-
下图有个5和3其实挺明显的，但是识别成1，请问要提高精度需要往哪个方向修改？
-
Hello,
It seems like it not really clear how to use the pre-trained models, what is are the features fed the to model directly?
If its possible to add a part in the readme file to clarify the usag…
-
### 🐛 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, …
-
### 🐛 Describe the bug
Honestly, I don't know if it's right to leave a bug report here.
However, it seems to be a problem that only occurs between pytorch and H100, so I write down this issue.
I'…
-
Our environment will very much depend on pytorch, so basing dependencies around this is important.
https://pytorch.org/get-started/locally/
https://github.com/pytorch/pytorch#from-source
-
## 🐛 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
Following any package manager install then running:
`
import torch
torch.cuda.is_available()
`
returns false
If I build a wheel from source it is successful, but the …
-
### 🐛 Describe the bug
Simply run torch.matmul on different machines, when gemm is large, we get almost **equal performance**.
However when it is small, **A800 + AMD is unstable and slow.**
Test …
-
## 🐛 Bug
Subclassing `torch.Tensor` results in unexpected behavior and crashes without warning when attempting to use `torch.cat` on the tensor object.
## To Reproduce
Run the code below:
…
-
Hello everyone,
When generating a bitstream for my CNN model I seem to run into the problem of no model being generated using vitis AI 3.5, however I do not seem to get any error message. Could any…