PytorchInsight
PytorchInsight copied to clipboard
implus
a pytorch lib with state-of-the-art architectures, pretrained models and real-time updated results
 Hello, I have a problem. What is the purpose of the identity transformation in the paper?
Hi, I got the following error when try to load sk_resnet50.pth ``` >>> checkpoint1 = torch.load('sk_resnet50.pth.tar', map_location=torch.device('cpu')) Traceback (most recent call last): File "", line 1, in File "/home/jinchen/.local/lib/python3.6/site-packages/torch/serialization.py", line...
my code: def get_se_resnet101(path_state_dict, device, vis_model=False): model = resnet_se.se_resnet101() if path_state_dict: pretrained_state_dict = torch.load(path_state_dict, map_location=torch.device('cpu')) model.load_state_dict(pretrained_state_dict, ) error: raise RuntimeError('Error(s) in loading state_dict for {}:\n\t{}'.format( RuntimeError: Error(s) in loading state_dict...
Your model ResNet34-Sk is not quite right, there is no code for the corresponding sk module in BasicBlock. If you use resnet34_sk directly, it is equivalent to ResNet34?
As paper(Selective Kernel Networks) said，the conventional convolution with a 5×5 kernel is replaced with the dilated convolution with a 3×3 kernel and dilation size 2. But the code is implemented...
sknet50
I downloaded sknet50, but failed to restore the model. Is there any code for sknet50(pytorch version)？ thanks error: self.base.load_state_dict(torch.load(model_path))
Hi. I have two questions: Question 1: ``` t = t - t.mean(dim=1, keepdim=True) std = t.std(dim=1, keepdim=True) + 1e-5 t = t / std t = t.view(b, self.groups, h,...
