PyTorch-Encoding
PyTorch-Encoding copied to clipboard
zhanghang1989
A CV toolkit for my papers.
When I run the following code： **python test.py --dataset ADE20K --model-zoo EncNet_ResNet50s_ADE --eval** I miss the error and i can't fix it : **ImportError: cannot import name 'gpu' from partially...
I can't download resnet50 and resnet101 model pretrained on the pcontext dataset, since my machine is off-line, it might be something wrong when I download it from the url like...
Using /home/user/anaconda3/lib/python3.7/site-packages Finished processing dependencies for torch-encoding==1.2.2b20201225 您好，我在安装torch-encoding成功之后，import encoding的时候报错： Traceback (most recent call last): File "", line 1, in File "/home/user/PyTorch-Encoding/encoding/__init__.py", line 13, in from . import nn, functions, parallel,...
Recently,I came across the paper Fast FCN in which the author uses the pytorch-encoding repository.In order to test their model on CamVid dataset,what changes should I make apart from writign...
Hi Mr. Zhang: When I test pre-trained model on MINC-2500 using: ``python main.py --dataset minc --model deepten --nclass 23 --resume deepten_minc.pth --eval``, I got the following errors: ``` => loading...
Hi, As I was configuring different combinations of ```pytorch``` and ```CUDA``` I realized if your device's current ```nvvc``` version and torch's compiled cuda version differ- which is totally ok for...
Environment: Ubuntu 18.04, CUDA 11.0, PyTorch 1.7.1, A100. When installed from source by `python setup.py install`, an nvcc fatal error raised: ``` nvcc fatal : Unsupported gpu architecture 'compute_80' RuntimeError:...
  [SyncBN Equations.pdf](https://github.com/zhanghang1989/PyTorch-Encoding/files/5287716/SyncBN.Equations.pdf) [SyncBN Implementation.docx](https://github.com/zhanghang1989/PyTorch-Encoding/files/5287717/SyncBN.Implementation.docx)
Dear HangZhang, Thanks for your code! I was working on a multi-GPU version of my code, which is like: model = CDCK2(xxx) model = encoding.parallel.DataParallelModel(model).cuda() The model is something like...
