places365
places365 copied to clipboard
have upgraded pretrained models to pytorch1.x
https://github.com/HuaizhengZhang/scene-recognition-pytorch1.x-tf2.x
I have retrained many models by using pytorch 1.4 based on python3.7.
Anyone interested in using scene classification models with the latest pytorch version is free to access.
The project is still under active development. You are welcome to PR.
PyTorch version: 1.4.0
Is debug build: No
CUDA used to build PyTorch: 10.1
OS: Ubuntu 18.04.3 LTS
GCC version: (Ubuntu 7.4.0-1ubuntu1~18.04.1) 7.4.0
CMake version: version 3.10.2
Python version: 3.7
Is CUDA available: Yes
CUDA runtime version: 10.1.243
Nvidia driver version: 418.116.00
cuDNN version: /usr/lib/x86_64-linux-gnu/libcudnn.so.7.6.2
Versions of relevant libraries:
[pip] numpy==1.18.1
[pip] torch==1.4.0
[pip] torchvision==0.5.0
The MIT project website is currently down, including their pre-trained model download links. Your repository is currently the only one that I can find that hosts pre-trained weights. Thank you so much!