stvir / grid-r-cnn Goto Github PK

I want to get the bboxes' x,y,w,h. But I can't find any modules or methods to get them.How can I do to gain them?

hello, i want to know whether grid RCNN in mmdetection is the same version as this one. Thanks.

@luxiin
@siyuanren
Why random_jitter?? What is the purpose of this??

" !python tools/test.py grid_rcnn_r50_fpn_2x.py grid_rcnn_res50.pth --show " I try to run this code output like this

Traceback (most recent call last):
File "tools/test.py", line 12, in
from mmdet.apis import init_dist
ModuleNotFoundError: No module named 'mmdet'

I tried to train Grid R-CNN with grid_rcnn_r50_fpn_2x.py, I used 4 gpus, setting lr=0.01 and warmup_iters=14660(2 epochs) 。The training goes well for now except that the training speed is very slow, about 2.2s/iter.

2019-08-12 23:29:06,094 - INFO - Epoch [2][4350/14659]  lr: 0.01000, eta: 8 days, 9:38:37, time: 2.414, data_time: 0.129, memory: 4836, loss_rpn_cls: 0.0598, loss_rpn_reg: 0.0411, loss_cls: 0.3345, acc: 89.5898, loss_grid: 0.6875, loss: 1.1229
2019-08-12 23:31:04,507 - INFO - Epoch [2][4400/14659]  lr: 0.01000, eta: 8 days, 9:41:07, time: 2.369, data_time: 0.134, memory: 4836, loss_rpn_cls: 0.0570, loss_rpn_reg: 0.0407, loss_cls: 0.3127, acc: 90.7246, loss_grid: 0.6755, loss: 1.0860
2019-08-12 23:32:52,252 - INFO - Epoch [2][4450/14659]  lr: 0.01000, eta: 8 days, 9:40:22, time: 2.155, data_time: 0.120, memory: 4836, loss_rpn_cls: 0.0632, loss_rpn_reg: 0.0409, loss_cls: 0.3332, acc: 90.3809, loss_grid: 0.6859, loss: 1.1231

My virtual environment is based on Anaconda 4.7, other system settings are as below:
Ubuntu 14.04
Pytorch 1.1
Python 3.7
CUDA 10.0
GCC 5.4
Need some help, thx.

in the paper, before the grid-branch, the proposals from rpn will go through the classificaiton branch. so in the classification branch, it only has the cls-loss? or still has the both cls-loss and reg-loss?

python tools/test.py configs/grid_rcnn_r50_fpn_2x.py checkpoints/grid_rcnn_res50.pth --show
loading annotations into memory...
Traceback (most recent call last):
File "tools/test.py", line 189, in
main()
File "tools/test.py", line 145, in main
dataset = get_dataset(cfg.data.test)
File "/home/fsr/Grid-R-CNN/mmdet/datasets/utils.py", line 110, in get_dataset
dset = obj_from_dict(data_info, datasets)
File "/home/fsr/anaconda3/envs/open-mmlab/lib/python3.7/site-packages/mmcv/runner/utils.py", line 50, in obj_from_dict
return obj_type(**args)
File "/home/fsr/Grid-R-CNN/mmdet/datasets/custom.py", line 61, in init
self.img_infos = self.load_annotations(ann_file)
File "/home/fsr/Grid-R-CNN/mmdet/datasets/coco.py", line 25, in load_annotations
self.coco = COCO(ann_file)
File "/home/fsr/anaconda3/envs/open-mmlab/lib/python3.7/site-packages/pycocotools-2.0.2-py3.7-linux-x86_64.egg/pycocotools/coco.py", line 84, in init
with open(annotation_file, 'r') as f:
FileNotFoundError: [Errno 2] No such file or directory: 'data/coco/annotations/instances_val2017.json'

but the file does exist.

hi @siyuanren
why do u get grid_points by dividing 2W instead of W in these two lines? and what do these lines do as below?

        for i in range(9):
            xs[i::9] = xs[i::9] + base[i//3]
            ys[i::9] = ys[i::9] + base[i%3]

when i train the model on my owner dataset， recall is very high but when i check the badcase , i find some extra exception detection boxes even on clean surface. What could be the cause?