pytorch-summary
pytorch-summary copied to clipboard
sksq96
Model summary in PyTorch similar to `model.summary()` in Keras
hello. when i use torch summary. it reports some issues about: File “F:\Anaconda3\lib\site-packages\torchsummary\torchsummary.py”, line 23, in [-1] + list(o.size())[1:] for o in output AttributeError: ‘NoneType’ object has no attribute ‘size’...
For automatic license checkers, it would be helpful if "MIT" is specified in the `setup.py`.
No issues for this: ``` ---------------------------------------------------------------- Layer (type) Output Shape Param # ================================================================ Linear-1 [-1, 1, 100] 30,100 Tanh-2 [-1, 1, 100] 0 Linear-3 [-1, 1, 50] 5,050 Tanh-4 [-1,...
Hi, I tried to use get my model summary on cpu by: summary(model, input_size=(1,200, 200),device=torch.device('cpu')) But I get the following error: AttributeError: 'torch.device' object has no attribute 'lower'. My troch...
Thanks for the great work on something essential that was sorely missing! I saw that it didn't have dictionary support. I personally use dictionary for outputs of my network, since...
Maybe I'm not understanding something but with the following code summary throws an error: ``` import torch from torchvision import models from torchsummary import summary device = torch.device('cuda' if torch.cuda.is_available()...
Some pre-trained models like the [deeplabv3_resnet50](https://pytorch.org/hub/pytorch_vision_deeplabv3_resnet101/) returns an `OrderedDict` containing the semantic mask and the auxillary loss as two separate Tensors under the keys `'out'` and `'aux'`. Usage of torchsummary...
Hi, If the number of parameters of the model is zero, then the call for (line 102): `total_params_size = abs(total_params.numpy() * 4. / (1024 ** 2.))` will fail because the...
