lymoon3129

Results 1 issues of lymoon3129

While copying the parameter named RCNN_top.0.weight, whose dimensions in the model are torch.Size([1024, 256, 7, 7]) and whose dimensions in the checkpoint are torch.Size([1024, 256, 14, 14]).

i can run test_net.py，but when i changed the code about faster_rcnn to fpn in demo.py, there someting wrong