-
### 🐛 Describe the bug
When trying to export [this model](https://github.com/gabrielmittag/NISQA) to ONNX, I get the following:
- `pytorch 1.10.1`: no errors/warnings, Segmentation fault
- `pytorc…
-
### 🐛 Describe the bug
I'm getting the error `RuntimeError: CUDA error: an illegal memory access was encountered` when running `nn.CrossEntropyLoss`. I was able to reproduce the error with the follow…
-
-
Has anyone meets the same error?
Error executing job with overrides: []
Error locating target 'diffusion_policy.dataset.pusht_image_dataset.PushTImageDataset', set env var HYDRA_FULL_ERROR=1 to se…
-
include/ATen/core/DeprecatedTypeProperties.h:37:3: error: reference to ‘DeviceType’ is ambiguous
DeviceType device_type() const {
^~~~~~~~~~
compilation terminated due to -Wfatal-errors.
-
### 🐛 Describe the bug
AMP consumes about 30x gpu memory when used on `bmm`.
Code:
```
import torch
import torch.nn as nn
class MyModule(nn.Module):
def __init__(self):
super…
Teoge updated
2 years ago
-
### Članovi tima:
Nemanja Vujadinović SV28-2020 (grupa 5 po službi, ali idem u 1.)
### Asistent:
Marko Njegomir
### Problem koji se rešava:
Potrebno je obučiti neuronsku mrežu da klasifi…
-
This blog post might give you some additional hints how to improve parts of the model: https://towardsdatascience.com/how-to-get-beautiful-results-with-neural-style-transfer-75d0c05d6489
Accompanyi…
-
### 🐛 Describe the bug
`parallelize_module` failed with `nn.Transformer` and the `PairwiseParallel` plan, which is unexpected according to [the doc](https://pytorch.org/docs/stable/distributed.tens…
-
## 🐛 Bug
At the forward step, pass a small ResNet model occupies me more than 15G GPU with torch1.8. Torch1.6 does not have this issue using the same code.
## To Reproduce
Steps to reproduce …