RuntimeError: Error(s) in loading state_dict for FasterRCNNVGG16:

[zcunyi]

RuntimeError: Error(s) in loading state_dict for FasterRCNNVGG16: size mismatch for head.cls_loc.bias: copying a param of torch.Size([8]) from checkpoint, where the shape is torch.Size([84]) in current model. size mismatch for head.cls_loc.weight: copying a param of torch.Size([8, 4096]) from checkpoint, where the shape is torch.Size([84, 4096]) in current model. size mismatch for head.score.bias: copying a param of torch.Size([2]) from checkpoint, where the shape is torch.Size([21]) in current model. size mismatch for head.score.weight: copying a param of torch.Size([2, 4096]) from checkpoint, where the shape is torch.Size([21, 4096]) in current model. Any help would be very much appreciated.

[Bigwode]

@zcunyi Please download the pretrained caffe model according to the second part of the readme and specify the path in config.py. CHECK if you run python misc/convert_caffe_pretrain.py before you train the model.