The CLEAR Benchmark:
Continual LEArning on Real-World Imagery

Labeled Data Hierarchy

The tree hierarchy of the data is showing as the following

root/
|   class_names.txt (each line is a class name)
|   labeled_metadata.json (with paths to labeled images' metadata)
|   all_metadata.json (with paths to all images' metadata)
|   download_all_images.py (for downloading unlabeled images)
└───labeled_images
|   └───1
|   |   └───computer
|   |   |   |   235821044.jpg
|   |   |   |   ...
|   |   └───camera
|   |   |   |   269400202.jpg
|   |   |   |   ...
|   |   └───...
|   └───2
|   └───...
└───labeled_metadata
|   └───1
|   |   |   computer.json (dict: key is flickr ID, value is metadata)
|   |   |   camera.json
|   |   |   ...
|   └───2
|   └───...
└───all_metadata
│   │   0.json
|   |   1.json
|   |   ...
└───features
|   └───moco_b0
|   |   |   features.json (with paths to labeled images' features files)
|   |   |   state_dict.pth.tar (a copy of the state_dict file)
|   |   └───1
|   |   |   |   computer.pth (dict: key is flickr ID, value is torch tensor)
|   |   |   |   camera.pth
|   |   |   |   ...
|   |   └───2
|   |   |   |   ...
|   |   └───...
|   └───moco_imagenet
|   |   └───...
|   └───byol_imagenet
|   |   └───...
|   └───imagenet
|   |   └───...