Method	mAP(mask)
FCOS	Res-R101-FPN	BlendMask (CVPR'20)	38.4
FCOS	Res-R101-FPN	CenterMask (CVPR'20)	38.3
FCOS	Res-R101-FPN	SipMask (ECCV'20)	37.8
FCOS	Res-R101-FPN	CondInst (ECCV'20)	39.1
FCOS	Res-R101-FPN	BCNet (CVPR'21)	39.6, Pretrained Model, Submission File
FCOS	Res-X101 FPN	BCNet (CVPR'21)	41.2

Introduction

Segmenting highly-overlapping objects is challenging, because typically no distinction is made between real object contours and occlusion boundaries. Unlike previous two-stage instance segmentation methods, BCNet models image formation as composition of two overlapping image layers, where the top GCN layer detects the occluding objects (occluder) and the bottom GCN layer infers partially occluded instance (occludee). The explicit modeling of occlusion relationship with bilayer structure naturally decouples the boundaries of both the occluding and occluded instances, and considers the interaction between them during mask regression. We validate the efficacy of bilayer decoupling on both one-stage and two-stage object detectors with different backbones and network layer choices. The network of BCNet is as follows:

A brief comparison of mask head architectures, see our paper for full details.

Step-by-step Installation

conda create -n bcnet python=3.7 -y
source activate bcnet
 
conda install pytorch==1.4.0 torchvision==0.5.0 cudatoolkit=10.1 -c pytorch
 
# FCOS and coco api and visualization dependencies
pip install ninja yacs cython matplotlib tqdm
pip install opencv-python==4.4.0.40
# Boundary dependency
pip install scikit-image
 
export INSTALL_DIR=$PWD
 
# install pycocotools. Please make sure you have installed cython.
cd $INSTALL_DIR
git clone https://github.com/cocodataset/cocoapi.git
cd cocoapi/PythonAPI
python setup.py build_ext install
 
# install BCNet
cd $INSTALL_DIR
git clone https://github.com/lkeab/BCNet.git
cd BCNet/
python3 setup.py build develop
 
unset INSTALL_DIR

Dataset Preparation

Prepare for coco2017 dataset following this instruction. And use our converted mask annotations (google drive or onedrive) to replace original annotation file for bilayer decoupling training.

  mkdir -p datasets/coco
  ln -s /path_to_coco_dataset/annotations datasets/coco/annotations
  ln -s /path_to_coco_dataset/train2017 datasets/coco/train2017
  ln -s /path_to_coco_dataset/test2017 datasets/coco/test2017
  ln -s /path_to_coco_dataset/val2017 datasets/coco/val2017

Multi-GPU Training and evaluation on Validation set

bash all.sh

CUDA_VISIBLE_DEVICES=0,1 python3 tools/train_net.py --num-gpus 2 \
	--config-file configs/fcos/fcos_imprv_R_50_FPN.yaml 2>&1 | tee log/train_log.txt

Pretrained Models

FCOS-version download: link

  mkdir pretrained_models
  #And put the downloaded pretrained models in this directory.

Testing on Test-dev

export PYTHONPATH=$PYTHONPATH:`pwd`
CUDA_VISIBLE_DEVICES=0,1 python3 tools/train_net.py --num-gpus 2 \
	--config-file configs/fcos/fcos_imprv_R_101_FPN.yaml \
	--eval-only MODEL.WEIGHTS ./pretrained_models/xxx.pth 2>&1 | tee log/test_log.txt

Visualization

bash visualize.sh

Reference script for producing bilayer mask annotation:

bash process.sh

The COCO-OCC split:

The COCO-OCC split download: link, which is detailed described in paper.

Citation

If you find BCNet useful in your research or refer to the provided baseline results, please star ⭐ this repository and consider citing 📝:

@inproceedings{ke2021bcnet,
    author = {Ke, Lei and Tai, Yu-Wing and Tang, Chi-Keung},
    title = {Deep Occlusion-Aware Instance Segmentation with Overlapping BiLayers},
    booktitle = {CVPR},
    year = {2021}
}

Related high-quality instance segmentation work:

@inproceedings{transfiner,
    author={Ke, Lei and Danelljan, Martin and Li, Xia and Tai, Yu-Wing and Tang, Chi-Keung and Yu, Fisher},
    title={Mask Transfiner for High-Quality Instance Segmentation},
    booktitle = {CVPR},
    year = {2022}
}

Related occlusion handling work:

@inproceedings{ke2021voin,
  author = {Ke, Lei and Tai, Yu-Wing and Tang, Chi-Keung},
  title = {Occlusion-Aware Video Object Inpainting},
  booktitle = {ICCV},
  year = {2021}
}

License

BCNet is released under the MIT license. See LICENSE for additional details. Thanks to the Third Party Libs detectron2.

Questions

Leave github issues or please contact '[email protected]'

bcnet's People

Contributors

Stargazers

Watchers

bcnet's Issues

pretrained weights

Thank your @lkeab for sharing such a great work !
Where can I download the pretrained weights ?

Full mask for occludees

Hi @lkeab ,
Thank you for your consideration.
From the issue 28
Regarding the question "every object will have a full mask no matter they are occluder or occludee?", it is yes for the amodal task.

I would like to ask about the COCO-OCC, is that split has full masks for every object from the beginning? If not, how you can conduct the mask for the ocludees?

This is an exciting result, but I would like to ask where can I download the newly synthetic occlusion images? I only find the new annotations find the annontion

ValueError: Unknown CUDA arch (8.0) or GPU not supported

When I tried python3 setup.py build develop, an error occured as follow
ValueError: Unknown CUDA arch (8.0) or GPU not supported
I tried on both V100, CUDA 11.2 and 1060ti, CUDA 11.2, this error always exists.
What should I do?
Many thanks.

[feature request] script for transforming coco-dataset to required?

Thank you for the code.

Prepare for coco2017 dataset following this instruction. And use our converted mask annotations to replace original annotation file for bilayer decoupling training.

It is possible to share the script for transforming coco-format to such a format?
Or could you explain, what exactly be done for these "converted mask"?

can't find the bcnet code

could you tell me where is the bcnet code in this projects

。

调试

BCNet的那块代码在哪里，所用的GCN那块代码怎么查看

how do i know if an instance is Occluder or Occludee?

Hi.
I have read this paper.
But I still confuse how to distinguish if an instance is an occluder or occludee when training the network. o(╥﹏╥)o

How to visualize GCN layer on Images?

bear with me for the question, wanted to visualize this part in any images.

调试

您好，在用自己数据集在执行bash process.sh指令之前，需要在detectron2/datasets/process_dataset.py文件中进行修改吗？
我之前没有修改出现了下面错误，如果需要修改需要怎么修改，修改哪里？谢谢！

train new dataset

Dear @lkeab,
I have tested successfully your model on coco dataset. Nevertheless, I also want to fine-tune the model on my custom dataset.
Can you provide the script to change the coco format to BCnet format or give me the pipeline of the dataset format ?

python3 setup.py build develop

Great job! But I failed in Step python3 setup.py build develop. The errors are as follow:

My Linux environment is: RTX3090, CUDA11.1, Pytorch1.7.
I would be greatly appreciated if you could spend some of your time solving the problem for me. I am very pleased to hear from you.
@lkeab

error: command 'gcc' failed with exit status 1

怎么测试单张图片(How to test single image)

where is setup.py

when I install the BCNet, there have an error:python3: can't open file 'setup.py': [Errno 2] No such file or directory....so what can i do

Where is the new dataset?

Hi, thanks for your awesome work.

After reading your paper, I noticed that there should be a new synthetic occlusion dataset. Where can I found it? And could you make your supplementary available on arixv?

Thanks .

results on custom dataset

Hello @lkeab ,
I was training your BCNet with my dataset. The results are not so good, but the thing I dont understand is that for some cases, the occluders are not detected as you can see my pictures below:

Checkpoint not found issue

I appreciate the good work!.

I try to explore the code and try to train. I am getting the following error message. what should i do to fix the issue

AssertionError: Checkpoint "detectron2://ImageNetPretrained/MSRA/R-101.pkl" not found!

Extension problem！

First of all, thank you for your outstanding work. What should I do if I want to use your bcnet module elsewhere? I think if it succeeds, it will be of great help to me.

调试

您好，在调试过程中出现了这个问题：在按照readme文件中的指令导入coco2017后，执行了bash all.sh进行训练，但是出现没有找到这个文件的指令：datasets/coco/annotations/instances_train_2017_transform_slight_correct.json这个文件找不到，是在执行训练命令之前还需要进行一步吗？还是哪里的问题？希望您能在百忙中解答一下，感谢！

training

你好，整个训练的顺序是按照您发的readme文件吗？我按照上面的这个步骤进行了安装环境，接着安装了CoCo数据集，我在执行bash all.sh时出现了下面的错误。这是什么地方的问题呀
Using /home/lab409/anaconda3/envs/bcnet/lib/python3.7/site-packages/oauthlib-3.1.0-py3.7.egg
Finished processing dependencies for detectron2==0.1
tee: log/train_log_159.txt: 没有那个文件或目录
Command Line Args: Namespace(config_file='configs/fcos/fcos_imprv_R_50_FPN_1x.yaml', dist_url='tcp://127.0.0.1:50152', eval_only=False, machine_rank=0, num_gpus=2, num_machines=1, opts=[], resume=False)
Traceback (most recent call last):
File "tools/train_net.py", line 161, in
args=(args,),
File "/home/lab409/BCNet-main /BCNet-main/detectron2/engine/launch.py", line 48, in launch
daemon=False,
File "/home/lab409/anaconda3/envs/bcnet/lib/python3.7/site-packages/torch/multiprocessing/spawn.py", line 171, in spawn
while not spawn_context.join():
File "/home/lab409/anaconda3/envs/bcnet/lib/python3.7/site-packages/torch/multiprocessing/spawn.py", line 118, in join
raise Exception(msg)
Exception:

-- Process 1 terminated with the following error:
Traceback (most recent call last):
File "/home/lab409/anaconda3/envs/bcnet/lib/python3.7/site-packages/torch/multiprocessing/spawn.py", line 19, in _wrap
fn(i, *args)
File "/home/lab409/BCNet-main /BCNet-main/detectron2/engine/launch.py", line 71, in _distributed_worker
assert num_gpus_per_machine <= torch.cuda.device_count()
AssertionError

KeyError:'bg_object_segmentation'.

Thank you for the open source code.
I use the coco dataset for training, and the annotation file is instances_train_2017_transform_slight_correct.json.
There was an KeyError:'bg_object_segmentation'.
I checked ‘dataset_dict’ and found that the annotation in ‘dataset_dict’ does not contain bg_object_segmentation，but when I open instances_train_2017_transform_slight_correct.json, there is bg_object_segmentation in 'instances_train_2017_transform_slight_correct.json'.

The error message is below：

[07/09 16:47:33 d2.engine.train_loop]: Starting training from iteration 0
<generator object AspectRatioGroupedDataset.iter at 0x7f1f3e3c4c50>
[07/09 16:47:34 d2.engine.hooks]: Total training time: 0:00:00 (0:00:00 on hooks)
Traceback (most recent call last):
File "/media/lc/files/YLQ/BCNet-main/detectron2/engine/train_loop.py", line 133, in train
self.run_step()
File "/media/lc/files/YLQ/BCNet-main/detectron2/engine/train_loop.py", line 212, in run_step
data = next(self._data_loader_iter)
File "/media/lc/files/YLQ/BCNet-main/detectron2/data/common.py", line 139, in iter
for d in self.dataset:
File "/home/lc/anaconda3/envs/bcnet/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 345, in next
data = self._next_data()
File "/home/lc/anaconda3/envs/bcnet/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 856, in _next_data
return self._process_data(data)
File "/home/lc/anaconda3/envs/bcnet/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 881, in _process_data
data.reraise()
File "/home/lc/anaconda3/envs/bcnet/lib/python3.6/site-packages/torch/_utils.py", line 394, in reraise
raise self.exc_type(msg)
KeyError: Caught KeyError in DataLoader worker process 0.
Original Traceback (most recent call last):
File "/home/lc/anaconda3/envs/bcnet/lib/python3.6/site-packages/torch/utils/data/_utils/worker.py", line 178, in _worker_loop
data = fetcher.fetch(index)
File "/home/lc/anaconda3/envs/bcnet/lib/python3.6/site-packages/torch/utils/data/_utils/fetch.py", line 44, in fetch
data = [self.dataset[idx] for idx in possibly_batched_index]
File "/home/lc/anaconda3/envs/bcnet/lib/python3.6/site-packages/torch/utils/data/_utils/fetch.py", line 44, in
data = [self.dataset[idx] for idx in possibly_batched_index]
File "/media/lc/files/YLQ/BCNet-main/detectron2/data/common.py", line 40, in getitem
data = self._map_func(self._dataset[cur_idx])
File "/media/lc/files/YLQ/BCNet-main/detectron2/utils/serialize.py", line 22, in call
return self._obj(*args, **kwargs)
File "/media/lc/files/YLQ/BCNet-main/detectron2/data/dataset_mapper.py", line 134, in call
annos, image_shape, mask_format=self.mask_format
File "/media/lc/files/YLQ/BCNet-main/detectron2/data/detection_utils.py", line 278, in annotations_to_instances
bo_segms = [obj["bg_object_segmentation"] for obj in annos]
File "/media/lc/files/YLQ/BCNet-main/detectron2/data/detection_utils.py", line 278, in
bo_segms = [obj["bg_object_segmentation"] for obj in annos]
KeyError: 'bg_object_segmentation'

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "/media/lc/files/YLQ/BCNet-main/tools/train_net.py", line 164, in
args=(args,),
File "/media/lc/files/YLQ/BCNet-main/detectron2/engine/launch.py", line 51, in launch
main_func(*args)
File "/media/lc/files/YLQ/BCNet-main/tools/train_net.py", line 151, in main
return trainer.train()
File "/media/lc/files/YLQ/BCNet-main/detectron2/engine/defaults.py", line 384, in train
super().train(self.start_iter, self.max_iter)
File "/media/lc/files/YLQ/BCNet-main/detectron2/engine/train_loop.py", line 136, in train
self.after_train()
File "/media/lc/files/YLQ/BCNet-main/detectron2/engine/train_loop.py", line 144, in after_train
h.after_train()
File "/media/lc/files/YLQ/BCNet-main/detectron2/engine/hooks.py", line 353, in after_train
self._do_eval()
File "/media/lc/files/YLQ/BCNet-main/detectron2/engine/hooks.py", line 321, in _do_eval
results = self._func()
File "/media/lc/files/YLQ/BCNet-main/detectron2/engine/defaults.py", line 335, in test_and_save_results
self._last_eval_results = self.test(self.cfg, self.model)
File "/media/lc/files/YLQ/BCNet-main/detectron2/engine/defaults.py", line 480, in test
data_loader = cls.build_test_loader(cfg, dataset_name)
File "/media/lc/files/YLQ/BCNet-main/detectron2/engine/defaults.py", line 442, in build_test_loader
return build_detection_test_loader(cfg, dataset_name)
File "/media/lc/files/YLQ/BCNet-main/detectron2/data/build.py", line 386, in build_detection_test_loader
else None,
File "/media/lc/files/YLQ/BCNet-main/detectron2/data/build.py", line 230, in get_detection_dataset_dicts
dataset_dicts = [DatasetCatalog.get(dataset_name) for dataset_name in dataset_names]
File "/media/lc/files/YLQ/BCNet-main/detectron2/data/build.py", line 230, in
dataset_dicts = [DatasetCatalog.get(dataset_name) for dataset_name in dataset_names]
File "/media/lc/files/YLQ/BCNet-main/detectron2/data/catalog.py", line 65, in get
return f()
File "/media/lc/files/YLQ/BCNet-main/detectron2/data/datasets/register_coco.py", line 35, in
DatasetCatalog.register(name, lambda: load_coco_json_eval(json_file, image_root, name))
File "/media/lc/files/YLQ/BCNet-main/detectron2/data/datasets/coco.py", line 57, in load_coco_json_eval
coco_api = COCO(json_file)
File "/home/lc/anaconda3/envs/bcnet/lib/python3.6/site-packages/pycocotools/coco.py", line 85, in init
dataset = json.load(f)
File "/home/lc/anaconda3/envs/bcnet/lib/python3.6/json/init.py", line 299, in load
parse_constant=parse_constant, object_pairs_hook=object_pairs_hook, **kw)
File "/home/lc/anaconda3/envs/bcnet/lib/python3.6/json/init.py", line 354, in loads
return _default_decoder.decode(s)
File "/home/lc/anaconda3/envs/bcnet/lib/python3.6/json/decoder.py", line 339, in decode
obj, end = self.raw_decode(s, idx=_w(s, 0).end())
File "/home/lc/anaconda3/envs/bcnet/lib/python3.6/json/decoder.py", line 355, in raw_decode
obj, end = self.scan_once(s, idx)
json.decoder.JSONDecodeError: Expecting property name enclosed in double quotes: line 1 column 205 (char 204)

Process finished with exit code 1

About data set conversion

Hey dear @lkeab
Thanks for this work. I want to use BCNet, but I only have about 1000 RGB images and their ground truth images. There is no problem with training with object detection such as Faster R-CNN, but when I try to do it with BCNet or mask-rcnn, I get an error "Cannot find field 'gt_masks' in the given Instances". How can I register dataset with ground truth without json segmentation file? In other words, ground truth is sufficient with RGB images to do instance segmentation, or how can I do it.

Thanks a lot in advance.

Confuse about the training details of mask head

Dear author:
Thanks for your great job!
I'm confused about the training details of mask head. I find that you use the roi_feat extracted from gt_bbox instand of pred box from FCOS to train maskhead, right?

In './fcos.py', you always add gt to proposals and do the match between proposals and gt. So the 'gt' added to proposals will 100% match the gt. Then in the 'self._sample_proposals' function, I find that it's not a sample function, it just return the index of matched proposal（which is the gt added to proposals）. Finally, I print out the proposal boxes which will be the input of maskhead, and I find it's the same as gt_box.

In the code comments, you say that when training starts the proposals will be low quality due to random initialization, so you add gt. But it will cause the input of maskhead is always the roi from gt_box.

数据转化

你好，现在builtin_meta.py中修改了things_classes,添加了自己的数据集，但是再执行bash process.sh时，出现了process_datasets中的错误，这个数据集转换之间的几个文件的关系没太明白，一直没有将自己的数据集转化成功，能帮忙解答一下吗，谢谢！

测试新的数据集(Test on new dataset)

您好，想用自己的数据集测试一下这个方法，想问一下，数据集那部分是需要将coco格式数据集再进行转化吗？应用数据集的那块代码在哪里可以查看呀

running problem!!!!!!!!!!

First of all, thank you for the exciting work of open source. I encountered some problems while running your project. I hope to get your help. It will be very useful to me.

I used the anaconda3 environment, cuda 10.2, and the other configurations are exactly the same as your readme. Do I need to install cuda and cudnn outside of anaconda?

Confusion about process_dataset.py

Thanks for your great job! I have some questions for you.
Could you tell me
1.the difference between the output file generated by process_dataset and the COCO dataset format？
2. line278-296 : I confused why do you filp the mat of contour and Interlaced sampling?

            union_mask_non_zero_num = np.count_nonzero(union_mask_whole.astype(int))
            record["annotations"][index1]['bg_object_segmentation'] = []
            if union_mask_non_zero_num > 20:
                sum_co_box += 1
                contours = measure.find_contours(union_mask_whole.astype(int), 0)
                for contour in contours:
                    if contour.shape[0] > 500: 
                        contour = np.flip(contour, axis=1)[::10,:]
                    elif contour.shape[0] > 200: 
                        contour = np.flip(contour, axis=1)[::5,:]
                    elif contour.shape[0] > 100: 
                        contour = np.flip(contour, axis=1)[::3,:]
                    elif contour.shape[0] > 50: 
                        contour = np.flip(contour, axis=1)[::2,:]
                    else:
                        contour = np.flip(contour, axis=1)

                    segmentation = contour.ravel().tolist()
                    record["annotations"][index1]['bg_object_segmentation'].append(segmentation)

It would be nice if you could give me more details.

setting NUM_CLASSES

in the beginning i would like to give others some notice: even though you've install pytorch via anaconda with cudatoolkit. But still. it is just for the pytorch. not for detectron2. pls consider using cuda package locally or use a docker.

question 1:
train_log_init.txt

I've found out you've noticed, that we should change MODEL.ROI_HEADS.NUM_CLASSES and MODEL.RETINANET.NUM_CLASSES. I've changed them in detectron2/config/defaults.py
Or tried to add the params in all.sh via adding MODEL.ROI_HEADS.NUM_CLASSES 2, MODEL.FCOS.NUM_CLASSES 2, MODEL.RETINANET.NUM_CLASSES 2
for my 2 classes (background not included). but none of them helps...
The error:
AssertionError: A prediction has category_id=62, which is not available in the dataset.
question 2:
the training seems stop immediately.
i've changed the MAX_ITER in yaml file, but it was not helped..

I think the both problems could be relevant, because the model is not trained for 2 classes.
the log file is attached. many thanks for your help!

你好，请问下这个代码能在单个gpu下训练吗，还有能在win系统下复现吗？我是科研小白，请多多见谅！

no training: Total training time: 0:00:00

I debugged the training process. There is no problem loading the data set. But when it runs to the 205th line of /home/zhaojing/BCNet/detectron2/engine/train_loop.py, the training ends.
data = next(self._data_loader_iter)

How to solve this problem，thank you!

The log is as follows：
.................
[07/15 18:54:16 d2.data.datasets.coco]: Loading /repository01/nucleus_seg_data/instanceSeg/MoNuSeg/annotations/instances_train2017bcnet.json takes 16.16 seconds.
[07/15 18:54:17 d2.data.datasets.coco]: Loaded 7680 images in COCO format from /repository01/nucleus_seg_data/instanceSeg/MoNuSeg/annotations/instances_train2017bcnet.json
[07/15 19:00:58 d2.data.build]: Removed 0 images with no usable annotations. 7680 images left.
[07/15 19:01:12 d2.data.build]: Distribution of instances among all 1 categories:

category	#instances
building	310262

[07/15 19:01:16 d2.data.common]: Serializing 7680 elements to byte tensors and concatenating them all ...
[07/15 19:01:20 d2.data.common]: Serialized dataset takes 253.14 MiB
[07/15 19:02:52 d2.data.detection_utils]: TransformGens used in training: [ResizeShortestEdge(short_edge_length=(600,), max_size=900, sample_style='choice'), RandomFlip()]
[07/15 19:03:31 d2.data.build]: Using training sampler TrainingSampler
[07/15 19:05:52 fvcore.common.checkpoint]: [Checkpointer] Loading from /home/zhaojing/BCNet/pretrainmodel/R-101.pkl ...
[07/15 19:05:52 d2.checkpoint.c2_model_loading]: Remapping C2 weights ......
[07/15 19:05:54 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res2.0.conv1.norm.bias loaded from res2_0_branch2a_bn_beta of shape (64,)
[07/15 19:05:54 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res2.0.conv1.norm.running_mean loaded from res2_0_branch2a_bn_running_mean of shape (64,)
[07/15 19:05:54 d2.checkpoint.c2_model_loading]: backbone.bottom_up.res2.0.conv1.norm.running_var loaded from res2_0_branch2a_bn_running_var of shape (64,)
............................

[07/15 16:52:25 d2.checkpoint.c2_model_loading]: The checkpoint state_dict contains keys that are not used by the model:
fc1000_b
fc1000_w
[07/15 16:52:25 d2.engine.train_loop]: Starting training from iteration 0
[07/15 16:52:25 d2.engine.hooks]: Total training time: 0:00:00 (0:00:00 on hooks)
[07/15 16:52:26 d2.data.datasets.coco]: Loaded 896 images in COCO format from /repository01/nucleus_seg_data/instanceSeg/MoNuSeg/annotations/instances_test2017bcnet.json
[07/15 16:52:26 d2.data.build]: Distribution of instances among all 1 categories:

category	#instances
building	24384

[07/15 16:52:26 d2.data.common]: Serializing 896 elements to byte tensors and concatenating them all ...
[07/15 16:52:26 d2.data.common]: Serialized dataset takes 7.96 MiB
[07/15 16:52:27 d2.evaluation.evaluator]: Start inference on 896 images
[07/15 16:52:28 d2.evaluation.evaluator]: Inference done 11/896. 0.0775 s / img. ETA=0:01:30
[07/15 16:52:33 d2.evaluation.evaluator]: Inference done 61/896. 0.0761 s / img. ETA=0:01:24


_libgcc_mutex             0.1                        main  
_openmp_mutex             4.5                       1_gnu  
blas                      1.0                         mkl    https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/free
bzip2                     1.0.8                h7b6447c_0  
ca-certificates           2021.7.5             h06a4308_1  
certifi                   2021.5.30        py37h06a4308_0  
cffi                      1.14.6           py37h400218f_0  
charset-normalizer        2.0.1                    pypi_0    pypi
cloudpickle               1.6.0                    pypi_0    pypi
cudatoolkit               10.0.130                      0    nvidia
cycler                    0.10.0                   pypi_0    pypi
cython                    3.0.0a8                  pypi_0    pypi
detectron2                0.1                       dev_0    <develop>
ffmpeg                    4.3                  hf484d3e_0    pytorch
freetype                  2.10.4               h5ab3b9f_0  
future                    0.18.2                   pypi_0    pypi
gmp                       6.2.1                h2531618_2  
gnutls                    3.6.15               he1e5248_0  
idna                      3.2                      pypi_0    pypi
intel-openmp              2021.2.0           h06a4308_610  
iopath                    0.1.9                    pypi_0    pypi
jpeg                      9b                            0    https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/free
kiwisolver                1.3.1                    pypi_0    pypi
lame                      3.100                h7b6447c_0  
lcms2                     2.12                 h3be6417_0  
ld_impl_linux-64          2.35.1               h7274673_9  
libffi                    3.3                  he6710b0_2  
libgcc-ng                 9.3.0               h5101ec6_17  
libgfortran-ng            7.5.0               ha8ba4b0_17  
libgfortran4              7.5.0               ha8ba4b0_17  
libgomp                   9.3.0               h5101ec6_17  
libiconv                  1.14                          0    https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/free
libidn2                   2.3.1                h27cfd23_0  
libpng                    1.6.37               hbc83047_0  
libstdcxx-ng              9.3.0               hd4cf53a_17  
libtasn1                  4.16.0               h27cfd23_0  
libtiff                   4.2.0                h85742a9_0  
libunistring              0.9.10               h27cfd23_0  
libuv                     1.40.0               h7b6447c_0  
libwebp-base              1.2.0                h27cfd23_0  
lz4-c                     1.9.3                h2531618_0  
mkl                       2021.2.0           h06a4308_296  
mkl-service               2.4.0            py37h7f8727e_0  
mkl_fft                   1.3.0            py37h42c9631_2  
mkl_random                1.2.1            py37ha9443f7_2  
ncurses                   6.2                  he6710b0_1  
nettle                    3.7.3                hbbd107a_1  
ninja                     1.7.2                         0    https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/free
numpy                     1.20.2           py37h2d18471_0  
numpy-base                1.20.2           py37hfae3a4d_0  
olefile                   0.46                     py37_0  
openh264                  2.1.0                hd408876_0  
openjpeg                  2.3.0                h05c96fa_1  
openssl                   1.1.1k               h27cfd23_0  
pillow                    6.2.2                    pypi_0    pypi
pip                       21.1.3           py37h06a4308_0  
portalocker               2.3.0                    pypi_0    pypi
pycocotools               2.0                      pypi_0    pypi
pycparser                 2.20                       py_2  
pydot                     1.4.2                    pypi_0    pypi
pyparsing                 3.0.0b2                  pypi_0    pypi
python                    3.7.10               h12debd9_4  
python-dateutil           2.8.1                    pypi_0    pypi
pytorch                   1.4.0           py3.7_cuda10.0.130_cudnn7.6.3_0    pytorch
pywavelets                1.1.1            py37h7b6447c_2  
pyyaml                    5.4.1                    pypi_0    pypi
readline                  8.1                  h27cfd23_0  
requests                  2.26.0                   pypi_0    pypi
scipy                     1.6.2            py37had2a1c9_1  
setuptools                52.0.0           py37h06a4308_0  
six                       1.16.0             pyhd3eb1b0_0  
sqlite                    3.36.0               hc218d9a_0  
tabulate                  0.8.9                    pypi_0    pypi
tensorboard               2.5.0                    pypi_0    pypi
tensorboard-data-server   0.6.1                    pypi_0    pypi
tensorboard-plugin-wit    1.8.0                    pypi_0    pypi
tk                        8.6.10               hbc83047_0  
torchaudio                0.4.0                      py37    pytorch
torchvision               0.5.0                py37_cu100    pytorch
tqdm                      4.61.2                   pypi_0    pypi
typing                    3.10.0.0         py37h06a4308_0  
typing_extensions         3.10.0.0           pyh06a4308_0  
urllib3                   1.26.6                   pypi_0    pypi
werkzeug                  2.0.1                    pypi_0    pypi
wheel                     0.36.2                   pypi_0    pypi
xz                        5.2.5                h7b6447c_0  
yacs                      0.1.8                    pypi_0    pypi
zlib                      1.2.11                        0    https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/free
zstd                      1.4.9                haebb681_0

how to use on single image?

Hello there! Thank you for opening up your project. If I want to use a single image for testing, how should I write the command?

python3 setup.py build develop

Hi, I'm really excited about your work. But now I'm meeting this problem. Is this a proper situation？If not，how I can solve the problem？Thank you.

调试

您好，我在用自己的数据集执行时，在执行bash all.sh命令后，出现了这个问题，请问这个地方应该怎么修改呀，谢谢！

Results Question

Hi! Thisi is a very insteresting paper. I have a question on results comparison.
In tab.3 BCNet + FCOS achieves 39.6 mask ap. Is this 3x training or 1x training on coco?
How about BCNet + Faster R-CNN?

bilayer occlusion modeling

您好，请问一下，ROI之后那部分遮挡和被遮挡部分的代码在那一块啊，还尚未开源吗

Data conversion

Thank you for the code.
How do I convert the standard coco file format into the json format usable by BCNet?
How to get bg_object_segmentation in the json file available on BCNet？There are 3700 instances in the training data.

[06/22 21:13:16 d2.engine.train_loop]: Starting training from iteration 0
[06/22 21:13:16 d2.engine.hooks]: Total training time: 0:00:00 (0:00:00 on hooks)

RuntimeError: cuDNN error: CUDNN_STATUS_NOT_SUPPORTED. This error may appear if you passed in a non-contiguous input.

I run the command like: CUDA_VISIBLE_DEVICES=2,3 python tools/train_net.py --num-gpus 2 --config-file configs/fcos/fcos_imprv_R_50_FPN.yaml 2>&1 | tee log/train_log.tx
After the Evaluation, we got a problem about cuDNN.

**[05/31 13:10:41 d2.evaluation.coco_evaluation]: Evaluation results for segm:

AP	AP50	AP75	APs	APm	APl
0.000	0.000	0.000	0.000	0.000	0.000
[05/31 13:10:41 d2.evaluation.coco_evaluation]: Per-category segm AP:
category	AP	category	AP	category	AP
:--------------	:------	:-------------	:------	:---------------	:------
person	0.000	bicycle	0.000	car	0.000
motorcycle	0.000	airplane	0.000	bus	0.000
train	0.000	truck	0.000	boat	0.000
traffic light	0.000	fire hydrant	0.000	stop sign	0.000
parking meter	0.000	bench	0.000	bird	0.000
cat	0.000	dog	0.000	horse	0.000
sheep	0.000	cow	0.000	elephant	0.000
bear	0.000	zebra	0.000	giraffe	0.000
backpack	0.000	umbrella	0.000	handbag	0.000
tie	0.000	suitcase	0.000	frisbee	0.000
skis	0.000	snowboard	0.000	sports ball	0.000
kite	0.000	baseball bat	0.000	baseball glove	0.000
skateboard	0.000	surfboard	0.000	tennis racket	0.000
bottle	0.000	wine glass	0.000	cup	0.000
fork	0.000	knife	0.000	spoon	0.000
bowl	0.000	banana	0.000	apple	0.000
sandwich	0.000	orange	0.000	broccoli	0.000
carrot	0.000	hot dog	0.000	pizza	0.000
donut	0.000	cake	0.000	chair	0.000
couch	0.000	potted plant	0.000	bed	0.000
dining table	0.000	toilet	0.000	tv	0.000
laptop	0.000	mouse	0.000	remote	0.000
keyboard	0.000	cell phone	0.000	microwave	0.000
oven	0.000	toaster	0.000	sink	0.000
refrigerator	0.000	book	0.000	clock	0.000
vase	0.000	scissors	0.000	teddy bear	0.000
hair drier	0.000	toothbrush	0.000
[05/31 13:10:42 d2.engine.defaults]: Evaluation results for coco_2017_val in csv format:
[05/31 13:10:42 d2.evaluation.testing]: copypaste: Task: bbox
[05/31 13:10:42 d2.evaluation.testing]: copypaste: AP,AP50,AP75,APs,APm,APl
[05/31 13:10:42 d2.evaluation.testing]: copypaste: 0.0000,0.0000,0.0000,0.0000,0.0000,0.0000
[05/31 13:10:42 d2.evaluation.testing]: copypaste: Task: segm
[05/31 13:10:42 d2.evaluation.testing]: copypaste: AP,AP50,AP75,APs,APm,APl
[05/31 13:10:42 d2.evaluation.testing]: copypaste: 0.0000,0.0000,0.0000,0.0000,0.0000,0.0000
Traceback (most recent call last):
File "tools/train_net.py", line 161, in

args=(args,),

File "/data/zlq/code/BCNet-main/detectron2/engine/launch.py", line 48, in launch
daemon=False,
File "/home/zlq/anaconda3/envs/bcnet/lib/python3.7/site-packages/torch/multiprocessing/spawn.py", line 171, in spawn
while not spawn_context.join():
File "/home/zlq/anaconda3/envs/bcnet/lib/python3.7/site-packages/torch/multiprocessing/spawn.py", line 118, in join
raise Exception(msg)
Exception:

-- Process 1 terminated with the following error:
Traceback (most recent call last):
File "/home/zlq/anaconda3/envs/bcnet/lib/python3.7/site-packages/torch/multiprocessing/spawn.py", line 19, in _wrap
fn(i, args)
File "/data/zlq/code/BCNet-main/detectron2/engine/launch.py", line 83, in _distributed_worker
main_func(args)
File "/data/zlq/code/BCNet-main/tools/train_net.py", line 149, in main
return trainer.train()
File "/data/zlq/code/BCNet-main/detectron2/engine/defaults.py", line 373, in train
super().train(self.start_iter, self.max_iter)
File "/data/zlq/code/BCNet-main/detectron2/engine/train_loop.py", line 131, in train
self.run_step()
File "/data/zlq/code/BCNet-main/detectron2/engine/train_loop.py", line 224, in run_step
losses.backward()
File "/home/zlq/anaconda3/envs/bcnet/lib/python3.7/site-packages/torch/tensor.py", line 195, in backward
torch.autograd.backward(self, gradient, retain_graph, create_graph)
File "/home/zlq/anaconda3/envs/bcnet/lib/python3.7/site-packages/torch/autograd/init.py", line 99, in backward
allow_unreachable=True) # allow_unreachable flag
RuntimeError: cuDNN error: CUDNN_STATUS_NOT_SUPPORTED. This error may appear if you passed in a non-contiguous input.

I followed the Step-by-step Installation.
Pytorch 1.4 .0
torchvision 0.5.0
cudatoolkit 10.1

Did anyone meet this problem before?
Is this a version problem? https://github.com/pytorch/pytorch/issues/32395

前景提取 (Foreground extraction)

作者您好。感谢的开源。我配置好了您的代码，运行了您的visual.sh，效果非常好。就是请问修改哪部分代码能实现前景提取呢？我需要剔除图像中的背景信息。

why we need the first indexs2.shape[0] in gt_bo_masks[:indexs2.shape[0]]?

Thanks for your attention, codes as follows.

new_gt_bo_masks1 = gt_bo_masks[indexs2,:,:].squeeze()
new_gt_bo_masks2 = gt_bo_masks[:indexs2.shape[0]]
if new_gt_bo_masks1.shape != new_gt_bo_masks2.shape:
new_gt_bo_masks1 = new_gt_bo_masks1.unsqueeze(0)
new_gt_bo_masks = torch.cat((new_gt_bo_masks1, new_gt_bo_masks2),0)

Results Question

Hi! Thisi is a very insteresting paper. I have a question on results comparison.
In Table 6. Results of the KINS dataset,
AP_seg of Mask R-CNN + ASN : 25.62
AP_seg of PANet + ASN : 26.81

But in [46]Amodal instance segmentation with kins dataset,
AP_seg of Mask R-CNN + ASN : 31.1
AP_seg of PANet + ASN : 32.2

AP_Det values are also different.

Why these results are different?

can't build on win10?

A issue about train

Config 'configs/fcos/fcos_imprv_R_50_FPN.yaml' has no VERSION. Assuming it to be compatible with latest v2.
Command Line Args: Namespace(config_file='configs/fcos/fcos_imprv_R_50_FPN.yaml', dist_url='tcp://127.0.0.1:50152', eval_only=False, machine_rank=0, num_gpus=1, num_machines=1, opts=[], resume=False)
�[32m[08/10 20:20:51 detectron2]: �[0mRank of current process: 0. World size: 1
�[32m[08/10 20:20:51 detectron2]: �[0mEnvironment info:

sys.platform linux
Python 3.7.11 (default, Jul 27 2021, 14:32:16) [GCC 7.5.0]
Numpy 1.20.3
Detectron2 Compiler GCC 5.4
Detectron2 CUDA Compiler 10.1
DETECTRON2_ENV_MODULE
PyTorch 1.4.0
PyTorch Debug Build False
torchvision 0.5.0
CUDA available True
GPU 0 GeForce GTX 1080 Ti
CUDA_HOME /usr/local/cuda-10.1
NVCC Cuda compilation tools, release 10.1, V10.1.105
Pillow 6.2.2
cv2 4.4.0

PyTorch built with:

GCC 7.3
Intel(R) oneAPI Math Kernel Library Version 2021.3-Product Build 20210617 for Intel(R) 64 architecture applications
Intel(R) MKL-DNN v0.21.1 (Git Hash 7d2fd500bc78936d1d648ca713b901012f470dbc)
OpenMP 201511 (a.k.a. OpenMP 4.5)
NNPACK is enabled
CUDA Runtime 10.1
NVCC architecture flags: -gencode;arch=compute_37,code=sm_37;-gencode;arch=compute_50,code=sm_50;-gencode;arch=compute_60,code=sm_60;-gencode;arch=compute_61,code=sm_61;-gencode;arch=compute_70,code=sm_70;-gencode;arch=compute_75,code=sm_75;-gencode;arch=compute_37,code=compute_37
CuDNN 7.6.3
Magma 2.5.1
Build settings: BLAS=MKL, BUILD_NAMEDTENSOR=OFF, BUILD_TYPE=Release, CXX_FLAGS= -Wno-deprecated -fvisibility-inlines-hidden -fopenmp -DUSE_FBGEMM -DUSE_QNNPACK -DUSE_PYTORCH_QNNPACK -O2 -fPIC -Wno-narrowing -Wall -Wextra -Wno-missing-field-initializers -Wno-type-limits -Wno-array-bounds -Wno-unknown-pragmas -Wno-sign-compare -Wno-unused-parameter -Wno-unused-variable -Wno-unused-function -Wno-unused-result -Wno-strict-overflow -Wno-strict-aliasing -Wno-error=deprecated-declarations -Wno-stringop-overflow -Wno-error=pedantic -Wno-error=redundant-decls -Wno-error=old-style-cast -fdiagnostics-color=always -faligned-new -Wno-unused-but-set-variable -Wno-maybe-uninitialized -fno-math-errno -fno-trapping-math -Wno-stringop-overflow, DISABLE_NUMA=1, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, USE_CUDA=ON, USE_EXCEPTION_PTR=1, USE_GFLAGS=OFF, USE_GLOG=OFF, USE_MKL=ON, USE_MKLDNN=ON, USE_MPI=OFF, USE_NCCL=ON, USE_NNPACK=ON, USE_OPENMP=ON, USE_STATIC_DISPATCH=OFF,

�[32m[08/10 20:20:51 detectron2]: �[0mCommand line arguments: Namespace(config_file='configs/fcos/fcos_imprv_R_50_FPN.yaml', dist_url='tcp://127.0.0.1:50152', eval_only=False, machine_rank=0, num_gpus=1, num_machines=1, opts=[], resume=False)
�[32m[08/10 20:20:51 detectron2]: �[0mContents of args.config_file=configs/fcos/fcos_imprv_R_50_FPN.yaml:

FCOS with improvements

BASE: "../Base-FCOS.yaml"
MODEL:

WEIGHTS: "detectron2:/ImageNetPretrained/MSRA/R-50.pkl"

WEIGHTS: "/home/zhangjian/code/BCNet/pretrained_models/R-50.pkl"
RESNETS:
DEPTH: 50

�[32m[08/10 20:20:51 detectron2]: �[0mRunning with full config:
CUDNN_BENCHMARK: False
DATALOADER:
ASPECT_RATIO_GROUPING: True
FILTER_EMPTY_ANNOTATIONS: True
NUM_WORKERS: 8
REPEAT_THRESHOLD: 0.0
SAMPLER_TRAIN: TrainingSampler
DATASETS:
PRECOMPUTED_PROPOSAL_TOPK_TEST: 1000
PRECOMPUTED_PROPOSAL_TOPK_TRAIN: 2000
PROPOSAL_FILES_TEST: ()
PROPOSAL_FILES_TRAIN: ()
TEST: ('coco_2017_val',)
TRAIN: ('coco_2017_train',)
GLOBAL:
HACK: 1.0
INPUT:
CROP:
ENABLED: False
SIZE: [0.9, 0.9]
TYPE: relative_range
FORMAT: BGR
MASK_FORMAT: polygon
MAX_SIZE_TEST: 900
MAX_SIZE_TRAIN: 900
MIN_SIZE_TEST: 600
MIN_SIZE_TRAIN: (600,)
MIN_SIZE_TRAIN_SAMPLING: choice
MODEL:
ANCHOR_GENERATOR:
ANGLES: [[-90, 0, 90]]
ASPECT_RATIOS: [[0.5, 1.0, 2.0]]
NAME: DefaultAnchorGenerator
OFFSET: 0.0
SIZES: [[32, 64, 128, 256, 512]]
BACKBONE:
FREEZE_AT: 2
NAME: build_retinanet_resnet_fpn_backbone
DEVICE: cuda
FCOS:
CENTERNESS_ON_REG: True
CENTER_SAMPLING_RADIUS: 1.5
FPN_STRIDES: [8, 16, 32, 64, 128]
INFERENCE_TH: 0.03
IN_FEATURES: ['p3', 'p4', 'p5', 'p6', 'p7']
IOU_LOSS_TYPE: giou
LOSS_ALPHA: 0.25
LOSS_GAMMA: 2.0
NMS_TH: 0.6
NORM_REG_TARGETS: True
NUM_CLASSES: 80
NUM_CONVS: 4
PRE_NMS_TOP_N: 1000
PRIOR_PROB: 0.01
TRAIN_PART: all
USE_DCN_IN_TOWER: False
FPN:
FUSE_TYPE: sum
IN_FEATURES: ['res3', 'res4', 'res5']
NORM:
OUT_CHANNELS: 256
KEYPOINT_ON: False
LOAD_PROPOSALS: False
MASK_ON: True
META_ARCHITECTURE: FCOS
PANOPTIC_FPN:
COMBINE:
ENABLED: True
INSTANCES_CONFIDENCE_THRESH: 0.5
OVERLAP_THRESH: 0.5
STUFF_AREA_LIMIT: 4096
INSTANCE_LOSS_WEIGHT: 1.0
PIXEL_MEAN: [103.53, 116.28, 123.675]
PIXEL_STD: [1.0, 1.0, 1.0]
PROPOSAL_GENERATOR:
MIN_SIZE: 0
NAME: RPN
RESNETS:
DEFORM_MODULATED: False
DEFORM_NUM_GROUPS: 1
DEFORM_ON_PER_STAGE: [False, False, False, False]
DEPTH: 50
NORM: FrozenBN
NUM_GROUPS: 1
OUT_FEATURES: ['res3', 'res4', 'res5']
RES2_OUT_CHANNELS: 256
RES5_DILATION: 1
STEM_OUT_CHANNELS: 64
STRIDE_IN_1X1: True
WIDTH_PER_GROUP: 64
RETINANET:
BBOX_REG_WEIGHTS: (1.0, 1.0, 1.0, 1.0)
FOCAL_LOSS_ALPHA: 0.25
FOCAL_LOSS_GAMMA: 2.0
IN_FEATURES: ['p3', 'p4', 'p5', 'p6', 'p7']
IOU_LABELS: [0, -1, 1]
IOU_THRESHOLDS: [0.4, 0.5]
NMS_THRESH_TEST: 0.5
NUM_CLASSES: 80
NUM_CONVS: 4
PRIOR_PROB: 0.01
SCORE_THRESH_TEST: 0.05
SMOOTH_L1_LOSS_BETA: 0.1
TOPK_CANDIDATES_TEST: 1000
ROI_BOX_CASCADE_HEAD:
BBOX_REG_WEIGHTS: ((10.0, 10.0, 5.0, 5.0), (20.0, 20.0, 10.0, 10.0), (30.0, 30.0, 15.0, 15.0))
IOUS: (0.5, 0.6, 0.7)
ROI_BOX_HEAD:
BBOX_REG_WEIGHTS: (10.0, 10.0, 5.0, 5.0)
CLS_AGNOSTIC_BBOX_REG: False
CONV_DIM: 256
FC_DIM: 1024
NAME:
NORM:
NUM_CONV: 0
NUM_FC: 0
POOLER_RESOLUTION: 14
POOLER_SAMPLING_RATIO: 0
POOLER_TYPE: ROIAlignV2
SMOOTH_L1_BETA: 0.0
ROI_HEADS:
BATCH_SIZE_PER_IMAGE: 512
IN_FEATURES: ['res4']
IOU_LABELS: [0, 1]
IOU_THRESHOLDS: [0.5]
NAME: Res5ROIHeads
NMS_THRESH_TEST: 0.5
NUM_CLASSES: 80
POSITIVE_FRACTION: 0.25
PROPOSAL_APPEND_GT: True
SCORE_THRESH_TEST: 0.05
ROI_KEYPOINT_HEAD:
CONV_DIMS: (512, 512, 512, 512, 512, 512, 512, 512)
LOSS_WEIGHT: 1.0
MIN_KEYPOINTS_PER_IMAGE: 1
NAME: KRCNNConvDeconvUpsampleHead
NORMALIZE_LOSS_BY_VISIBLE_KEYPOINTS: True
NUM_KEYPOINTS: 17
POOLER_RESOLUTION: 14
POOLER_SAMPLING_RATIO: 0
POOLER_TYPE: ROIAlignV2
ROI_MASK_HEAD:
CLS_AGNOSTIC_MASK: True
CONV_DIM: 256
NAME: MaskRCNNConvUpsampleHead
NORM:
NUM_CONV: 4
POOLER_RESOLUTION: 14
POOLER_SAMPLING_RATIO: 0
POOLER_TYPE: ROIAlignV2
RPN:
BATCH_SIZE_PER_IMAGE: 256
BBOX_REG_WEIGHTS: (1.0, 1.0, 1.0, 1.0)
BOUNDARY_THRESH: -1
HEAD_NAME: StandardRPNHead
IN_FEATURES: ['res4']
IOU_LABELS: [0, -1, 1]
IOU_THRESHOLDS: [0.3, 0.7]
LOSS_WEIGHT: 1.0
NMS_THRESH: 0.7
POSITIVE_FRACTION: 0.5
POST_NMS_TOPK_TEST: 1000
POST_NMS_TOPK_TRAIN: 2000
PRE_NMS_TOPK_TEST: 6000
PRE_NMS_TOPK_TRAIN: 12000
SMOOTH_L1_BETA: 0.0
SEM_SEG_HEAD:
COMMON_STRIDE: 4
CONVS_DIM: 128
IGNORE_VALUE: 255
IN_FEATURES: ['p2', 'p3', 'p4', 'p5']
LOSS_WEIGHT: 1.0
NAME: SemSegFPNHead
NORM: GN
NUM_CLASSES: 54
WEIGHTS: /home/zhangjian/code/BCNet/pretrained_models/R-50.pkl
OUTPUT_DIR: ./output
SEED: 41965809
SOLVER:
BASE_LR: 0.01
BIAS_LR_FACTOR: 1.0
CHECKPOINT_PERIOD: 20000
GAMMA: 0.1
IMS_PER_BATCH: 2
LR_SCHEDULER_NAME: WarmupMultiStepLR
MAX_ITER: 90000
MOMENTUM: 0.9
STEPS: (60000, 80000)
WARMUP_FACTOR: 0.001
WARMUP_ITERS: 1000
WARMUP_METHOD: linear
WEIGHT_DECAY: 0.0001
WEIGHT_DECAY_BIAS: 0.0001
WEIGHT_DECAY_NORM: 0.0
TEST:
AUG:
ENABLED: False
FLIP: True
MAX_SIZE: 4000
MIN_SIZES: (400, 500, 600, 700, 800, 900, 1000, 1100, 1200)
DETECTIONS_PER_IMAGE: 100
EVAL_PERIOD: 0
EXPECTED_RESULTS: []
KEYPOINT_OKS_SIGMAS: []
PRECISE_BN:
ENABLED: False
NUM_ITER: 200
VERSION: 2
VIS_PERIOD: 0
�[32m[08/10 20:20:51 detectron2]: �[0mFull config saved to /home/zhangjian/code/BCNet/output/config.yaml
�[32m[08/10 20:20:53 d2.engine.defaults]: �[0mModel:
FCOS(
(backbone): FPN(
(fpn_lateral3): Conv2d(512, 256, kernel_size=(1, 1), stride=(1, 1))
(fpn_output3): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(fpn_lateral4): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1))
(fpn_output4): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(fpn_lateral5): Conv2d(2048, 256, kernel_size=(1, 1), stride=(1, 1))
(fpn_output5): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(top_block): LastLevelP6P7(
(p6): Conv2d(256, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1))
(p7): Conv2d(256, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1))
)
(bottom_up): ResNet(
(stem): BasicStem(
(conv1): Conv2d(
3, 64, kernel_size=(7, 7), stride=(2, 2), padding=(3, 3), bias=False
(norm): FrozenBatchNorm2d(num_features=64, eps=1e-05)
)
)
(res2): Sequential(
(0): BottleneckBlock(
(shortcut): Conv2d(
64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
)
(conv1): Conv2d(
64, 64, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=64, eps=1e-05)
)
(conv2): Conv2d(
64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=64, eps=1e-05)
)
(conv3): Conv2d(
64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
)
)
(1): BottleneckBlock(
(conv1): Conv2d(
256, 64, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=64, eps=1e-05)
)
(conv2): Conv2d(
64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=64, eps=1e-05)
)
(conv3): Conv2d(
64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
)
)
(2): BottleneckBlock(
(conv1): Conv2d(
256, 64, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=64, eps=1e-05)
)
(conv2): Conv2d(
64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=64, eps=1e-05)
)
(conv3): Conv2d(
64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
)
)
)
(res3): Sequential(
(0): BottleneckBlock(
(shortcut): Conv2d(
256, 512, kernel_size=(1, 1), stride=(2, 2), bias=False
(norm): FrozenBatchNorm2d(num_features=512, eps=1e-05)
)
(conv1): Conv2d(
256, 128, kernel_size=(1, 1), stride=(2, 2), bias=False
(norm): FrozenBatchNorm2d(num_features=128, eps=1e-05)
)
(conv2): Conv2d(
128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=128, eps=1e-05)
)
(conv3): Conv2d(
128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=512, eps=1e-05)
)
)
(1): BottleneckBlock(
(conv1): Conv2d(
512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=128, eps=1e-05)
)
(conv2): Conv2d(
128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=128, eps=1e-05)
)
(conv3): Conv2d(
128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=512, eps=1e-05)
)
)
(2): BottleneckBlock(
(conv1): Conv2d(
512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=128, eps=1e-05)
)
(conv2): Conv2d(
128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=128, eps=1e-05)
)
(conv3): Conv2d(
128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=512, eps=1e-05)
)
)
(3): BottleneckBlock(
(conv1): Conv2d(
512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=128, eps=1e-05)
)
(conv2): Conv2d(
128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=128, eps=1e-05)
)
(conv3): Conv2d(
128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=512, eps=1e-05)
)
)
)
(res4): Sequential(
(0): BottleneckBlock(
(shortcut): Conv2d(
512, 1024, kernel_size=(1, 1), stride=(2, 2), bias=False
(norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
)
(conv1): Conv2d(
512, 256, kernel_size=(1, 1), stride=(2, 2), bias=False
(norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
)
(conv2): Conv2d(
256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
)
(conv3): Conv2d(
256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
)
)
(1): BottleneckBlock(
(conv1): Conv2d(
1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
)
(conv2): Conv2d(
256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
)
(conv3): Conv2d(
256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
)
)
(2): BottleneckBlock(
(conv1): Conv2d(
1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
)
(conv2): Conv2d(
256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
)
(conv3): Conv2d(
256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
)
)
(3): BottleneckBlock(
(conv1): Conv2d(
1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
)
(conv2): Conv2d(
256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
)
(conv3): Conv2d(
256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
)
)
(4): BottleneckBlock(
(conv1): Conv2d(
1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
)
(conv2): Conv2d(
256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
)
(conv3): Conv2d(
256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
)
)
(5): BottleneckBlock(
(conv1): Conv2d(
1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
)
(conv2): Conv2d(
256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
)
(conv3): Conv2d(
256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
)
)
)
(res5): Sequential(
(0): BottleneckBlock(
(shortcut): Conv2d(
1024, 2048, kernel_size=(1, 1), stride=(2, 2), bias=False
(norm): FrozenBatchNorm2d(num_features=2048, eps=1e-05)
)
(conv1): Conv2d(
1024, 512, kernel_size=(1, 1), stride=(2, 2), bias=False
(norm): FrozenBatchNorm2d(num_features=512, eps=1e-05)
)
(conv2): Conv2d(
512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=512, eps=1e-05)
)
(conv3): Conv2d(
512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=2048, eps=1e-05)
)
)
(1): BottleneckBlock(
(conv1): Conv2d(
2048, 512, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=512, eps=1e-05)
)
(conv2): Conv2d(
512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=512, eps=1e-05)
)
(conv3): Conv2d(
512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=2048, eps=1e-05)
)
)
(2): BottleneckBlock(
(conv1): Conv2d(
2048, 512, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=512, eps=1e-05)
)
(conv2): Conv2d(
512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=512, eps=1e-05)
)
(conv3): Conv2d(
512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False
(norm): FrozenBatchNorm2d(num_features=2048, eps=1e-05)
)
)
)
)
)
(box_selector): FCOSPostProcessor()
(head): FCOSHead(
(cls_tower): Sequential(
(0): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(1): GroupNorm(32, 256, eps=1e-05, affine=True)
(2): ReLU()
(3): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(4): GroupNorm(32, 256, eps=1e-05, affine=True)
(5): ReLU()
(6): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(7): GroupNorm(32, 256, eps=1e-05, affine=True)
(8): ReLU()
(9): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(10): GroupNorm(32, 256, eps=1e-05, affine=True)
(11): ReLU()
)
(bbox_tower): Sequential(
(0): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(1): GroupNorm(32, 256, eps=1e-05, affine=True)
(2): ReLU()
(3): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(4): GroupNorm(32, 256, eps=1e-05, affine=True)
(5): ReLU()
(6): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(7): GroupNorm(32, 256, eps=1e-05, affine=True)
(8): ReLU()
(9): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(10): GroupNorm(32, 256, eps=1e-05, affine=True)
(11): ReLU()
)
(cls_logits): Conv2d(256, 80, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(bbox_pred): Conv2d(256, 4, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(centerness): Conv2d(256, 1, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(scales): ModuleList(
(0): Scale()
(1): Scale()
(2): Scale()
(3): Scale()
(4): Scale()
)
)
(mask_pooler): ROIPooler(
(level_poolers): ModuleList(
(0): ROIAlign(output_size=(14, 14), spatial_scale=0.125, sampling_ratio=0, aligned=True)
(1): ROIAlign(output_size=(14, 14), spatial_scale=0.0625, sampling_ratio=0, aligned=True)
(2): ROIAlign(output_size=(14, 14), spatial_scale=0.03125, sampling_ratio=0, aligned=True)
(3): ROIAlign(output_size=(14, 14), spatial_scale=0.015625, sampling_ratio=0, aligned=True)
(4): ROIAlign(output_size=(14, 14), spatial_scale=0.0078125, sampling_ratio=0, aligned=True)
)
)
(mask_head): MaskRCNNConvUpsampleHead(
(mask_fcn1): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(mask_fcn2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(mask_fcn3): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(mask_fcn4): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(boundary_fcn1): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(boundary_fcn2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(boundary_fcn3): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(boundary_fcn4): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(deconv): ConvTranspose2d(256, 256, kernel_size=(2, 2), stride=(2, 2))
(boundary_deconv_bo): ConvTranspose2d(256, 256, kernel_size=(2, 2), stride=(2, 2))
(boundary_deconv): ConvTranspose2d(256, 256, kernel_size=(2, 2), stride=(2, 2))
(bo_deconv): ConvTranspose2d(256, 256, kernel_size=(2, 2), stride=(2, 2))
(query_transform_bound_bo): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(key_transform_bound_bo): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(value_transform_bound_bo): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(output_transform_bound_bo): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(query_transform_bound): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(key_transform_bound): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(value_transform_bound): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(output_transform_bound): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(blocker_bound_bo): BatchNorm2d(256, eps=0.0001, momentum=0.1, affine=True, track_running_stats=True)
(blocker_bound): BatchNorm2d(256, eps=0.0001, momentum=0.1, affine=True, track_running_stats=True)
(predictor): Conv2d(256, 1, kernel_size=(1, 1), stride=(1, 1))
(predictor_bo): Conv2d(256, 1, kernel_size=(1, 1), stride=(1, 1))
(boundary_predictor_bo): Conv2d(256, 1, kernel_size=(1, 1), stride=(1, 1))
(boundary_predictor): Conv2d(256, 1, kernel_size=(1, 1), stride=(1, 1))
)
)
�[32m[08/10 20:24:06 d2.data.datasets.coco]: �[0mLoading datasets/coco/annotations/instances_train_2017_transform_slight_correct.json takes 193.00 seconds.
�[32m[08/10 20:24:08 d2.data.datasets.coco]: �[0mLoaded 118287 images in COCO format from datasets/coco/annotations/instances_train_2017_transform_slight_correct.json
�[32m[08/10 20:24:18 d2.data.build]: �[0mRemoved 1021 images with no usable annotations. 117266 images left.
�[32m[08/10 20:24:21 d2.data.build]: �[0mDistribution of instances among all 80 categories:
�[36m| category | #instances | category | #instances | category | #instances |
|:-------------:|:-------------|:------------:|:-------------|:-------------:|:-------------|
| person | 257253 | bicycle | 7056 | car | 43533 |
| motorcycle | 8654 | airplane | 5129 | bus | 6061 |
| train | 4570 | truck | 9970 | boat | 10576 |
| traffic light | 12842 | fire hydrant | 1865 | stop sign | 1983 |
| parking meter | 1283 | bench | 9820 | bird | 10542 |
| cat | 4766 | dog | 5500 | horse | 6567 |
| sheep | 9223 | cow | 8014 | elephant | 5484 |
| bear | 1294 | zebra | 5269 | giraffe | 5128 |
| backpack | 8714 | umbrella | 11265 | handbag | 12342 |
| tie | 6448 | suitcase | 6112 | frisbee | 2681 |
| skis | 6623 | snowboard | 2681 | sports ball | 6299 |
| kite | 8802 | baseball bat | 3273 | baseball gl.. | 3747 |
| skateboard | 5536 | surfboard | 6095 | tennis racket | 4807 |
| bottle | 24070 | wine glass | 7839 | cup | 20574 |
| fork | 5474 | knife | 7760 | spoon | 6159 |
| bowl | 14323 | banana | 9195 | apple | 5776 |
| sandwich | 4356 | orange | 6302 | broccoli | 7261 |
| carrot | 7758 | hot dog | 2884 | pizza | 5807 |
| donut | 7005 | cake | 6296 | chair | 38073 |
| couch | 5779 | potted plant | 8631 | bed | 4192 |
| dining table | 15695 | toilet | 4149 | tv | 5803 |
| laptop | 4960 | mouse | 2261 | remote | 5700 |
| keyboard | 2854 | cell phone | 6422 | microwave | 1672 |
| oven | 3334 | toaster | 225 | sink | 5609 |
| refrigerator | 2634 | book | 24077 | clock | 6320 |
| vase | 6577 | scissors | 1464 | teddy bear | 4729 |
| hair drier | 198 | toothbrush | 1945 | | |
| total | 849949 | | | | |�[0m
�[32m[08/10 20:24:21 d2.data.common]: �[0mSerializing 117266 elements to byte tensors and concatenating them all ...
�[32m[08/10 20:24:24 d2.data.common]: �[0mSerialized dataset takes 655.57 MiB
�[32m[08/10 20:24:24 d2.data.detection_utils]: �[0mTransformGens used in training: [ResizeShortestEdge(short_edge_length=(600,), max_size=900, sample_style='choice'), RandomFlip()]
�[32m[08/10 20:24:24 d2.data.build]: �[0mUsing training sampler TrainingSampler
�[32m[08/10 20:24:38 fvcore.common.checkpoint]: �[0m[Checkpointer] Loading from /home/zhangjian/code/BCNet/pretrained_models/R-50.pkl ...
�[32m[08/10 20:24:40 d2.checkpoint.c2_model_loading]: �[0mRemapping C2 weights ......
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res2.0.conv1.norm.bias loaded from res2_0_branch2a_bn_beta of shape (64,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res2.0.conv1.norm.running_mean loaded from res2_0_branch2a_bn_running_mean of shape (64,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res2.0.conv1.norm.running_var loaded from res2_0_branch2a_bn_running_var of shape (64,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res2.0.conv1.norm.weight loaded from res2_0_branch2a_bn_gamma of shape (64,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res2.0.conv1.weight loaded from res2_0_branch2a_w of shape (64, 64, 1, 1)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res2.0.conv2.norm.bias loaded from res2_0_branch2b_bn_beta of shape (64,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res2.0.conv2.norm.running_mean loaded from res2_0_branch2b_bn_running_mean of shape (64,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res2.0.conv2.norm.running_var loaded from res2_0_branch2b_bn_running_var of shape (64,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res2.0.conv2.norm.weight loaded from res2_0_branch2b_bn_gamma of shape (64,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res2.0.conv2.weight loaded from res2_0_branch2b_w of shape (64, 64, 3, 3)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res2.0.conv3.norm.bias loaded from res2_0_branch2c_bn_beta of shape (256,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res2.0.conv3.norm.running_mean loaded from res2_0_branch2c_bn_running_mean of shape (256,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res2.0.conv3.norm.running_var loaded from res2_0_branch2c_bn_running_var of shape (256,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res2.0.conv3.norm.weight loaded from res2_0_branch2c_bn_gamma of shape (256,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res2.0.conv3.weight loaded from res2_0_branch2c_w of shape (256, 64, 1, 1)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res2.0.shortcut.norm.bias loaded from res2_0_branch1_bn_beta of shape (256,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res2.0.shortcut.norm.running_mean loaded from res2_0_branch1_bn_running_mean of shape (256,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res2.0.shortcut.norm.running_var loaded from res2_0_branch1_bn_running_var of shape (256,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res2.0.shortcut.norm.weight loaded from res2_0_branch1_bn_gamma of shape (256,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res2.0.shortcut.weight loaded from res2_0_branch1_w of shape (256, 64, 1, 1)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res2.1.conv1.norm.bias loaded from res2_1_branch2a_bn_beta of shape (64,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res2.1.conv1.norm.running_mean loaded from res2_1_branch2a_bn_running_mean of shape (64,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res2.1.conv1.norm.running_var loaded from res2_1_branch2a_bn_running_var of shape (64,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res2.1.conv1.norm.weight loaded from res2_1_branch2a_bn_gamma of shape (64,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res2.1.conv1.weight loaded from res2_1_branch2a_w of shape (64, 256, 1, 1)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res2.1.conv2.norm.bias loaded from res2_1_branch2b_bn_beta of shape (64,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res2.1.conv2.norm.running_mean loaded from res2_1_branch2b_bn_running_mean of shape (64,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res2.1.conv2.norm.running_var loaded from res2_1_branch2b_bn_running_var of shape (64,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res2.1.conv2.norm.weight loaded from res2_1_branch2b_bn_gamma of shape (64,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res2.1.conv2.weight loaded from res2_1_branch2b_w of shape (64, 64, 3, 3)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res2.1.conv3.norm.bias loaded from res2_1_branch2c_bn_beta of shape (256,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res2.1.conv3.norm.running_mean loaded from res2_1_branch2c_bn_running_mean of shape (256,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res2.1.conv3.norm.running_var loaded from res2_1_branch2c_bn_running_var of shape (256,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res2.1.conv3.norm.weight loaded from res2_1_branch2c_bn_gamma of shape (256,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res2.1.conv3.weight loaded from res2_1_branch2c_w of shape (256, 64, 1, 1)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res2.2.conv1.norm.bias loaded from res2_2_branch2a_bn_beta of shape (64,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res2.2.conv1.norm.running_mean loaded from res2_2_branch2a_bn_running_mean of shape (64,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res2.2.conv1.norm.running_var loaded from res2_2_branch2a_bn_running_var of shape (64,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res2.2.conv1.norm.weight loaded from res2_2_branch2a_bn_gamma of shape (64,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res2.2.conv1.weight loaded from res2_2_branch2a_w of shape (64, 256, 1, 1)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res2.2.conv2.norm.bias loaded from res2_2_branch2b_bn_beta of shape (64,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res2.2.conv2.norm.running_mean loaded from res2_2_branch2b_bn_running_mean of shape (64,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res2.2.conv2.norm.running_var loaded from res2_2_branch2b_bn_running_var of shape (64,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res2.2.conv2.norm.weight loaded from res2_2_branch2b_bn_gamma of shape (64,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res2.2.conv2.weight loaded from res2_2_branch2b_w of shape (64, 64, 3, 3)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res2.2.conv3.norm.bias loaded from res2_2_branch2c_bn_beta of shape (256,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res2.2.conv3.norm.running_mean loaded from res2_2_branch2c_bn_running_mean of shape (256,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res2.2.conv3.norm.running_var loaded from res2_2_branch2c_bn_running_var of shape (256,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res2.2.conv3.norm.weight loaded from res2_2_branch2c_bn_gamma of shape (256,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res2.2.conv3.weight loaded from res2_2_branch2c_w of shape (256, 64, 1, 1)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res3.0.conv1.norm.bias loaded from res3_0_branch2a_bn_beta of shape (128,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res3.0.conv1.norm.running_mean loaded from res3_0_branch2a_bn_running_mean of shape (128,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res3.0.conv1.norm.running_var loaded from res3_0_branch2a_bn_running_var of shape (128,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res3.0.conv1.norm.weight loaded from res3_0_branch2a_bn_gamma of shape (128,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res3.0.conv1.weight loaded from res3_0_branch2a_w of shape (128, 256, 1, 1)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res3.0.conv2.norm.bias loaded from res3_0_branch2b_bn_beta of shape (128,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res3.0.conv2.norm.running_mean loaded from res3_0_branch2b_bn_running_mean of shape (128,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res3.0.conv2.norm.running_var loaded from res3_0_branch2b_bn_running_var of shape (128,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res3.0.conv2.norm.weight loaded from res3_0_branch2b_bn_gamma of shape (128,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res3.0.conv2.weight loaded from res3_0_branch2b_w of shape (128, 128, 3, 3)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res3.0.conv3.norm.bias loaded from res3_0_branch2c_bn_beta of shape (512,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res3.0.conv3.norm.running_mean loaded from res3_0_branch2c_bn_running_mean of shape (512,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res3.0.conv3.norm.running_var loaded from res3_0_branch2c_bn_running_var of shape (512,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res3.0.conv3.norm.weight loaded from res3_0_branch2c_bn_gamma of shape (512,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res3.0.conv3.weight loaded from res3_0_branch2c_w of shape (512, 128, 1, 1)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res3.0.shortcut.norm.bias loaded from res3_0_branch1_bn_beta of shape (512,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res3.0.shortcut.norm.running_mean loaded from res3_0_branch1_bn_running_mean of shape (512,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res3.0.shortcut.norm.running_var loaded from res3_0_branch1_bn_running_var of shape (512,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res3.0.shortcut.norm.weight loaded from res3_0_branch1_bn_gamma of shape (512,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res3.0.shortcut.weight loaded from res3_0_branch1_w of shape (512, 256, 1, 1)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res3.1.conv1.norm.bias loaded from res3_1_branch2a_bn_beta of shape (128,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res3.1.conv1.norm.running_mean loaded from res3_1_branch2a_bn_running_mean of shape (128,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res3.1.conv1.norm.running_var loaded from res3_1_branch2a_bn_running_var of shape (128,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res3.1.conv1.norm.weight loaded from res3_1_branch2a_bn_gamma of shape (128,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res3.1.conv1.weight loaded from res3_1_branch2a_w of shape (128, 512, 1, 1)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res3.1.conv2.norm.bias loaded from res3_1_branch2b_bn_beta of shape (128,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res3.1.conv2.norm.running_mean loaded from res3_1_branch2b_bn_running_mean of shape (128,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res3.1.conv2.norm.running_var loaded from res3_1_branch2b_bn_running_var of shape (128,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res3.1.conv2.norm.weight loaded from res3_1_branch2b_bn_gamma of shape (128,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res3.1.conv2.weight loaded from res3_1_branch2b_w of shape (128, 128, 3, 3)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res3.1.conv3.norm.bias loaded from res3_1_branch2c_bn_beta of shape (512,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res3.1.conv3.norm.running_mean loaded from res3_1_branch2c_bn_running_mean of shape (512,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res3.1.conv3.norm.running_var loaded from res3_1_branch2c_bn_running_var of shape (512,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res3.1.conv3.norm.weight loaded from res3_1_branch2c_bn_gamma of shape (512,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res3.1.conv3.weight loaded from res3_1_branch2c_w of shape (512, 128, 1, 1)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res3.2.conv1.norm.bias loaded from res3_2_branch2a_bn_beta of shape (128,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res3.2.conv1.norm.running_mean loaded from res3_2_branch2a_bn_running_mean of shape (128,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res3.2.conv1.norm.running_var loaded from res3_2_branch2a_bn_running_var of shape (128,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res3.2.conv1.norm.weight loaded from res3_2_branch2a_bn_gamma of shape (128,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res3.2.conv1.weight loaded from res3_2_branch2a_w of shape (128, 512, 1, 1)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res3.2.conv2.norm.bias loaded from res3_2_branch2b_bn_beta of shape (128,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res3.2.conv2.norm.running_mean loaded from res3_2_branch2b_bn_running_mean of shape (128,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res3.2.conv2.norm.running_var loaded from res3_2_branch2b_bn_running_var of shape (128,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res3.2.conv2.norm.weight loaded from res3_2_branch2b_bn_gamma of shape (128,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res3.2.conv2.weight loaded from res3_2_branch2b_w of shape (128, 128, 3, 3)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res3.2.conv3.norm.bias loaded from res3_2_branch2c_bn_beta of shape (512,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res3.2.conv3.norm.running_mean loaded from res3_2_branch2c_bn_running_mean of shape (512,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res3.2.conv3.norm.running_var loaded from res3_2_branch2c_bn_running_var of shape (512,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res3.2.conv3.norm.weight loaded from res3_2_branch2c_bn_gamma of shape (512,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res3.2.conv3.weight loaded from res3_2_branch2c_w of shape (512, 128, 1, 1)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res3.3.conv1.norm.bias loaded from res3_3_branch2a_bn_beta of shape (128,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res3.3.conv1.norm.running_mean loaded from res3_3_branch2a_bn_running_mean of shape (128,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res3.3.conv1.norm.running_var loaded from res3_3_branch2a_bn_running_var of shape (128,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res3.3.conv1.norm.weight loaded from res3_3_branch2a_bn_gamma of shape (128,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res3.3.conv1.weight loaded from res3_3_branch2a_w of shape (128, 512, 1, 1)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res3.3.conv2.norm.bias loaded from res3_3_branch2b_bn_beta of shape (128,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res3.3.conv2.norm.running_mean loaded from res3_3_branch2b_bn_running_mean of shape (128,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res3.3.conv2.norm.running_var loaded from res3_3_branch2b_bn_running_var of shape (128,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res3.3.conv2.norm.weight loaded from res3_3_branch2b_bn_gamma of shape (128,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res3.3.conv2.weight loaded from res3_3_branch2b_w of shape (128, 128, 3, 3)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res3.3.conv3.norm.bias loaded from res3_3_branch2c_bn_beta of shape (512,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res3.3.conv3.norm.running_mean loaded from res3_3_branch2c_bn_running_mean of shape (512,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res3.3.conv3.norm.running_var loaded from res3_3_branch2c_bn_running_var of shape (512,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res3.3.conv3.norm.weight loaded from res3_3_branch2c_bn_gamma of shape (512,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res3.3.conv3.weight loaded from res3_3_branch2c_w of shape (512, 128, 1, 1)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res4.0.conv1.norm.bias loaded from res4_0_branch2a_bn_beta of shape (256,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res4.0.conv1.norm.running_mean loaded from res4_0_branch2a_bn_running_mean of shape (256,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res4.0.conv1.norm.running_var loaded from res4_0_branch2a_bn_running_var of shape (256,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res4.0.conv1.norm.weight loaded from res4_0_branch2a_bn_gamma of shape (256,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res4.0.conv1.weight loaded from res4_0_branch2a_w of shape (256, 512, 1, 1)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res4.0.conv2.norm.bias loaded from res4_0_branch2b_bn_beta of shape (256,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res4.0.conv2.norm.running_mean loaded from res4_0_branch2b_bn_running_mean of shape (256,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res4.0.conv2.norm.running_var loaded from res4_0_branch2b_bn_running_var of shape (256,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res4.0.conv2.norm.weight loaded from res4_0_branch2b_bn_gamma of shape (256,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res4.0.conv2.weight loaded from res4_0_branch2b_w of shape (256, 256, 3, 3)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res4.0.conv3.norm.bias loaded from res4_0_branch2c_bn_beta of shape (1024,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res4.0.conv3.norm.running_mean loaded from res4_0_branch2c_bn_running_mean of shape (1024,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res4.0.conv3.norm.running_var loaded from res4_0_branch2c_bn_running_var of shape (1024,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res4.0.conv3.norm.weight loaded from res4_0_branch2c_bn_gamma of shape (1024,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res4.0.conv3.weight loaded from res4_0_branch2c_w of shape (1024, 256, 1, 1)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res4.0.shortcut.norm.bias loaded from res4_0_branch1_bn_beta of shape (1024,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res4.0.shortcut.norm.running_mean loaded from res4_0_branch1_bn_running_mean of shape (1024,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res4.0.shortcut.norm.running_var loaded from res4_0_branch1_bn_running_var of shape (1024,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res4.0.shortcut.norm.weight loaded from res4_0_branch1_bn_gamma of shape (1024,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res4.0.shortcut.weight loaded from res4_0_branch1_w of shape (1024, 512, 1, 1)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res4.1.conv1.norm.bias loaded from res4_1_branch2a_bn_beta of shape (256,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res4.1.conv1.norm.running_mean loaded from res4_1_branch2a_bn_running_mean of shape (256,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res4.1.conv1.norm.running_var loaded from res4_1_branch2a_bn_running_var of shape (256,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res4.1.conv1.norm.weight loaded from res4_1_branch2a_bn_gamma of shape (256,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res4.1.conv1.weight loaded from res4_1_branch2a_w of shape (256, 1024, 1, 1)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res4.1.conv2.norm.bias loaded from res4_1_branch2b_bn_beta of shape (256,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res4.1.conv2.norm.running_mean loaded from res4_1_branch2b_bn_running_mean of shape (256,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res4.1.conv2.norm.running_var loaded from res4_1_branch2b_bn_running_var of shape (256,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res4.1.conv2.norm.weight loaded from res4_1_branch2b_bn_gamma of shape (256,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res4.1.conv2.weight loaded from res4_1_branch2b_w of shape (256, 256, 3, 3)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res4.1.conv3.norm.bias loaded from res4_1_branch2c_bn_beta of shape (1024,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res4.1.conv3.norm.running_mean loaded from res4_1_branch2c_bn_running_mean of shape (1024,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res4.1.conv3.norm.running_var loaded from res4_1_branch2c_bn_running_var of shape (1024,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res4.1.conv3.norm.weight loaded from res4_1_branch2c_bn_gamma of shape (1024,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res4.1.conv3.weight loaded from res4_1_branch2c_w of shape (1024, 256, 1, 1)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res4.2.conv1.norm.bias loaded from res4_2_branch2a_bn_beta of shape (256,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res4.2.conv1.norm.running_mean loaded from res4_2_branch2a_bn_running_mean of shape (256,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res4.2.conv1.norm.running_var loaded from res4_2_branch2a_bn_running_var of shape (256,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res4.2.conv1.norm.weight loaded from res4_2_branch2a_bn_gamma of shape (256,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res4.2.conv1.weight loaded from res4_2_branch2a_w of shape (256, 1024, 1, 1)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res4.2.conv2.norm.bias loaded from res4_2_branch2b_bn_beta of shape (256,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res4.2.conv2.norm.running_mean loaded from res4_2_branch2b_bn_running_mean of shape (256,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res4.2.conv2.norm.running_var loaded from res4_2_branch2b_bn_running_var of shape (256,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res4.2.conv2.norm.weight loaded from res4_2_branch2b_bn_gamma of shape (256,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res4.2.conv2.weight loaded from res4_2_branch2b_w of shape (256, 256, 3, 3)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res4.2.conv3.norm.bias loaded from res4_2_branch2c_bn_beta of shape (1024,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res4.2.conv3.norm.running_mean loaded from res4_2_branch2c_bn_running_mean of shape (1024,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res4.2.conv3.norm.running_var loaded from res4_2_branch2c_bn_running_var of shape (1024,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res4.2.conv3.norm.weight loaded from res4_2_branch2c_bn_gamma of shape (1024,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res4.2.conv3.weight loaded from res4_2_branch2c_w of shape (1024, 256, 1, 1)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res4.3.conv1.norm.bias loaded from res4_3_branch2a_bn_beta of shape (256,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res4.3.conv1.norm.running_mean loaded from res4_3_branch2a_bn_running_mean of shape (256,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res4.3.conv1.norm.running_var loaded from res4_3_branch2a_bn_running_var of shape (256,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res4.3.conv1.norm.weight loaded from res4_3_branch2a_bn_gamma of shape (256,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res4.3.conv1.weight loaded from res4_3_branch2a_w of shape (256, 1024, 1, 1)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res4.3.conv2.norm.bias loaded from res4_3_branch2b_bn_beta of shape (256,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res4.3.conv2.norm.running_mean loaded from res4_3_branch2b_bn_running_mean of shape (256,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res4.3.conv2.norm.running_var loaded from res4_3_branch2b_bn_running_var of shape (256,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res4.3.conv2.norm.weight loaded from res4_3_branch2b_bn_gamma of shape (256,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res4.3.conv2.weight loaded from res4_3_branch2b_w of shape (256, 256, 3, 3)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res4.3.conv3.norm.bias loaded from res4_3_branch2c_bn_beta of shape (1024,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res4.3.conv3.norm.running_mean loaded from res4_3_branch2c_bn_running_mean of shape (1024,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res4.3.conv3.norm.running_var loaded from res4_3_branch2c_bn_running_var of shape (1024,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res4.3.conv3.norm.weight loaded from res4_3_branch2c_bn_gamma of shape (1024,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res4.3.conv3.weight loaded from res4_3_branch2c_w of shape (1024, 256, 1, 1)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res4.4.conv1.norm.bias loaded from res4_4_branch2a_bn_beta of shape (256,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res4.4.conv1.norm.running_mean loaded from res4_4_branch2a_bn_running_mean of shape (256,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res4.4.conv1.norm.running_var loaded from res4_4_branch2a_bn_running_var of shape (256,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res4.4.conv1.norm.weight loaded from res4_4_branch2a_bn_gamma of shape (256,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res4.4.conv1.weight loaded from res4_4_branch2a_w of shape (256, 1024, 1, 1)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res4.4.conv2.norm.bias loaded from res4_4_branch2b_bn_beta of shape (256,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res4.4.conv2.norm.running_mean loaded from res4_4_branch2b_bn_running_mean of shape (256,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res4.4.conv2.norm.running_var loaded from res4_4_branch2b_bn_running_var of shape (256,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res4.4.conv2.norm.weight loaded from res4_4_branch2b_bn_gamma of shape (256,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res4.4.conv2.weight loaded from res4_4_branch2b_w of shape (256, 256, 3, 3)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res4.4.conv3.norm.bias loaded from res4_4_branch2c_bn_beta of shape (1024,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res4.4.conv3.norm.running_mean loaded from res4_4_branch2c_bn_running_mean of shape (1024,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res4.4.conv3.norm.running_var loaded from res4_4_branch2c_bn_running_var of shape (1024,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res4.4.conv3.norm.weight loaded from res4_4_branch2c_bn_gamma of shape (1024,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res4.4.conv3.weight loaded from res4_4_branch2c_w of shape (1024, 256, 1, 1)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res4.5.conv1.norm.bias loaded from res4_5_branch2a_bn_beta of shape (256,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res4.5.conv1.norm.running_mean loaded from res4_5_branch2a_bn_running_mean of shape (256,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res4.5.conv1.norm.running_var loaded from res4_5_branch2a_bn_running_var of shape (256,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res4.5.conv1.norm.weight loaded from res4_5_branch2a_bn_gamma of shape (256,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res4.5.conv1.weight loaded from res4_5_branch2a_w of shape (256, 1024, 1, 1)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res4.5.conv2.norm.bias loaded from res4_5_branch2b_bn_beta of shape (256,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res4.5.conv2.norm.running_mean loaded from res4_5_branch2b_bn_running_mean of shape (256,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res4.5.conv2.norm.running_var loaded from res4_5_branch2b_bn_running_var of shape (256,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res4.5.conv2.norm.weight loaded from res4_5_branch2b_bn_gamma of shape (256,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res4.5.conv2.weight loaded from res4_5_branch2b_w of shape (256, 256, 3, 3)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res4.5.conv3.norm.bias loaded from res4_5_branch2c_bn_beta of shape (1024,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res4.5.conv3.norm.running_mean loaded from res4_5_branch2c_bn_running_mean of shape (1024,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res4.5.conv3.norm.running_var loaded from res4_5_branch2c_bn_running_var of shape (1024,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res4.5.conv3.norm.weight loaded from res4_5_branch2c_bn_gamma of shape (1024,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res4.5.conv3.weight loaded from res4_5_branch2c_w of shape (1024, 256, 1, 1)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res5.0.conv1.norm.bias loaded from res5_0_branch2a_bn_beta of shape (512,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res5.0.conv1.norm.running_mean loaded from res5_0_branch2a_bn_running_mean of shape (512,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res5.0.conv1.norm.running_var loaded from res5_0_branch2a_bn_running_var of shape (512,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res5.0.conv1.norm.weight loaded from res5_0_branch2a_bn_gamma of shape (512,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res5.0.conv1.weight loaded from res5_0_branch2a_w of shape (512, 1024, 1, 1)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res5.0.conv2.norm.bias loaded from res5_0_branch2b_bn_beta of shape (512,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res5.0.conv2.norm.running_mean loaded from res5_0_branch2b_bn_running_mean of shape (512,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res5.0.conv2.norm.running_var loaded from res5_0_branch2b_bn_running_var of shape (512,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res5.0.conv2.norm.weight loaded from res5_0_branch2b_bn_gamma of shape (512,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res5.0.conv2.weight loaded from res5_0_branch2b_w of shape (512, 512, 3, 3)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res5.0.conv3.norm.bias loaded from res5_0_branch2c_bn_beta of shape (2048,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res5.0.conv3.norm.running_mean loaded from res5_0_branch2c_bn_running_mean of shape (2048,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res5.0.conv3.norm.running_var loaded from res5_0_branch2c_bn_running_var of shape (2048,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res5.0.conv3.norm.weight loaded from res5_0_branch2c_bn_gamma of shape (2048,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res5.0.conv3.weight loaded from res5_0_branch2c_w of shape (2048, 512, 1, 1)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res5.0.shortcut.norm.bias loaded from res5_0_branch1_bn_beta of shape (2048,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res5.0.shortcut.norm.running_mean loaded from res5_0_branch1_bn_running_mean of shape (2048,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res5.0.shortcut.norm.running_var loaded from res5_0_branch1_bn_running_var of shape (2048,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res5.0.shortcut.norm.weight loaded from res5_0_branch1_bn_gamma of shape (2048,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res5.0.shortcut.weight loaded from res5_0_branch1_w of shape (2048, 1024, 1, 1)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res5.1.conv1.norm.bias loaded from res5_1_branch2a_bn_beta of shape (512,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res5.1.conv1.norm.running_mean loaded from res5_1_branch2a_bn_running_mean of shape (512,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res5.1.conv1.norm.running_var loaded from res5_1_branch2a_bn_running_var of shape (512,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res5.1.conv1.norm.weight loaded from res5_1_branch2a_bn_gamma of shape (512,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res5.1.conv1.weight loaded from res5_1_branch2a_w of shape (512, 2048, 1, 1)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res5.1.conv2.norm.bias loaded from res5_1_branch2b_bn_beta of shape (512,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res5.1.conv2.norm.running_mean loaded from res5_1_branch2b_bn_running_mean of shape (512,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res5.1.conv2.norm.running_var loaded from res5_1_branch2b_bn_running_var of shape (512,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res5.1.conv2.norm.weight loaded from res5_1_branch2b_bn_gamma of shape (512,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res5.1.conv2.weight loaded from res5_1_branch2b_w of shape (512, 512, 3, 3)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res5.1.conv3.norm.bias loaded from res5_1_branch2c_bn_beta of shape (2048,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res5.1.conv3.norm.running_mean loaded from res5_1_branch2c_bn_running_mean of shape (2048,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res5.1.conv3.norm.running_var loaded from res5_1_branch2c_bn_running_var of shape (2048,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res5.1.conv3.norm.weight loaded from res5_1_branch2c_bn_gamma of shape (2048,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res5.1.conv3.weight loaded from res5_1_branch2c_w of shape (2048, 512, 1, 1)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res5.2.conv1.norm.bias loaded from res5_2_branch2a_bn_beta of shape (512,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res5.2.conv1.norm.running_mean loaded from res5_2_branch2a_bn_running_mean of shape (512,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res5.2.conv1.norm.running_var loaded from res5_2_branch2a_bn_running_var of shape (512,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res5.2.conv1.norm.weight loaded from res5_2_branch2a_bn_gamma of shape (512,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res5.2.conv1.weight loaded from res5_2_branch2a_w of shape (512, 2048, 1, 1)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res5.2.conv2.norm.bias loaded from res5_2_branch2b_bn_beta of shape (512,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res5.2.conv2.norm.running_mean loaded from res5_2_branch2b_bn_running_mean of shape (512,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res5.2.conv2.norm.running_var loaded from res5_2_branch2b_bn_running_var of shape (512,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res5.2.conv2.norm.weight loaded from res5_2_branch2b_bn_gamma of shape (512,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res5.2.conv2.weight loaded from res5_2_branch2b_w of shape (512, 512, 3, 3)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res5.2.conv3.norm.bias loaded from res5_2_branch2c_bn_beta of shape (2048,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res5.2.conv3.norm.running_mean loaded from res5_2_branch2c_bn_running_mean of shape (2048,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res5.2.conv3.norm.running_var loaded from res5_2_branch2c_bn_running_var of shape (2048,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res5.2.conv3.norm.weight loaded from res5_2_branch2c_bn_gamma of shape (2048,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.res5.2.conv3.weight loaded from res5_2_branch2c_w of shape (2048, 512, 1, 1)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.stem.conv1.norm.bias loaded from res_conv1_bn_beta of shape (64,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.stem.conv1.norm.running_mean loaded from res_conv1_bn_running_mean of shape (64,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.stem.conv1.norm.running_var loaded from res_conv1_bn_running_var of shape (64,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.stem.conv1.norm.weight loaded from res_conv1_bn_gamma of shape (64,)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mbackbone.bottom_up.stem.conv1.weight loaded from conv1_w of shape (64, 3, 7, 7)
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mSome model parameters or buffers are not found in the checkpoint:
�[34mbackbone.fpn_lateral3.{bias, weight}�[0m
�[34mbackbone.fpn_lateral4.{bias, weight}�[0m
�[34mbackbone.fpn_lateral5.{bias, weight}�[0m
�[34mbackbone.fpn_output3.{bias, weight}�[0m
�[34mbackbone.fpn_output4.{bias, weight}�[0m
�[34mbackbone.fpn_output5.{bias, weight}�[0m
�[34mbackbone.top_block.p6.{bias, weight}�[0m
�[34mbackbone.top_block.p7.{bias, weight}�[0m
�[34mhead.bbox_pred.{bias, weight}�[0m
�[34mhead.bbox_tower.0.{bias, weight}�[0m
�[34mhead.bbox_tower.1.{bias, weight}�[0m
�[34mhead.bbox_tower.10.{bias, weight}�[0m
�[34mhead.bbox_tower.3.{bias, weight}�[0m
�[34mhead.bbox_tower.4.{bias, weight}�[0m
�[34mhead.bbox_tower.6.{bias, weight}�[0m
�[34mhead.bbox_tower.7.{bias, weight}�[0m
�[34mhead.bbox_tower.9.{bias, weight}�[0m
�[34mhead.centerness.{bias, weight}�[0m
�[34mhead.cls_logits.{bias, weight}�[0m
�[34mhead.cls_tower.0.{bias, weight}�[0m
�[34mhead.cls_tower.1.{bias, weight}�[0m
�[34mhead.cls_tower.10.{bias, weight}�[0m
�[34mhead.cls_tower.3.{bias, weight}�[0m
�[34mhead.cls_tower.4.{bias, weight}�[0m
�[34mhead.cls_tower.6.{bias, weight}�[0m
�[34mhead.cls_tower.7.{bias, weight}�[0m
�[34mhead.cls_tower.9.{bias, weight}�[0m
�[34mhead.scales.0.scale�[0m
�[34mhead.scales.1.scale�[0m
�[34mhead.scales.2.scale�[0m
�[34mhead.scales.3.scale�[0m
�[34mhead.scales.4.scale�[0m
�[34mmask_head.blocker_bound.{bias, num_batches_tracked, running_mean, running_var, weight}�[0m
�[34mmask_head.blocker_bound_bo.{bias, num_batches_tracked, running_mean, running_var, weight}�[0m
�[34mmask_head.bo_deconv.{bias, weight}�[0m
�[34mmask_head.boundary_deconv.{bias, weight}�[0m
�[34mmask_head.boundary_deconv_bo.{bias, weight}�[0m
�[34mmask_head.boundary_fcn1.{bias, weight}�[0m
�[34mmask_head.boundary_fcn2.{bias, weight}�[0m
�[34mmask_head.boundary_fcn3.{bias, weight}�[0m
�[34mmask_head.boundary_fcn4.{bias, weight}�[0m
�[34mmask_head.boundary_predictor.{bias, weight}�[0m
�[34mmask_head.boundary_predictor_bo.{bias, weight}�[0m
�[34mmask_head.deconv.{bias, weight}�[0m
�[34mmask_head.key_transform_bound.weight�[0m
�[34mmask_head.key_transform_bound_bo.weight�[0m
�[34mmask_head.mask_fcn1.{bias, weight}�[0m
�[34mmask_head.mask_fcn2.{bias, weight}�[0m
�[34mmask_head.mask_fcn3.{bias, weight}�[0m
�[34mmask_head.mask_fcn4.{bias, weight}�[0m
�[34mmask_head.output_transform_bound.weight�[0m
�[34mmask_head.output_transform_bound_bo.weight�[0m
�[34mmask_head.predictor.{bias, weight}�[0m
�[34mmask_head.predictor_bo.{bias, weight}�[0m
�[34mmask_head.query_transform_bound.weight�[0m
�[34mmask_head.query_transform_bound_bo.weight�[0m
�[34mmask_head.value_transform_bound.weight�[0m
�[34mmask_head.value_transform_bound_bo.weight�[0m
�[32m[08/10 20:24:41 d2.checkpoint.c2_model_loading]: �[0mThe checkpoint state_dict contains keys that are not used by the model:
�[35mfc1000_b�[0m
�[35mfc1000_w�[0m
�[35mconv1_b�[0m
�[32m[08/10 20:24:41 d2.engine.train_loop]: �[0mStarting training from iteration 0
According to the installation steps, the program is stuck at the beginning of training, can you give me a point?

调试

您好，在原有的coco数据集进行执行时，执行bash all.sh命令后，出现了下面错误，这个文件该从哪里找呀，谢谢！

Mask dataset

Dear @lkeab
According to this picture in your paper:

So, every objects will have full mask no matter they are occluder or occludee ?

json.decoder.JSONDecodeError: Expecting value: line 1 column 188829059 (char 188829058)

Really hope that you (@lkeab ) can spend some time in checking my problem as follows:
Traceback (most recent call last):
File "tools/train_net.py", line 161, in
args=(args,),
File "/gpfs1/home/BCNet/detectron2/engine/launch.py", line 48, in launch
daemon=False,
File "/home/anaconda3/envs/bcnet/lib/python3.7/site-packages/torch/multiprocessing/spawn.py", line 200, in spawn
return start_processes(fn, args, nprocs, join, daemon, start_method='spawn')
File "/home/anaconda3/envs/bcnet/lib/python3.7/site-packages/torch/multiprocessing/spawn.py", line 158, in start_processes
while not context.join():
File "/home/anaconda3/envs/bcnet/lib/python3.7/site-packages/torch/multiprocessing/spawn.py", line 119, in join
raise Exception(msg)
Exception:

-- Process 1 terminated with the following error:
Traceback (most recent call last):
File "/home/anaconda3/envs/bcnet/lib/python3.7/site-packages/torch/multiprocessing/spawn.py", line 20, in _wrap
fn(i, *args)
File "/gpfs1/home/BCNet/detectron2/engine/launch.py", line 83, in _distributed_worker
main_func(*args)
File "/gpfs1/home//BCNet/tools/train_net.py", line 143, in main
trainer = Trainer(cfg)
File "/gpfs1/home/BCNet/detectron2/engine/defaults.py", line 246, in init
data_loader = self.build_train_loader(cfg)
File "/gpfs1/home/BCNet/detectron2/engine/defaults.py", line 420, in build_train_loader
return build_detection_train_loader(cfg)
File "/gpfs1/home/BCNet/detectron2/data/build.py", line 306, in build_detection_train_loader
proposal_files=cfg.DATASETS.PROPOSAL_FILES_TRAIN if cfg.MODEL.LOAD_PROPOSALS else None,
File "/gpfs1/home/BCNet/detectron2/data/build.py", line 226, in get_detection_dataset_dicts
dataset_dicts = [DatasetCatalog.get(dataset_name) for dataset_name in dataset_names]
File "/gpfs1/home/BCNet/detectron2/data/build.py", line 226, in
dataset_dicts = [DatasetCatalog.get(dataset_name) for dataset_name in dataset_names]
File "/gpfs1/home/BCNet/detectron2/data/catalog.py", line 61, in get
return f()
File "/gpfs1/home/BCNet/detectron2/data/datasets/register_coco.py", line 33, in
DatasetCatalog.register(name, lambda: load_coco_json(json_file, image_root, name))
File "/gpfs1/home/BCNet/detectron2/data/datasets/coco.py", line 226, in load_coco_json
coco_api = COCO(json_file)
File "/home/anaconda3/envs/bcnet/lib/python3.7/site-packages/pycocotools-2.0-py3.7-linux-x86_64.egg/pycocotools/coco.py", line 84, in init
dataset = json.load(open(annotation_file, 'r'))
File "/home/anaconda3/envs/bcnet/lib/python3.7/json/init.py", line 296, in load
parse_constant=parse_constant, object_pairs_hook=object_pairs_hook, **kw)
File "/home/anaconda3/envs/bcnet/lib/python3.7/json/init.py", line 348, in loads
return _default_decoder.decode(s)
File "/homeanaconda3/envs/bcnet/lib/python3.7/json/decoder.py", line 337, in decode
obj, end = self.raw_decode(s, idx=_w(s, 0).end())
File "/home/anaconda3/envs/bcnet/lib/python3.7/json/decoder.py", line 355, in raw_decode
raise JSONDecodeError("Expecting value", s, err.value) from None
json.decoder.JSONDecodeError: Expecting value: line 1 column 188829059 (char 188829058)

GCN

The article suggests where GCN, are GCN embodied in the code？

Can BCNet cut out letters from a manuscript?

Hi.

I am very much a beginner, so please bear with me if I am not very technical or precise. (I'll do my best to be clear! 🙂 )

I'm working on a project where I want to cut out all individual letters from images of a long manuscript. One line of a page looks a lot like this:

I want to cut out each letter, with no background -- like this, for example:

I am wondering:

If I provided enough annotations for each letter, would BCNet be able to accomplish my goal? Or would you recommend some other route?

What is the results of your model on COCO 1x training?

Hi! what is mask ap results for 1x training of BCNet using mask-rcnn?

Recommend Projects

React

A declarative, efficient, and flexible JavaScript library for building user interfaces.
Vue.js

🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
Typescript

TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
TensorFlow

An Open Source Machine Learning Framework for Everyone
Django

The Web framework for perfectionists with deadlines.
Laravel

A PHP framework for web artisans
D3

Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

javascript

JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
web

Some thing interesting about web. New door for the world.
server

A server is a program made to process requests and deliver data to clients.
Machine learning

Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Visualization

Some thing interesting about visualization, use data art
Game

Some thing interesting about game, make everyone happy.

Recommend Org

Facebook

We are working to build community through open source technology. NB: members must have two-factor auth.
Microsoft

Open source projects and samples from Microsoft.
Google

Google ❤️ Open Source for everyone.
Alibaba

Alibaba Open Source for everyone
D3

Data-Driven Documents codes.
Tencent

China tencent open source team.