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
24,252
questions
-3
votes
0
answers
14
views
Why the Intel Iris performs better than RTX 3050 laptop GPU in training a Yolov8 model [closed]
I am facing a very weird situation. I have Dell G-15 Gaming laptop with Core i5 12500h and Rtx 3050. I am new to deep learning and AI. I am training a model with Yolo v8 for Automated Number Plate ...
0
votes
0
answers
21
views
More CPU cores lead to less performance DRL (Deep Reinforcement Learning)
We are currently working on a deep RL project and are encountering an issue where switching the training from our laptops to a workstation with more CPU cores causes the performance to drastically ...
- 11
0
votes
0
answers
10
views
Set torch.nn.Parameter's data, including the gradient
I have an existing nn.Parameter, and a tensor with a gradient. I want to set the tensor to the parameter in a way that the parameter will have the same gradient (including perhaps .grad_fn and so on). ...
- 73
0
votes
0
answers
16
views
Finetuning BERT on classification task, tensor device mismatch error
I'm having trouble on fine-tuning a BERT model on a classification task, as I'm quite new to this. My data is composed of two columns, "item_title" (my input) and "meta_categ_id" (...
0
votes
1
answer
15
views
When calling torchvision.transforms.Normalize and converting to PIL.Image, how are values above 1 handled?
Applying torchvision.Normalize should lead to values below 0 and above 1, and thus below 0 and 255 when switching to integer values.
However, when watching the values, this seems NOT to be the case. ...
- 340
0
votes
0
answers
10
views
RuntimeError: The size of tensor a (49313) must match the size of tensor b (49310) at non-singleton dimension 0
I'm looking to use a Sequential.nn model in Pytorch to predict Cost. I'm encountering the following error when attempting to calculate loss off the model. I've had some trouble trying to use nn to ...
0
votes
0
answers
14
views
Inconsistent tensor device management detected by autograd
In my code, I encountered issues with tensor device management, specifically with tensors stored in custom containers (TensorPack objects). Initially, tensors were defaulting to CPU, even when the ...
- 149
1
vote
1
answer
56
views
Generate n random 2D points within a valid region
I want to generate a fixed number of random-uniformly distributed xy points within a valid mask.
The generated points should be continuous, i.e. can be "between pixels".
I'm looking for an ...
- 33
0
votes
0
answers
6
views
ValueError: GetLogdirSubdirectories: path exists and is not a directory, logs
I'm using Tensorboard, which is in the pytorch package, and I've generated a quadratic function value and written it into a folder called Logs, but when I type Tensorboard --logdir=logs in the ...
0
votes
1
answer
20
views
How to convert a set of tensor values to a list while keeping the format float precision
I have a 3 lists of ids (sequence[i].id_column) and when I print them, I see (I don't know for what reason) the format of the second list changes! for example 4.2 becomes 4.2e+00. I tried to add all ...
- 3
1
vote
0
answers
11
views
Why loss value in probablistic-layers at the beginning of training proccess is large value
I try to build model with conv-flipout layer and desne-flipout layer instead of conv2d and dense-layer, but when training the model, at first the loss value become large as (100) then decrease slowly ...
- 47
0
votes
0
answers
30
views
Which api in `libtorch` corresponding the `ctx.needs_input_grad` in pytorch when to define custom `torch.autograd.Function`?
When I tanslate the following python code to cpp code with libtorch api
class _SphericalHarmonics(torch.autograd.Function):
"""Spherical Harmonics"""
@...
- 101
0
votes
0
answers
7
views
ONNXRuntimeError for exported torchvision / fasterrcnn_mobilenet_v3_large_fpn
I get an ONNXRuntimeError when running FasterRCNN model exported to .onnx
Error:
onnxruntime.capi.onnxruntime_pybind11_state.RuntimeException: [ONNXRuntimeError] : 6 : RUNTIME_EXCEPTION : Non-zero ...
- 319
0
votes
0
answers
32
views
CUDA Out of Memory Error with RTX 4060 When Training ResNet-18 on 128x128 Images
I am encountering a CUDA out-of-memory error while training a ResNet-18 model on 128x128 images using my RTX 4060 GPU. Despite reducing the batch size, I still face this issue. Below are the details ...
- 108
0
votes
0
answers
14
views
Loss function showing 'nan' when trying to run across multiple GPUs in Pytorch lightning
I'm trying to implement Pytorch lightning into a model I have written to solve the Allen-cahn diffusion equation. When I run the code on one gpu, the program runs as expected, but when I try to use ...
