Recent questions tagged pytorch

0 votes

1.5k views

1 answer

pytorch - How to perform indexing and slicing for sparse tensor

I'm trying to access elements of the sparse coo tensor. i = [[0,2]] v = [np.array([1,2, ... .com/questions/65845579/how-to-perform-indexing-and-slicing-for-sparse-tensor...

asked Oct 7, 2021 in Technique[技术] by 深蓝 (71.8m points)

0 votes

2.1k views

1 answer

pytorch - TypeError: cannot serialize '_io.TextIOWrapper' object

I'm using rtx 3080, python 3.7, torch 1.7.1, torchvision 0.8.2 i tried chaning python ... //stackoverflow.com/questions/65856075/typeerror-cannot-serialize-io-textiowrapper-object...

asked Oct 7, 2021 in Technique[技术] by 深蓝 (71.8m points)

0 votes

1.7k views

1 answer

pytorch - Is there a way to use GPU instead of CPU for BERT tokenization?

I'm using a BERT tokenizer over a large dataset of sentences (2.3M lines, 6.53bn words): #creating a BERT tokenizer ... -there-a-way-to-use-gpu-instead-of-cpu-for-bert-tokenization...

asked Oct 7, 2021 in Technique[技术] by 深蓝 (71.8m points)

0 votes

1.4k views

1 answer

pytorch - .grad is None after backward()

cur_z_arr[j].grad is None after when the code is executed. I don't know why. I also tried cur_z_arr[j] ... :https://stackoverflow.com/questions/65880786/grad-is-none-after-backward...

asked Oct 7, 2021 in Technique[技术] by 深蓝 (71.8m points)

0 votes

1.2k views

1 answer

pytorch - Expected more than 1 value per channel when training, got input size torch.Size([1, **])

I met an error when I use BatchNorm1d, code: ##% first I set a model class net(nn.Module): def __init__(self, ... -than-1-value-per-channel-when-training-got-input-size-torch-size...

asked Oct 7, 2021 in Technique[技术] by 深蓝 (71.8m points)

0 votes

1.3k views

1 answer

pytorch - running_mean should contain %% elements not ** when use BatchNorm1d

code: ##% first ,I set a model: class net(nn.Module): def __init__(self, max_len, feature_linear, rnn ... /65884987/running-mean-should-contain-elements-not-when-use-batchnorm1d...

asked Oct 7, 2021 in Technique[技术] by 深蓝 (71.8m points)

0 votes

1.2k views

1 answer

pytorch - Why using GPT2Tokenizer convert Arabic characters to symbols?

I am trying to use GPT2 for Arabic text classification task as follows: tokenizer = GPT2Tokenizer. ... 65897844/why-using-gpt2tokenizer-convert-arabic-characters-to-symbols...

asked Oct 7, 2021 in Technique[技术] by 深蓝 (71.8m points)

0 votes

1.3k views

1 answer

pytorch - slice tensor of tensors using boolean tensor

Having two tensors :inputs_tokens is a batch of 20x300 of token ids and seq_A is my model output with size ... .com/questions/65908585/slice-tensor-of-tensors-using-boolean-tensor...

asked Oct 7, 2021 in Technique[技术] by 深蓝 (71.8m points)

0 votes

1.5k views

1 answer

pytorch - Getting fcntl error when importing PyKeops in Python

I've installed PyKeops package using pip on Windows. The packages seems to be installed properly. Even my ... /65909971/getting-fcntl-error-when-importing-pykeops-in-python...

asked Oct 7, 2021 in Technique[技术] by 深蓝 (71.8m points)

0 votes

1.2k views

1 answer

pytorch - mmdetection cannot get the same results among multi runs after setting the random seed

Even though I set the random seed, and deterministic is true, the values of losses are different among multi runs. ... get-the-same-results-among-multi-runs-after-setting-the-rando...

asked Oct 7, 2021 in Technique[技术] by 深蓝 (71.8m points)

0 votes

1.1k views

1 answer

pytorch - Is the pytorch_transformers from huggingface maintained?

Huggingface has two libraries Pytorch_transformers 1.2.0 and transformers 4. and others? There are some ... /65917197/is-the-pytorch-transformers-from-huggingface-maintained...

asked Oct 7, 2021 in Technique[技术] by 深蓝 (71.8m points)

0 votes

1.3k views

1 answer

pytorch - docker THCudaCheck FAIL no kernel image is available for execution on the device error (pytorch_1565272279342/work/aten/src/THC/THCGeneral.cpp)

FROM nvidia/cuda:10.0-cudnn7-runtime-ubuntu16.04 ... /opt/conda/bin/conda install -y -c pytorch cudatoolkit=10. ... -fail-no-kernel-image-is-available-for-execution-on-the-device...

asked Oct 7, 2021 in Technique[技术] by 深蓝 (71.8m points)

0 votes

1.3k views

1 answer

pytorch - volatile was removed and now had no effect use with.torch.no_grad() instread

my torch program stopped at this point I guess i can not use volatile=True how should I change it and what is the ... -removed-and-now-has-no-effect-use-with-torch-no-grad-instead...

asked Oct 7, 2021 in Technique[技术] by 深蓝 (71.8m points)

0 votes

1.2k views

1 answer

pytorch - Is partial 3D convolution or transpose+2D convolution faster?

I have some data of shape B*C*T*H*W. I want to apply 2d convolutions on the H*W dimension. ... .com/questions/65930768/is-partial-3d-convolution-or-transpose2d-convolution-faster...

asked Oct 7, 2021 in Technique[技术] by 深蓝 (71.8m points)

0 votes

1.4k views

1 answer

pytorch - Unable to backpropagate through torch.rfft

I have two losses: one the usual L1 loss and second one involving torch.rfft() def dft_amp(img) ... /stackoverflow.com/questions/65932593/unable-to-backpropagate-through-torch-rfft...

asked Oct 7, 2021 in Technique[技术] by 深蓝 (71.8m points)

0 votes

1.2k views

1 answer

pytorch - Torch model forward with a diferent image size

I am testing some well known models for computer vision: UNet, FC-DenseNet103, this implementation I train ... questions/65933454/torch-model-forward-with-a-diferent-image-size...

asked Oct 7, 2021 in Technique[技术] by 深蓝 (71.8m points)

0 votes

1.2k views

1 answer

pytorch - How to create a tensor of given shape and interval?

I am going through Pytorch and want to create a random tensor of shape 5X3 in the interval [3,7) torch.rand ... /65617507/how-to-create-a-tensor-of-given-shape-and-interval...

asked Oct 7, 2021 in Technique[技术] by 深蓝 (71.8m points)

0 votes

1.1k views

1 answer

pytorch runs slow when data are pre-transported to GPU

I have a model written in pytorch. Since my dataset is small, I can directly load all of the data to GPU ... /65642697/pytorch-runs-slow-when-data-are-pre-transported-to-gpu...

asked Oct 7, 2021 in Technique[技术] by 深蓝 (71.8m points)

0 votes

1.3k views

1 answer

pytorch - osError: [Errno 22] Invalid argument due to batch size

I get this error in Google colab. If I use GPU and I set to batch size 16 I get this error but I ... .com/questions/65645018/oserror-errno-22-invalid-argument-due-to-batch-size...

asked Oct 7, 2021 in Technique[技术] by 深蓝 (71.8m points)

0 votes

1.3k views

1 answer

pytorch - Google Colab -- MLP execution time not constant, but decreasing?

I am currently working a lot with Google Colab, and wanted to time the execution time of a small MLP ... /66049240/google-colab-mlp-execution-time-not-constant-but-decreasing...

asked Oct 6, 2021 in Technique[技术] by 深蓝 (71.8m points)

0 votes

1.3k views

1 answer

pytorch - why torch.Tensor subtract works well when tensor size is different?

This example will make it easier to understand. The following fails: A = tensor.torch([[1, 2, 3], [4 ... 66059474/why-torch-tensor-subtract-works-well-when-tensor-size-is-different...

asked Oct 6, 2021 in Technique[技术] by 深蓝 (71.8m points)

0 votes

1.4k views

1 answer

pytorch - why torch.Tensor subtract works well when tensor size is different?

This example will make it easier to understand. The following fails: A = tensor.torch([[1, 2, 3], [4 ... 66059474/why-torch-tensor-subtract-works-well-when-tensor-size-is-different...

asked Oct 6, 2021 in Technique[技术] by 深蓝 (71.8m points)

0 votes

962 views

1 answer

pytorch - Customizing the batch with specific elements

I am a fresh starter with pytorch. Strangley I cannot find anything related to this, although it seems ... .com/questions/66065272/customizing-the-batch-with-specific-elements...

asked Oct 6, 2021 in Technique[技术] by 深蓝 (71.8m points)

0 votes

978 views

1 answer

pytorch - Customizing the batch with specific elements

I am a fresh starter with pytorch. Strangley I cannot find anything related to this, although it seems ... .com/questions/66065272/customizing-the-batch-with-specific-elements...

asked Oct 6, 2021 in Technique[技术] by 深蓝 (71.8m points)

0 votes

1.5k views

1 answer

pytorch - pytorch conv2d的源代码在哪里？(Where is the source code of pytorch conv2d?)

Where do I find the source code of the pytorch function conv2d? (在哪里可以找到pytorch函数conv2d的源代码？) It should ... blob/master/torch/nn/functional.py) ask by user3435407 translate from so...

asked Mar 6, 2021 in Technique[技术] by 深蓝 (71.8m points)

0 votes

1.4k views

1 answer

pytorch - 我应该在libtorch中执行其他操作之前先调用::: init_num_threads吗？(Should I call at::init_num_threads before doing anything else in libtorch?)

I run neural nets in libtorch. (我在libtorch中运行神经网络 ) For optimal performance, should I call at::init_num_threads before calling ... 在什么情况下应该称呼它？) ask by user31264 translate from so...

asked Mar 6, 2021 in Technique[技术] by 深蓝 (71.8m points)

0 votes

1.4k views

1 answer

pytorch - 我应该在libtorch中执行其他操作之前先调用::: init_num_threads吗？(Should I call at::init_num_threads before doing anything else in libtorch?)

I run neural nets in libtorch. (我在libtorch中运行神经网络 ) For optimal performance, should I call at::init_num_threads before calling ... 在什么情况下应该称呼它？) ask by user31264 translate from so...

asked Feb 21, 2021 in Technique[技术] by 深蓝 (71.8m points)

0 votes

1.5k views

1 answer

pytorch - pytorch conv2d的源代码在哪里？(Where is the source code of pytorch conv2d?)

Where do I find the source code of the pytorch function conv2d? (在哪里可以找到pytorch函数conv2d的源代码？) It should ... blob/master/torch/nn/functional.py) ask by user3435407 translate from so...

asked Feb 21, 2021 in Technique[技术] by 深蓝 (71.8m points)

Categories

Just Browsing Browsing

Most popular tags