ayulockin / SwAV-TF

TensorFlow implementation of "Unsupervised Learning of Visual Features by Contrasting Cluster Assignments".
https://app.wandb.ai/authors/swav-tf/reports/Unsupervised-Visual-Representation-Learning-with-SwAV--VmlldzoyMjg3Mzg
Apache License 2.0
85 stars 12 forks source link

Restructuring the files #8

Closed sayakpaul closed 4 years ago

sayakpaul commented 4 years ago

As we had developed a number of notebooks I thought we could structure them a bit better. In this PR, I attempt at that and I went for the following directory structure:

├── LICENSE
├── README.md
├── Train_SwAV_10_epochs.ipynb
├── Train_SwAV_40_epochs.ipynb
├── fine_tuning
│   ├── Fine_Tuning_10_Epochs.ipynb
│   ├── Fine_Tuning_40_Epochs.ipynb
│   ├── Fine_Tuning_Supervised_10Perc.ipynb
│   └── Fine_Tuning_Supervised_Full_Dataset.ipynb
├── initial_notebooks
│   ├── Building_MultiCropDataset.ipynb
│   ├── Minimal_Sinkhorn_Knopp.ipynb
│   └── MultiCropDataset_Architecture.ipynb
├── linear_evaluation
│   ├── Linear_Evaluation_10_Epochs.ipynb
│   ├── Linear_Evaluation_40_Epochs.ipynb
│   └── Linear_Evaluation_Fully_Supervised.ipynb
└── utils
    ├── architecture.py
    └── multicrop_dataset.py

Additionally, as I changed the location of many of the notebooks I had to remove the "Open in Colab" button from them to prevent "Not found" error.