Questions tagged [pytorch]

PyTorch is an open-source deep learning framework and API that creates a Dynamic Computational Graph, which allows you to flexibly change the way your neural network behaves on the fly and is capable of performing automatic backward differentiation.

PyTorch

Tensors and Dynamic neural networks in Python with strong GPU acceleration.

PyTorch is a deep learning framework that puts Python first.

Important: pytorch and torch are different frameworks. Please, do not use PyTorch's tag when asking about Torch and vice-versa.

22623 questions

521

votes

18 answers

How do I check if PyTorch is using the GPU?

How do I check if PyTorch is using the GPU? The nvidia-smi command can detect GPU activity, but I want to check it directly from inside a Python script.

python memory-management gpu nvidia pytorch

asked Jan 08 '18 at 14:50

vvvvv

25,404
19
49
81

376

votes

10 answers

How do I save a trained model in PyTorch?

How do I save a trained model in PyTorch? I have read that: torch.save()/torch.load() is for saving/loading a serializable object. model.state_dict()/model.load_state_dict() is for saving/loading model state.

python serialization deep-learning pytorch tensor

asked Mar 09 '17 at 19:06

Wasi Ahmad

35,739
32
114
161

333

votes

9 answers

What does .view() do in PyTorch?

What does .view() do to a tensor x? What do negative values mean? x = x.view(-1, 16 * 5 * 5)

python memory pytorch tensor

asked Feb 27 '17 at 07:21

Wasi Ahmad

35,739
32
114
161

331

votes

7 answers

Why do we need to call zero_grad() in PyTorch?

Why does zero_grad() need to be called during training? | zero_grad(self) | Sets gradients of all model parameters to zero.

python neural-network deep-learning pytorch gradient-descent

asked Dec 28 '17 at 04:31

user1424739

11,937
17
63
152

318

votes

11 answers

How do I print the model summary in PyTorch?

How do I print the summary of a model in PyTorch like what model.summary() does in Keras: Model Summary: ____________________________________________________________________________________________________ Layer (type) Output…

python pytorch

asked Feb 27 '17 at 07:35

Wasi Ahmad

35,739
32
114
161

254

votes

10 answers

How do I initialize weights in PyTorch?

How do I initialize weights and biases of a network (via e.g. He or Xavier initialization)?

python machine-learning deep-learning neural-network pytorch

asked Mar 22 '18 at 16:34

Fábio Perez

23,850
22
76
100

246

votes

4 answers

What does model.eval() do in pytorch?

When should I use .eval()? I understand it is supposed to allow me to "evaluate my model". How do I turn it back off for training? Example training code using .eval().

python machine-learning deep-learning pytorch

asked Feb 01 '20 at 15:58

Gulzar

23,452
27
113
201

224

votes

5 answers

What's the difference between reshape and view in pytorch?

In numpy, we use ndarray.reshape() for reshaping an array. I noticed that in pytorch, people use torch.view(...) for the same purpose, but at the same time, there is also a torch.reshape(...) existing. So I am wondering what the differences are…

python pytorch

asked Apr 04 '18 at 05:09

Lifu Huang

11,930
14
55
77

209

votes

6 answers

What does model.train() do in PyTorch?

Does it call forward() in nn.Module? I thought when we call the model, forward method is being used. Why do we need to specify train()?

python pytorch

asked Jul 20 '18 at 00:10

aerin

20,607
28
102
140

204

votes

8 answers

What does .contiguous() do in PyTorch?

What does x.contiguous() do for a tensor x?

python memory pytorch contiguous

asked Feb 21 '18 at 21:30

MBT

21,733
19
84
102

172

votes

5 answers

Why do we "pack" the sequences in PyTorch?

I was trying to replicate How to use packing for variable-length sequence inputs for rnn but I guess I first need to understand why we need to "pack" the sequence. I understand why we "pad" them but why is "packing" (via pack_padded_sequence)…

deep-learning pytorch recurrent-neural-network tensor zero-padding

asked Jun 25 '18 at 19:40

aerin

20,607
28
102
140

167

votes

10 answers

Check the total number of parameters in a PyTorch model

How do I count the total number of parameters in a PyTorch model? Something similar to model.count_params() in Keras.

python pytorch

asked Mar 09 '18 at 19:55

Fábio Perez

23,850
22
76
100

166

votes

6 answers

pytorch - connection between loss.backward() and optimizer.step()

Where is an explicit connection between the optimizer and the loss? How does the optimizer know where to get the gradients of the loss without a call liks this optimizer.step(loss)? -More context- When I minimize the loss, I didn't have to pass the…

machine-learning neural-network pytorch gradient-descent

asked Dec 30 '18 at 06:30

aerin

20,607
28
102
140

163

votes

4 answers

PyTorch preferred way to copy a tensor

There seems to be several ways to create a copy of a tensor in PyTorch, including y = tensor.new_tensor(x) #a y = x.clone().detach() #b y = torch.empty_like(x).copy_(x) #c y = torch.tensor(x) #d b is explicitly preferred over a and d according…

python pytorch copy tensor

asked Mar 20 '19 at 16:51

dkv

6,602
10
34
54

163

votes

6 answers

Pytorch tensor to numpy array

I have a pytorch Tensor of shape [4, 3, 966, 1296]. I want to convert it to numpy array using the following code: imgs = imgs.numpy()[:, ::-1, :, :] How does that code work?

python numpy pytorch

asked Apr 11 '18 at 06:49

DukeLover

2,184
2
19
27

2 3

…

99 100 Next