pytorch-faster-rcnn

pytorch-faster-rcnn copied to clipboard

Error using resnet50-fpn backbone

2

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()...

Mansoor-at

The map is vey low

2

I have been running the model for a long time, but the map is always 0

Ayu000

I want to know how much mAP can this method get?

1

shuxiao0312

AttributeError: module 'torch.distributed' has no attribute 'barrier'

2

Hello, I encountered this problem during verification. I would be very grateful if you could give me the answer. 

glt999

Question about CPU use

3

How could I modify this repository for use on a CPU?

courtney-ann

Model parameter error

1

Hi, I downloaded your model fasterrcnn_resnet50_fpn_coco-258fb6c6.pth, but when i try to load this model using model.load_state_dict(checkpoint['model]), it shows "key error 'model'" so i try to print keys in model dictionaries...

lhcezx

pred_boxes = self.decode_single(rel_codes.reshape(box_sum, -1), concat_boxes) => rel_codes = rel_codes.view(box_sum, -1) pred_boxes = self.decode_single(rel_codes, concat_boxes) ########################bug ########################################### the rel_codes = rel_codes.view(box_sum, -1) #reshape fail on fpn resnet-50 ########################correct###################################### rel_codes = rel_codes[:box_sum]...

fatalfeel

self.conv = nn.Conv2d(in_channels, in_channels, kernel_size=3, stride=1, padding=1) '''background/foreground score''' self.cls_logits = nn.Conv2d(in_channels, num_anchors, kernel_size=1, stride=1) #wrong '''bbox regression parameters''' self.bbox_pred = nn.Conv2d(in_channels, num_anchors * 4, kernel_size=1, stride=1) ################### self.cls_logits =...

fatalfeel

just star it~~~thanks full py source in faster-rcnn, easier to learn

fatalfeel

RuntimeError: shape '[516096, -1]' is invalid for input of size 2095104

3

I modified the data_root_dir in train_config.py and also placed the data as mentioned in the README.md I face this error: ``` /home/dksingh/anaconda3/envs/mmdet220/lib/python3.7/site-packages/torch/nn/functional.py:3000: UserWarning: The default behavior for interpolate/upsample with float...

deepaksinghcv