Skip to main content
2 votes
1 answer
73 views

I am trying to follow along with this webpage: https://jtr13.github.io/cc21fall2/tutorial-on-r-torch-package.html I am trying to understand R's implementation of PyTorch. I am having some trouble with ...
Huy Pham's user avatar
  • 173
2 votes
1 answer
25 views

In Torch, .view() reshapes the tensor. However, there are multiple ways to reshape a multi-dimensional tensor to a target shape. How does it decide between those different ways? For example, in Torch, ...
Sanchit's user avatar
  • 21
Advice
0 votes
4 replies
62 views

Evening, Is there any way to find a specific sequence of numerical values, matching certain logic (in the same way as in a regex), within a numpy/torch array or matrix row? I know i could just convert ...
Ghost's user avatar
  • 1,594
0 votes
0 answers
65 views

I'm trying to run the Qwen2.5-Coder-3B model locally with 8-bit quantization using BitsAndBytes. While loading the model, I noticed that some examples also specify torch_dtype=torch.float16. From my ...
SHresTho12's user avatar
0 votes
0 answers
89 views

I am trying to install PyTorch 2.7.0 with CUDA 12.6 support in a Docker container, but I get the following error: ERROR: Could not find a version that satisfies the requirement torch==2.7.0+cu126 (...
charlie's user avatar
  • 357
0 votes
0 answers
64 views

i use windows 11 nvcc --version nvcc: NVIDIA (R) Cuda compiler driver Copyright (c) 2005-2025 NVIDIA Corporation Built on Wed_Apr__9_19:29:17_Pacific_Daylight_Time_2025 Cuda compilation tools, release ...
JohnPython's user avatar
3 votes
0 answers
112 views

I have encountered a particular problem while executing a function from the transformers library of huggingface on an Intel GPU wheel of torch. Since I am doing something I normally shouldn't be ...
Logarithmnepnep's user avatar
0 votes
0 answers
64 views

I have a machine-translation model. In this model, I calculate a vector for a given sentence and I take this vector, aggregate with each generated output of RNN and put it into RNN again for ...
cuneyttyler's user avatar
  • 1,395
0 votes
1 answer
116 views

I was trying to follow a project in university where we had to import cellpose. The import delivered an error message which could be tracebacked to import torch (see below). Every import was done in a ...
Ehrenmann's user avatar
0 votes
0 answers
271 views

I’m running Silero VAD (via PyTorch + torchaudio) on a Linode cloud instance (2 dedicated CPUs, 4 GB RAM). When I process 10-minute audio chunks, I always get repeated warnings like this and it doesn'...
Uktamjon's user avatar
0 votes
1 answer
76 views

I have a model that take more than one arguments in forward. Recently I'm trying to query some informations my model by fvcore module in python, but I can't find any document for multiple forward ...
H.M's user avatar
  • 586
0 votes
1 answer
61 views

If you use cosine decay for example and you have starting learning rate and final learning rate, can you tune those hyperparameters so that final learning rate is in some ratio of starting learning ...
ict's user avatar
  • 1
1 vote
1 answer
142 views

I am trying to minimize a non-convex function using three different L-BFGS implementations in R: optim(method = "L-BFGS-B"), torch::optim_lbfgs(), and lbfgs::lbfgs(). I have set the same ...
Alyde Bles's user avatar
0 votes
0 answers
48 views

I wrote a code for SHAP on images. It was working for two days, then it brought following error : module 'shap' has no attribute 'DeepExplainer' I uninstalled and installed the SHAP module again and ...
Samaneh Rezaei's user avatar
0 votes
0 answers
40 views

I am trying to use torch.autograd.functional.jacobian to calculate the gradients of the model parameters with respect to a set of losses, but it returns all zeros. My function definition is as follows ...
catfish's user avatar

15 30 50 per page
1
2 3 4 5
145