pytorch-summary
pytorch-summary copied to clipboard
sksq96
Model summary in PyTorch similar to `model.summary()` in Keras
This is a useful information to dynamically compute max/recommended batch size.
RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cuda:1 and cuda:0! (when checking arugment for argument target in method wrapper_nll_loss_forward) from torchvision.models.resnet...
My model has an input in Long dtype which is passed to an torch.nn.Embedding layer. Since all the input data are created in torch.FloatTensor type, it creates runtime error when...
I'd like to get a summary for the following BERT model ``` model = torch.hub.load('huggingface/pytorch-transformers', 'model', 'bert-base-uncased') ``` What shape or shapes should I use? how to get list of...
File "C:\Users\simon\Desktop\DeepRL.old\deep_rl\agent\PPO_agent.py", line 25, in __init__ torchsummary.summary(self.network,(100, 2, 11)) ...... File "C:\Users\simon\Desktop\DeepRL.old\deep_rl\network\network_bodies.py", line 149, in forward y, (h_n,c_n) = self.lstm1(x) File "C:\Anaconda\lib\site-packages\torch\nn\modules\module.py", line 491, in __call__ hook_result = hook(self, input,...
Hello, I'm trying to use pytorch-summary But, my model's input is "dict" type. What can I do for using this library about dict input? Thank you for sharing awesome library...
When i use summary(model, input_size), There is a problem about the parameter 'input_size", in general, input_size = (C, H, W), but for graph datasets, there are nodes and labels and...
While dealing with multi-input, the current implementation calculates the number of elements in input as the product of all dimensions in all inputs, I believe this is not accurate. For...
Hello there, I found recently that the main function does not work on the `torchvision` implementation of DenseNet. ``` from torchvision.models import densenet121 from torchsummary import summary model = densenet121().eval().cuda()...
For example in the forward path, I define as def forward(self, input, path1=True): I realize that when I want to pass summary(model, [(3, 32,32),(True)]) or summary(model, [(3, 32,32),(True)] or summary(model,...
