-
We've been struggling too much with setting up running 6 models from Whisperer Challenge. Over the weekend, I researched some existing HSI dataset, probably with HSI dataset. Here's some [chat log](ht…
-
### System Info
```
~/work/llama-stack/distributions/meta-reference-gpu (main)]$ python -m "torch.utils.collect_env"
/home/kaiwu/.conda/envs/llamastack-meta-reference-gpu/lib/python3.10/runpy.py:12…
-
### 机器学习
- [ ] [A Gentle Introduction to Object Recognition With Deep Learning](https://machinelearningmastery.com/object-recognition-with-deep-learning/)--目标检测入门介绍
- [ ] [Cloth Swapping with Deep…
-
### Your current environment
The output of `python collect_env.py`
```text
Collecting environment information...
WARNING 10-25 14:14:20 _custom_ops.py:19] Failed to import from vllm._C with Im…
-
I've seen this as a previous issue but it was closed. I have access to the required HW but I am still encountering the error message shown below:
Traceback (most recent call last):
File "inferen…
-
Pytorch 2.1 compile mode supports fused kernels which updated the performance flag.
Is there any document to compare the performance with pytorch 2.1 compile mode . For example, 5 CNN models and 5…
-
# Morphology CNN for Galaxy10 DECaLS
A simple small CNN to classify Galaxy10 DECaLS images.
Contacts: Mike Walmsley
Participants: as above
## Goals and deliverable
Script to train a simpl…
-
**Target:** Figure out if by default Torch `scaled_dot_product_attention` when executing in Hopper architecture, thus `PLATFORM_SUPPORTS_CUDNN_ATTENTION` and `SM90OrLater` evaluate to `True`, executes…
-
### Describe the bug
When using rotation_matrix_to_angle_axis and angle_axis_to_rotation_matrix as conversion, the loss may have NaN gradient.
Especially when the angle of axis angle is very smal…
-
### 🐛 Describe the bug
See code snippets:
```
import torch
from torch import nn
m = nn.ConvTranspose3d(32, 16, bias=False, kernel_size=(4, 4, 4), padding=(1, 1, 1), stride=(2, 2, 2))
input = t…