-
## 🐛 Bug
A simple code snippet throws the aforementioned error.
## To Reproduce
Steps to reproduce the behavior:
Run the following code (autogenerated from a previous error message in a bi…
-
### 🐛 Describe the bug
The batched GEMM has a poor performance for bigger batch size(`12*7*120*64*129`) with smaller matrix size(`3x3`, `3x1`):
```python
import torch
import time
points = t…
-
### 🐛 Describe the bug
First I wanted to say that FlexAttention is amazing new addition that simplifies and accelerates otherwise complicated attention-mask implementation - so thanks a lot for thi…
-
### 🐛 Describe the bug
When I upgrade to PyTorch 2.2 via Pip, importing torch fails with an undefined symbol error:
```
Traceback (most recent call last):
File "", line 1, in
File "/scratc…
-
### 🐛 Describe the bug
A similar issue was reported in #32591. Unfortunately, it doesn't look like it was actually fully fixed at the time.
Comparing
```python
(a * b).sum(dim=-1)
torch.einsum(…
RuRo updated
2 months ago
-
## 🐛 Bug
The output of `torch.finfo(torch.float16)` seems to be incorrect.
## To Reproduce
Steps to reproduce the behavior:
```
>>> import torch
>>> torch.finfo(torch.float16)
finfo(res…
-
### 🐛 Describe the bug
I'm experiencing a torch.fft.irfft shape mismatch when exporting a model using torch.onnx.dynamo_export. Details below
### Error logs
I've got shapes for repro below
`…
-
### 🐛 Describe the bug
``` python
torch.use_deterministic_algorithms(True)
input = torch.tensor([1, 2, 3, 4, 5, 6, 7, 8, 9])
index = torch.tensor([0, 1, 1, 1, 2])
src = torch.tensor([11, 12, 13, …
-
one interesting application of this representation might be that it might be explainable in a useful form.
If we train a model on the image, we can then use one of the established interpretability…
-
In GitLab by @vkse1934 on Nov 8, 2024, 09:21
_Merges feature/android/cnn -> develop_
## 개요
- ResNet 개발
1. build.gradle PyTorch 의존성 추가
2. ResnetClassifier 클래스 추가
3. PyTorch 모델 추가 (Mel Spectogram 변환…