ClassyVision icon indicating copy to clipboard operation
ClassyVision copied to clipboard

An end-to-end PyTorch framework for image and video classification

Results 53 ClassyVision issues
Sort by recently updated
recently updated
newest added

Summary: Fixes https://fb.workplace.com/groups/1148364849411890/permalink/1278947843020256/ Differential Revision: D45665663

CLA Signed
fb-exported

Summary: Moves the progressbar hook to tqdm. The new hook lets tqdm estimate the remaining time for the overall task, and for the current phase in a given epoch (train...

CLA Signed
fb-exported

Summary: We want to check whether training XRayVideo with simply video resizing (in addition to other existing transformation like horizontal flipping and normalization) without random corp is sufficient. The resize...

CLA Signed
fb-exported

Summary: Productionization/testing requires model output in dict. This change supports exporting the model as such. Differential Revision: D27917487

CLA Signed
fb-exported

## 📚 Documentation [efficientnet.py](https://github.com/facebookresearch/ClassyVision/blob/main/classy_vision/models/efficientnet.py) It's a clean and well documented code. Kudos to the authors and thank you for making it open source :) On the line 195, I think...

## ❓ Questions and Help I have created the data folder with the following structure train/label_1/aa.png train/label_2/bb.png val/label_1/cc.png and so on The config used is { "name": "classification_task", "num_epochs": 95,...

## 🚀 Feature We should pass a reference to the task object to the optimizer + param scheduler to be able to use more complex parameter schedulers ## Motivation /...

enhancement

Please don't merge this PR yet. Still troubleshooting changes. * delete website/siteConfig.js * create website/docusaurus.config.js * create website/src/css/custom.css * update .gitignore * update website/package.json

CLA Signed

Differential Revision: D29577409

CLA Signed
fb-exported