adityaarun1 / detectron.pytorch Goto Github PK

Hi, thanks for the great work! I wonder if you have replicated the performance on COCO under the new version.

from torch.utils.data.dataloader import numpy_type_map
ImportError: cannot import name 'numpy_type_map'

what is it happened?

Hey!

I have finetuned a network on VOC 2007, which was initially trained on COCO Dataset.

I am now trying to evaluate the training on the validation set. When I run the command,
python tools/test_net.py --dataset voc2007 --cfg configs/baselines/e2e_mask_rcnn_R-50-FPN_1x.yaml --load_ckpt {path/to/your/checkpoint},

I get this:
INFO task_evaluation.py: 61: Evaluating bounding boxes is done!

INFO task_evaluation.py: 104: Evaluating segmentations
Traceback (most recent call last):

File "tools/test_net.py", line 125, in
check_expected_results=True)

File "/home/deep/data/asif/Detectron/Detectron.pytorch/lib/core/test_engine.py", line 128, in run_inference
all_results = result_getter()

File "/home/deep/data/asif/Detectron/Detectron.pytorch/lib/core/test_engine.py", line 108, in result_getter
multi_gpu=multi_gpu_testing

File "/home/deep/data/asif/Detectron/Detectron.pytorch/lib/core/test_engine.py", line 163, in test_net_on_dataset
dataset, all_boxes, all_segms, all_keyps, output_dir

File "/home/deep/data/asif/Detectron/Detectron.pytorch/lib/datasets/task_evaluation.py", line 63, in evaluate_all
results = evaluate_masks(dataset, all_boxes, all_segms, output_dir)

File "/home/deep/data/asif/Detectron/Detectron.pytorch/lib/datasets/task_evaluation.py", line 128, in evaluate_masks
'No evaluator for dataset: {}'.format(dataset.name)

NotImplementedError: No evaluator for dataset: voc_2007_test

This appears from the task_evaluation file where no implementation for voc evaluation in masks. Is there a work around?

Since, voc is already in json format I guessed it is still possible to evaluate segmentations in the task_evaluation script! How to do this?

Hi!
I am trying to use voc dataset to infer test images. It works fine with the coco dataset! I am exploring the code and its abilities as I ultimately want to use a custom dataset and classes! So, I was trying to visualize the training performance of VOC2007 on the infer_simple.py. But its not possible as the infer_simple.py only accepts coco or keypoints coco as the acceptable dataset. Am I doing something wrong here?

Import Error using Pytorch 1.1.0

I encountered this error during a dataset conversion to COCO json format

----> 6 from lib.utils.boxes import xyxy_to_xywh
.
.
.
/content/Detectron.pytorch/lib/nn/parallel/scatter_gather.py in <module>()
      6 from ._functions import Scatter, Gather
      7 from torch._six import string_classes, int_classes
----> 8 from torch.utils.data.dataloader import numpy_type_map
      9 
     10 

ImportError: cannot import name 'numpy_type_map'

It seems that numpy_type_map has been moved to torch/utils/data/_utils/collate.py in pytorch 1.1.0

Maybe numpy_type_map should be redefined entirely instead of being imported.

EDIT: Same error encountered when executing

python tools/download_imagenet_weights.py

Hi,

I am finetuning a COCO pretrained model with VOC dataset. I am using the config file : e2e_mask_rcnn_R-50-FPN_1x.yaml

I found a key to freeze the backbone of model with TRAIN.FREEZE_CONV_BODY: True
But this only freezes the Convolutional layers. How do I freeze the Fast RCNN and MRCNN layers so I can update the output layers alone by fine tuning ?

I installed torchvision 0.3.0 first, and it told me:

ERROR: torchvision 0.3.0 has requirement torch>=1.1.0, but you'll have torch 1.0.1 which is incompatible.

when I pip install torch-1.0.1-cp35-cp35m-manylinux1_x86_64.whl. So what are the matched versions?

Hi!

I trained from scratch completely a network with COCO2017 dataset with:

python tools/train_net_step.py --dataset coco2017 --cfg configs/baselines/e2e_mask_rcnn_R-50-FPN_1x.yaml --use_tfboard --bs=2

I now used the checkpoint (pth file) created from the train from scratch to finetune with VOC2007 dataset.

As expected I ran into trouble because the number of classes in VOC (21) and COCO (81) are different. I understand its possible to finetune as there are steps given to finetune custom dataset with different number of classes. I would like to know how to do this?

The command i used:
python tools/train_net_step.py --dataset voc2007 --cfg configs/baselines/e2e_mask_rcnn_R-50-FPN_1x.yaml --load_ckpt=/home/deep/data/asif/Detectron/Detectron.pytorch/Outputs/e2e_mask_rcnn_R-50-FPN_1x/Mar14-14-59-32_deeppc_step/ckpt/model_step719999.pth --use_tfboard --bs=2

The errors I got:
Traceback (most recent call last):
File "tools/train_net_step.py", line 471, in
main()
File "tools/train_net_step.py", line 331, in main
net_utils.load_ckpt(maskRCNN, checkpoint['model'])
File "/home/deep/data/asif/Detectron/Detectron.pytorch/lib/utils/net.py", line 163, in load_ckpt
model.load_state_dict(state_dict, strict=False)
File "/home/deep/anaconda3/envs/detectron/lib/python3.7/site-packages/torch/nn/modules/module.py", line 769, in load_state_dict
self.class.name, "\n\t".join(error_msgs)))
RuntimeError: Error(s) in loading state_dict for Generalized_RCNN:
size mismatch for Box_Outs.cls_score.weight: copying a param with shape torch.Size([81, 1024]) from checkpoint, the shape in current model is torch.Size([21, 1024]).
size mismatch for Box_Outs.cls_score.bias: copying a param with shape torch.Size([81]) from checkpoint, the shape in current model is torch.Size([21]).
size mismatch for Box_Outs.bbox_pred.weight: copying a param with shape torch.Size([324, 1024]) from checkpoint, the shape in current model is torch.Size([84, 1024]).
size mismatch for Box_Outs.bbox_pred.bias: copying a param with shape torch.Size([324]) from checkpoint, the shape in current model is torch.Size([84]).
size mismatch for Mask_Outs.classify.weight: copying a param with shape torch.Size([81, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([21, 256, 1, 1]).
size mismatch for Mask_Outs.classify.bias: copying a param with shape torch.Size([81]) from checkpoint, the shape in current model is torch.Size([21]).