facebookresearch · prigoyal · Sep 21, 2021
diff --git a/.github/CONTRIBUTING.md b/.github/CONTRIBUTING.md
@@ -31,17 +31,17 @@ VISSL is designed to be extensible so that it's easy to extend any modular compo
 
 When sending a PR, please do:
 
-1. Fork the repo and create your branch from `master`.
+1. Fork the repo and create your branch from `main`.
 2. If a PR contains multiple orthogonal changes, split it to several PRs.
 3. If you've added code that should be tested, add tests.
 4. If you've changed APIs, update the documentation.
-5. Ensure the test suite passes. Follow [cpu test instructions](https://github.com/facebookresearch/vissl/blob/master/tests/README.md) and [integration tests][https://github.com/facebookresearch/vissl/blob/master/dev/run_quick_tests.sh].
+5. Ensure the test suite passes. Follow [cpu test instructions](https://github.com/facebookresearch/vissl/blob/main/tests/README.md) and [integration tests][https://github.com/facebookresearch/vissl/blob/main/dev/run_quick_tests.sh].
 6. Make sure your code follows our coding practices (see next section).
 7. If you haven't already, complete the Contributor License Agreement ("CLA").
 
 ## Coding Style
 
-Please follow [our coding practices](https://github.com/facebookresearch/vissl/blob/master/dev/README.md#practices-for-coding-quality) and choose either option to properly format your code before submitting PRs.
+Please follow [our coding practices](https://github.com/facebookresearch/vissl/blob/main/dev/README.md#practices-for-coding-quality) and choose either option to properly format your code before submitting PRs.
 
 ## Contributor License Agreement ("CLA")
 In order to accept your pull request, we need you to submit a CLA. You only need

diff --git a/.github/ISSUE_TEMPLATE/bugs.md b/.github/ISSUE_TEMPLATE/bugs.md
@@ -28,7 +28,7 @@ please tell us the expected behavior.
 
 Provide your environment information using the following command:
 ```
-wget -nc -q https://github.com/facebookresearch/vissl/raw/master/vissl/utils/collect_env.py && python collect_env.py
+wget -nc -q https://github.com/facebookresearch/vissl/raw/main/vissl/utils/collect_env.py && python collect_env.py
 ```
 
 ## When to expect Triage

diff --git a/.github/ISSUE_TEMPLATE/documentation.md b/.github/ISSUE_TEMPLATE/documentation.md
@@ -6,4 +6,4 @@ about: Report an issue related to VISSL documentation
 
 ## 📚 VISSL Documentation
 
-A clear and concise description of what content in the [Docs](https://github.com/facebookresearch/vissl/tree/master/docs) is an issue.
+A clear and concise description of what content in the [Docs](https://github.com/facebookresearch/vissl/tree/main/docs) is an issue.
diff --git a/.github/ISSUE_TEMPLATE/questions-help-support.md b/.github/ISSUE_TEMPLATE/questions-help-support.md
@@ -12,7 +12,7 @@ Describe what you want to do, including:
 
 ## ❓ What does an API do and how to use it?
 Please link to which API or documentation you're asking about from
-https://github.com/facebookresearch/vissl/tree/master/docs
+https://github.com/facebookresearch/vissl/tree/main/docs
 
 
 NOTE:

diff --git a/.github/ISSUE_TEMPLATE/unexpected-problems-bugs.md b/.github/ISSUE_TEMPLATE/unexpected-problems-bugs.md
@@ -38,9 +38,9 @@ Only in one of the two conditions, we will help with it:
 
 Provide your environment information using the following command:
 ```
-wget -nc -q https://github.com/facebookresearch/vissl/raw/master/vissl/utils/collect_env.py && python collect_env.py
+wget -nc -q https://github.com/facebookresearch/vissl/raw/main/vissl/utils/collect_env.py && python collect_env.py
 ```
 
 If your issue looks like an installation issue / environment issue,
 please first try to solve it with the instructions in
-https://github.com/facebookresearch/vissl/tree/master/docs
+https://github.com/facebookresearch/vissl/tree/main/docs
diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml
@@ -11,7 +11,7 @@ repos:
     -   id: check-ast
     -   id: check-merge-conflict
     -   id: no-commit-to-branch
-        args: ['--branch=master']
+        args: ['--branch=main']
     -   id: end-of-file-fixer
 
 -   repo: https://github.com/psf/black

diff --git a/GETTING_STARTED.md b/GETTING_STARTED.md
@@ -103,4 +103,4 @@ python3 run_distributed_engines.py \
     config.HOOKS.TENSORBOARD_SETUP.USE_TENSORBOARD=true
 ```
 
-Explore **all the parameters and settings VISSL supports** in [VISSL defaults.yaml file](https://github.com/facebookresearch/vissl/blob/master/vissl/config/defaults.yaml)
+Explore **all the parameters and settings VISSL supports** in [VISSL defaults.yaml file](https://github.com/facebookresearch/vissl/blob/main/vissl/config/defaults.yaml)
diff --git a/INSTALL.md b/INSTALL.md
@@ -131,7 +131,7 @@ python -c 'import vissl, apex'
 
 #### Step 1: Create Conda environment
 
-If you don't have anaconda, [run this bash scrip to install conda](https://github.com/facebookresearch/vissl/blob/master/docker/common/install_conda.sh).
+If you don't have anaconda, [run this bash scrip to install conda](https://github.com/facebookresearch/vissl/blob/main/docker/common/install_conda.sh).
 
 ```bash
 conda create -n vissl_env python=3.7

diff --git a/MODEL_ZOO.md b/MODEL_ZOO.md
@@ -41,7 +41,7 @@ python extra_scripts/convert_vissl_to_torchvision.py \
 
 ### Converting Torchvision to VISSL
 
-All the ResNe(X)t models in Torchvision can be directly loaded in VISSL. This involves simply setting the `REMOVE_PREFIX`, `APPEND_PREFIX` options in the config file following the [instructions here](https://github.com/facebookresearch/vissl/blob/master/vissl/config/defaults.yaml#L418-L435). Also, see the example below for how torchvision models are loaded.
+All the ResNe(X)t models in Torchvision can be directly loaded in VISSL. This involves simply setting the `REMOVE_PREFIX`, `APPEND_PREFIX` options in the config file following the [instructions here](https://github.com/facebookresearch/vissl/blob/main/vissl/config/defaults.yaml#L418-L435). Also, see the example below for how torchvision models are loaded.
 
 
 ## Models
@@ -50,20 +50,20 @@ VISSL is 100% compatible with TorchVision ResNet models. You can benchmark these
 
 ### Supervised
 
-To reproduce the numbers below, the experiment configuration is provided in json format for each model [here](https://github.com/facebookresearch/vissl/tree/master/configs/config/model_zoo/benchmark_in1k_linear_supervised.json).
+To reproduce the numbers below, the experiment configuration is provided in json format for each model [here](https://github.com/facebookresearch/vissl/tree/main/configs/config/model_zoo/benchmark_in1k_linear_supervised.json).
 
 | Method | Model | PreTrain dataset | ImageNet top-1 acc. | URL |
 | ------ | ----- | ---------------- | ------------------- | --- |
-| Supervised      |    [RN50 - Torchvision](https://github.com/pytorch/vision/blob/master/torchvision/models/resnet.py)                             |     ImageNet      | 76.1 | [model](https://download.pytorch.org/models/resnet50-19c8e357.pth)
-| Supervised      |    [RN101 - Torchvision](https://github.com/pytorch/vision/blob/master/torchvision/models/resnet.py)                            |     ImageNet      | 77.21 | [model](https://download.pytorch.org/models/resnet101-5d3b4d8f.pth)
+| Supervised      |    [RN50 - Torchvision](https://github.com/pytorch/vision/blob/main/torchvision/models/resnet.py)                             |     ImageNet      | 76.1 | [model](https://download.pytorch.org/models/resnet50-19c8e357.pth)
+| Supervised      |    [RN101 - Torchvision](https://github.com/pytorch/vision/blob/main/torchvision/models/resnet.py)                            |     ImageNet      | 77.21 | [model](https://download.pytorch.org/models/resnet101-5d3b4d8f.pth)
 | Supervised      |    [RN50 - Caffe2](https://github.com/facebookresearch/fair_self_supervision_benchmark/blob/master/MODEL_ZOO.md#models)         |     ImageNet      | 75.88 | [model](https://dl.fbaipublicfiles.com/vissl/model_zoo/converted_vissl_rn50_supervised_in1k_caffe2.torch)
 | Supervised      |    [RN50 - Caffe2](https://github.com/facebookresearch/fair_self_supervision_benchmark/blob/master/MODEL_ZOO.md#models)         |     Places205     | 58.49 | [model](https://dl.fbaipublicfiles.com/vissl/model_zoo/converted_vissl_rn50_supervised_places205_caffe2.torch)
 | Supervised      |    [Alexnet BVLC - Caffe2](https://github.com/facebookresearch/fair_self_supervision_benchmark/blob/master/MODEL_ZOO.md#models) |     ImageNet      | 49.54 | [model](https://dl.fbaipublicfiles.com/vissl/model_zoo/converted_caffenet_bvlc_in1k_supervised.torch)
 | Supervised      |    RN50 - VISSL - 105 epochs                                                                                                    |     ImageNet      | 75.45 | [model](https://dl.fbaipublicfiles.com/vissl/model_zoo/sup_rn50_in1k_ep105_supervised_8gpu_resnet_17_07_20.733dbdee/model_final_checkpoint_phase208.torch)
 
 ### Semi-weakly and Semi-supervised
 
-To reproduce the numbers below, the experiment configuration is provided in json format for each model [here](https://github.com/facebookresearch/vissl/tree/master/configs/config/model_zoo/benchmark_in1k_linear_supervised.json).
+To reproduce the numbers below, the experiment configuration is provided in json format for each model [here](https://github.com/facebookresearch/vissl/tree/main/configs/config/model_zoo/benchmark_in1k_linear_supervised.json).
 
 | Method | Model | PreTrain dataset | ImageNet top-1 acc. | URL |
 | ------ | ----- | ---------------- | ------------------- | --- |
@@ -72,7 +72,7 @@ To reproduce the numbers below, the experiment configuration is provided in json
 
 ### Jigsaw
 
-To reproduce the numbers below, the experiment configuration is provided in json format for each model [here](https://github.com/facebookresearch/vissl/tree/master/configs/config/model_zoo/benchmark_in1k_linear_jigsaw.json).
+To reproduce the numbers below, the experiment configuration is provided in json format for each model [here](https://github.com/facebookresearch/vissl/tree/main/configs/config/model_zoo/benchmark_in1k_linear_jigsaw.json).
 
 | Method | Model | PreTrain dataset | ImageNet top-1 acc. | URL |
 | ------ | ----- | ---------------- | ------------------- | --- |
@@ -89,7 +89,7 @@ To reproduce the numbers below, the experiment configuration is provided in json
 
 ### Colorization
 
-To reproduce the numbers below, the experiment configuration is provided in json format for each model [here](https://github.com/facebookresearch/vissl/tree/master/configs/config/model_zoo/benchmark_in1k_linear_colorization.json).
+To reproduce the numbers below, the experiment configuration is provided in json format for each model [here](https://github.com/facebookresearch/vissl/tree/main/configs/config/model_zoo/benchmark_in1k_linear_colorization.json).
 
 | Method | Model | PreTrain dataset | ImageNet top-1 acc. | URL |
 | ------ | ----- | ---------------- | ------------------- | --- |
@@ -102,7 +102,7 @@ To reproduce the numbers below, the experiment configuration is provided in json
 
 ### RotNet
 
-To reproduce the numbers below, the experiment configuration is provided in json format for each model [here](https://github.com/facebookresearch/vissl/tree/master/configs/config/model_zoo/benchmark_in1k_linear_rotnet_deepcluster_clusterfit.json).
+To reproduce the numbers below, the experiment configuration is provided in json format for each model [here](https://github.com/facebookresearch/vissl/tree/main/configs/config/model_zoo/benchmark_in1k_linear_rotnet_deepcluster_clusterfit.json).
 
 | Method | Model | PreTrain dataset | ImageNet top-1 acc. | URL |
 | ------ | ----- | ---------------- | ------------------- | --- |
@@ -112,23 +112,23 @@ To reproduce the numbers below, the experiment configuration is provided in json
 
 ### DeepCluster
 
-To reproduce the numbers below, the experiment configuration is provided in json format for each model [here](https://github.com/facebookresearch/vissl/tree/master/configs/config/model_zoo/benchmark_in1k_linear_rotnet_deepcluster_clusterfit.json).
+To reproduce the numbers below, the experiment configuration is provided in json format for each model [here](https://github.com/facebookresearch/vissl/tree/main/configs/config/model_zoo/benchmark_in1k_linear_rotnet_deepcluster_clusterfit.json).
 
 | Method | Model | PreTrain dataset | ImageNet top-1 acc. | URL |
 | ------ | ----- | ---------------- | ------------------- | --- |
 | [DeepCluster](https://arxiv.org/abs/1807.05520)   |    [AlexNet official](https://github.com/facebookresearch/deepcluster#pre-trained-models)   |   ImageNet-1K      | 37.88 | [model](https://dl.fbaipublicfiles.com/vissl/model_zoo/deepcluster_alexnet_checkpoint.torch)
 
 ### ClusterFit
 
-To reproduce the numbers below, the experiment configuration is provided in json format for each model [here](https://github.com/facebookresearch/vissl/tree/master/configs/config/model_zoo/benchmark_in1k_linear_rotnet_deepcluster_clusterfit.json).
+To reproduce the numbers below, the experiment configuration is provided in json format for each model [here](https://github.com/facebookresearch/vissl/tree/main/configs/config/model_zoo/benchmark_in1k_linear_rotnet_deepcluster_clusterfit.json).
 
 | Method | Model | PreTrain dataset | ImageNet top-1 acc. | URL |
 | ------ | ----- | ---------------- | ------------------- | --- |
 | [ClusterFit](https://arxiv.org/abs/1912.03330)    |    RN50 - 105 epochs - 16K clusters from RotNet  |  ImageNet-1K   | 53.63 | [model](https://dl.fbaipublicfiles.com/vissl/model_zoo/converted_vissl_rn50_rotnet_16kclusters_in1k_ep105.torch)
 
 ### NPID
 
-To reproduce the numbers below, the experiment configuration is provided in json format for each model [here](https://github.com/facebookresearch/vissl/tree/master/configs/config/model_zoo/benchmark_in1k_linear_npid_pirl.json).
+To reproduce the numbers below, the experiment configuration is provided in json format for each model [here](https://github.com/facebookresearch/vissl/tree/main/configs/config/model_zoo/benchmark_in1k_linear_npid_pirl.json).
 
 | Method | Model | PreTrain dataset | ImageNet top-1 acc. | URL |
 | ------ | ----- | ---------------- | ------------------- | --- |
@@ -137,7 +137,7 @@ To reproduce the numbers below, the experiment configuration is provided in json
 
 ### NPID++
 
-To reproduce the numbers below, the experiment configuration is provided in json format for each model [here](https://github.com/facebookresearch/vissl/tree/master/configs/config/model_zoo/benchmark_in1k_linear_npid_pirl.json).
+To reproduce the numbers below, the experiment configuration is provided in json format for each model [here](https://github.com/facebookresearch/vissl/tree/main/configs/config/model_zoo/benchmark_in1k_linear_npid_pirl.json).
 
 | Method | Model | PreTrain dataset | ImageNet top-1 acc. | URL |
 | ------ | ----- | ---------------- | ------------------- | --- |
@@ -146,18 +146,18 @@ To reproduce the numbers below, the experiment configuration is provided in json
 
 ### PIRL
 
-To reproduce the numbers below, the experiment configuration is provided in json format for each model [here](https://github.com/facebookresearch/vissl/tree/master/configs/config/model_zoo/benchmark_in1k_linear_npid_pirl.json).
+To reproduce the numbers below, the experiment configuration is provided in json format for each model [here](https://github.com/facebookresearch/vissl/tree/main/configs/config/model_zoo/benchmark_in1k_linear_npid_pirl.json).
 
 | Method | Model | PreTrain dataset | ImageNet top-1 acc. | URL |
 | ------ | ----- | ---------------- | ------------------- | --- |
 | [PIRL](https://arxiv.org/abs/1912.01991)      |    RN50 - 200 epochs       |      ImageNet-1K      | 62.55 | [model](https://dl.fbaipublicfiles.com/vissl/model_zoo/pirl_jigsaw_4node_200ep_pirl_jigsaw_4node_resnet_22_07_20.ffd17b75/model_final_checkpoint_phase199.torch)
 | [PIRL](https://arxiv.org/abs/1912.01991)      |    RN50 - 800 epochs       |      ImageNet-1K      | 64.29 | [model](https://dl.fbaipublicfiles.com/vissl/model_zoo/pirl_jigsaw_4node_pirl_jigsaw_4node_resnet_22_07_20.34377f59/model_final_checkpoint_phase799.torch)
 
-**NOTE:** Please see [projects/PIRL/README.md](https://github.com/facebookresearch/vissl/blob/master/projects/PIRL/README.md) for more PIRL models provided by authors.
+**NOTE:** Please see [projects/PIRL/README.md](https://github.com/facebookresearch/vissl/blob/main/projects/PIRL/README.md) for more PIRL models provided by authors.
 
 ### SimCLR
 
-To reproduce the numbers below, the experiment configuration is provided in json format for each model [here](https://github.com/facebookresearch/vissl/tree/master/configs/config/model_zoo/benchmark_in1k_linear_simclr.json).
+To reproduce the numbers below, the experiment configuration is provided in json format for each model [here](https://github.com/facebookresearch/vissl/tree/main/configs/config/model_zoo/benchmark_in1k_linear_simclr.json).
 
 | Method | Model | PreTrain dataset | ImageNet top-1 acc. | URL |
 | ------ | ----- | ---------------- | ------------------- | --- |
@@ -174,7 +174,7 @@ To reproduce the numbers below, the experiment configuration is provided in json
 
 ### DeepClusterV2
 
-To reproduce the numbers below, the experiment configuration is provided in json format for each model [here](https://github.com/facebookresearch/vissl/tree/master/configs/config/model_zoo/benchmark_in1k_linear_deepclusterv2_swav.json).
+To reproduce the numbers below, the experiment configuration is provided in json format for each model [here](https://github.com/facebookresearch/vissl/tree/main/configs/config/model_zoo/benchmark_in1k_linear_deepclusterv2_swav.json).
 
 | Method | Model | PreTrain dataset | ImageNet top-1 acc. | URL |
 | ------ | ----- | ---------------- | ------------------- | --- |
@@ -184,7 +184,7 @@ To reproduce the numbers below, the experiment configuration is provided in json
 
 ### SwAV
 
-To reproduce the numbers below, the experiment configuration is provided in json format for each model [here](https://github.com/facebookresearch/vissl/tree/master/configs/config/model_zoo/benchmark_in1k_linear_deepclusterv2_swav.json).
+To reproduce the numbers below, the experiment configuration is provided in json format for each model [here](https://github.com/facebookresearch/vissl/tree/main/configs/config/model_zoo/benchmark_in1k_linear_deepclusterv2_swav.json).
 
 There is some standard deviation in linear results if we run the same eval several times and pre-train a SwAV model several times. The evals reported below are for 1 run.
 
@@ -200,7 +200,7 @@ There is some standard deviation in linear results if we run the same eval sever
 | [SwAV](https://arxiv.org/abs/2006.09882)   |    RN50-w2 - 400 epochs - 2x224+6x96 - 4096 batch-size |    ImageNet-1K      | 77.01 | [model](https://dl.fbaipublicfiles.com/vissl/model_zoo/swav_rn50w2_in1k_bs32_16node_400ep_swav_8node_resnet_30_07_20.93563e51/model_final_checkpoint_phase399.torch)
 | [SwAV](https://arxiv.org/abs/2006.09882)   |    RN50-w4 - 400 epochs - 2x224+6x96 - 2560 batch-size |    ImageNet-1K      | 77.03 | [model](https://dl.fbaipublicfiles.com/vissl/model_zoo/swav_rn50w4_in1k_bs40_8node_400ep_swav_8node_resnet_30_07_20.1736135b/model_final_checkpoint_phase399.torch)
 
-**NOTE:** Please see [projects/SwAV/README.md](https://github.com/facebookresearch/vissl/blob/master/projects/SwAV/README.md) for more SwAV models provided by authors.
+**NOTE:** Please see [projects/SwAV/README.md](https://github.com/facebookresearch/vissl/blob/main/projects/SwAV/README.md) for more SwAV models provided by authors.
 
 ### MoCoV2
 
@@ -217,7 +217,7 @@ There is some standard deviation in linear results if we run the same eval sever
 
 ### DINO
 
-The model is obtained with [this config](https://github.com/facebookresearch/vissl/blob/master/configs/config/pretrain/dino/dino_16gpus_deits16.yaml).
+The model is obtained with [this config](https://github.com/facebookresearch/vissl/blob/main/configs/config/pretrain/dino/dino_16gpus_deits16.yaml).
 | Method | Model | PreTrain dataset | ImageNet k-NN acc. | URL |
 | ------ | ----- | ---------------- | ------------------- | --- |
 | [DINO](https://arxiv.org/abs/)   |    DeiT-S/16 - 300 epochs - 1024 batch-size         |    ImageNet-1K      | 73.4 | [model](https://dl.fbaipublicfiles.com/vissl/model_zoo/dino_300ep_deitsmall16/model_final_checkpoint_phase299.torch)