-
With #26 fixed on my side, I was able to perform some benchmarks now. The libDNN generated convolutions are about 3x-4x faster than my naive kernel described in #26, which is very nice! But they are s…
romix updated
6 years ago
-
Thank you for sharing the code of this interesting work.
As you mentioned, the experiments can be reproduced by ```python3 -m alsa.main.replicate```. However, it is really not easy to follow the c…
-
Hi, I am fairly new to this, i was hoping you could help me with an error I encounter whenever I try to run train_softmax.py as instructed in the wiki.
here is a copy of the whole process:
D:\Da…
-
### Branch
main branch (mmpretrain version)
### Describe the bug
_base_ = [
'../_base_/models/resnet50.py', # model settings
'../_base_/schedules/imagenet_bs256.py', # schedule…
-
Hi，Thanks for sharing the code. I tried to reproduce your code. I encountered a problem. The environment configuration is the same as your code requirements, but every time the GPU is not working, the…
-
### 🐛 Describe the bug
Trying to import the MNIST dataset on Linux as follows:
```python
import torchvision.datasets as datasets
mnist_trainset = datasets.MNIST(root='./data', train=True, downlo…
-
Hello, I am very glad to see the latest and best quantitative method. I have some questions while reproducing the results. I hope you can answer your questions. I used the script for training RESNET p…
-
### System Info / 系統信息
cuda11.8
x2 3090
linux ubuntu 22.04 lts
pytorch2.4
### Information / 问题信息
- [X] The official example scripts / 官方的示例脚本
- [X] My own modified scripts / 我自己修改的脚本和任务
###…
-
## Instructions To Reproduce the 🐛 Bug:
1. what changes you made (`git diff`) or what code you wrote
```
diff --git a/dev/launch_slurm.sh b/dev/launch_slurm.sh
index 193b09e..60b3e9d 100755
---…
-
I'm using a custom dataset in CoCo format. I have tried a small learning rate, but it is useless.But my dataset can be trained on Faster RCNN and Centernet (In order to save energy, I directly modifie…