[Newibie] is what i did correct ?(Train/Test Loss) [Uncategorized] (5)
Calling Backward in a Custom Backward [autograd] (3)
Contracting two rank 3 tensors along a certain dimension [Uncategorized] (4)
Dataset size greater than cpu memory, how to make a dataset [Uncategorized] (4)
Setting the seed [Uncategorized] (4)
Understand nn Module [Uncategorized] (5)
GPU implementation of QR\SVD [Uncategorized] (6)
How to save the state of LSTM and use it for initialization in next training sample? [nlp] (1)
Output of nn.functional.conv2d [vision] (4)
Tensor.to(device) changes is_leaf, causing "can't optimize a non-leaf Tensor" [Uncategorized] (2)
Additional Argument for Parameter in Custom Optimizer [Uncategorized] (1)
Is there a special tag symbol for sequences? [nlp] (1)
Self-defined backward is called but the gradients do not back propagate to the previous layers as expected [autograd] (1)
How to represent class_to_idx map for custom dataset in Pytorch [vision] (8)
What's the meaning of gain in initial [Uncategorized] (4)
Transfer learning with different inputs [vision] (9)
Cross Entropy "sum"/N vs Cross-Entropy "mean" [Uncategorized] (6)
Does Pytorch support parallelism across multiple CPUs? [Uncategorized] (7)
Extending Tensors to lie on Riemannian manifold [Uncategorized] (5)
Manually scaling gradients during backward pass [autograd] (1)
Using a word embedding model for inference - question [Uncategorized] (1)
Autograd.grad() for Tensor [autograd] (5)
Optimizer, set learning rate per param [vision] (1)
Costum loss function, without a backward function, how it work? [Uncategorized] (4)
Img segmentation problem [vision] (1)
Input size of linear layer [vision] (2)
Shape '[1, 255, 3025]' is invalid for input of size 689520 [Uncategorized] (2)
How to visualize different models in one same window using PyTorch Visdom to compare their performance? [vision] (5)
Creating network with fixed weights in higher layers similar to intial layer [vision] (1)
3D UNet for brain tumor segmentation - problems with GPU memory [Uncategorized] (4)