pytorch-faster-rcnn icon indicating copy to clipboard operation
pytorch-faster-rcnn copied to clipboard

Error using resnet50-fpn backbone

Open Mansoor-at opened this issue 2 years ago • 2 comments

Hi I am getting following error if i use resnet50-fpn backbone. mobilenet just works fine. Could you help me.

Traceback (most recent call last): File "/Users/Mansoor/PycharmProjects/pythonProject/train.py", line 131, in main() File "/Users/Mansoor/PycharmProjects/pythonProject/train.py", line 83, in main print_freq=50, warmup=False) File "/Users/Mansoor/PycharmProjects/pythonProject/utils/train_utils.py", line 373, in train_one_epoch loss_dict = model(images, targets) File "/Users/Mansoor/opt/anaconda3/envs/pythonProject/lib/python3.6/site-packages/torch/nn/modules/module.py", line 550, in call result = self.forward(*input, **kwargs) File "/Users/Mansoor/PycharmProjects/pythonProject/utils/faster_rcnn_utils.py", line 85, in forward proposals, proposal_losses = self.rpn(images, features, targets) File "/Users/Mansoor/opt/anaconda3/envs/pythonProject/lib/python3.6/site-packages/torch/nn/modules/module.py", line 550, in call result = self.forward(*input, **kwargs) File "/Users/Mansoor/PycharmProjects/pythonProject/utils/rpn_utils.py", line 290, in forward proposals = self.box_coder.decode(pred_bbox_deltas.detach(), anchors) File "/Users/Mansoor/PycharmProjects/pythonProject/utils/det_utils.py", line 182, in decode rel_codes.reshape(box_sum, -1), concat_boxes RuntimeError: shape '[96768, -1]' is invalid for input of size 392832

Mansoor-at avatar Mar 08 '22 19:03 Mansoor-at

I changed anchor_size from [64, 128, 256] to [32, 64, 128, 256, 512] in train_config.py

Ayu000 avatar Apr 29 '22 10:04 Ayu000

I changed anchor_size from [64, 128, 256] to [32, 64, 128, 256, 512] in train_config.py

Thanks so much! But i still don't understand the reason for this! Can you explain more ?

TrinhThiBaoAnh avatar Aug 05 '22 10:08 TrinhThiBaoAnh