Comments (7)
@naeem7789 Hello, my code ran on the desktop, which may be a little different from your situation. When you use the code 'torch.hub.load()' to create the pre-trained model, the folder ‘ ~/.cache/torch/hub/’ will be created automatically to store the downloaded files and the pre-trained model checkpoint.
If your code is run on kaggle.com notebook, I think you can do the following:
a. Copy the code into your own code
b. Use the function resnext101_32x48d_wsl() copied into your code to replace the code ‘model = torch.hub.load('facebookresearch/WSL-Images', 'resnext101_32x48d_wsl')’ to load the pre-trained model.
If you still have questions, you can continue to contact me. Good luck !
from wsl-images.
I have solved this problem. @saarimrahman The solution is:
a. manually download this code
b. unzip and put it under ~/.cache/torch/hub/
c. finally rename it to facebookresearch_WSL-Images_master. Then you can run your code successfully.
from wsl-images.
I ended up resolving this by downloading the checkpoint for the model from this repo, and copying over the model instantiation & definition from here. Then once I instantiated the model, I loaded the weights using the checkpoint I downloaded.
from wsl-images.
I have the same problem. Hope you can help to solve it. Looking forward to your reply!
from wsl-images.
@Gao-JT we are facing the same problem.
Can you elaborate where we have to create that ~/.cache/torch/hub/?
from wsl-images.
We are running the code on kaggle.com notebook
from wsl-images.
@Gao-JT , Thank you Sir , its working
from wsl-images.
Related Issues (20)
- Passing 'pretrained' parameter to torch.hub.load raises error
- About training set
- Is there anyone who implemented the ResNeXt WSL reproduction results in tensorflow2.x or tensorflow1.x,Thx!
- Pretrained hashtag prediction model HOT 4
- how can I do the final hashtag prediction using the pretrained model?
- How to find the precision of the various layers when laoding the models resnext101 models
- Significant numerical differences with torch.amp.autocast() compared with stock pretrained resnext101
- default branch name breaking torch.hub HOT 1
- Will ResNeXt-101 32x4d be available? HOT 1
- Error
- cuda out of memory
- Model performance
- Get "TypeError: __init__() got an unexpected keyword argument 'groups'" during ResNet init HOT 1
- About performance in Cub-200 finetune. HOT 2
- x101-32*8d doesn't work well when I put it in cascade rcnn in mmdetection HOT 5
- can not load model from hub
- OSError: [Errno 22] Invalid argument HOT 4
- WSL models not fine-tuned for ImageNet HOT 7
- How to solve ZeroDivisionError: float division by zero? HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from wsl-images.