vturrisi · vturrisi · Nov 29, 2021 · Nov 19, 2021 · Nov 19, 2021 · Nov 19, 2021
diff --git a/.github/CODE_OF_CONDUCT.md b/.github/CODE_OF_CONDUCT.md
@@ -0,0 +1,131 @@
+# Contributor Covenant Code of Conduct
+
+## Our Pledge
+
+We as members, contributors, and leaders pledge to make participation in our
+community a harassment-free experience for everyone, regardless of age, body
+size, visible or invisible disability, ethnicity, sex characteristics, gender
+identity and expression, level of experience, education, socio-economic status,
+nationality, personal appearance, race, caste, color, religion, or sexual
+identity and orientation.
+
+We pledge to act and interact in ways that contribute to an open, welcoming,
+diverse, inclusive, and healthy community.
+
+## Our Standards
+
+Examples of behavior that contributes to a positive environment for our
+community include:
+
+* Demonstrating empathy and kindness toward other people
+* Being respectful of differing opinions, viewpoints, and experiences
+* Giving and gracefully accepting constructive feedback
+* Accepting responsibility and apologizing to those affected by our mistakes,
+  and learning from the experience
+* Focusing on what is best not just for us as individuals, but for the overall
+  community
+
+Examples of unacceptable behavior include:
+
+* The use of sexualized language or imagery, and sexual attention or advances of
+  any kind
+* Trolling, insulting or derogatory comments, and personal or political attacks
+* Public or private harassment
+* Publishing others' private information, such as a physical or email address,
+  without their explicit permission
+* Other conduct which could reasonably be considered inappropriate in a
+  professional setting
+
+## Enforcement Responsibilities
+
+Community leaders are responsible for clarifying and enforcing our standards of
+acceptable behavior and will take appropriate and fair corrective action in
+response to any behavior that they deem inappropriate, threatening, offensive,
+or harmful.
+
+Community leaders have the right and responsibility to remove, edit, or reject
+comments, commits, code, wiki edits, issues, and other contributions that are
+not aligned to this Code of Conduct, and will communicate reasons for moderation
+decisions when appropriate.
+
+## Scope
+
+This Code of Conduct applies within all community spaces, and also applies when
+an individual is officially representing the community in public spaces.
+Examples of representing our community include using an official e-mail address,
+posting via an official social media account, or acting as an appointed
+representative at an online or offline event.
+
+## Enforcement
+
+Instances of abusive, harassing, or otherwise unacceptable behavior may be
+reported to the community leaders responsible for enforcement at `vt.turrisi@gmail.com`.
+All complaints will be reviewed and investigated promptly and fairly.
+
+All community leaders are obligated to respect the privacy and security of the
+reporter of any incident.
+
+## Enforcement Guidelines
+
+Community leaders will follow these Community Impact Guidelines in determining
+the consequences for any action they deem in violation of this Code of Conduct:
+
+### 1. Correction
+
+**Community Impact**: Use of inappropriate language or other behavior deemed
+unprofessional or unwelcome in the community.
+
+**Consequence**: A private, written warning from community leaders, providing
+clarity around the nature of the violation and an explanation of why the
+behavior was inappropriate. A public apology may be requested.
+
+### 2. Warning
+
+**Community Impact**: A violation through a single incident or series of
+actions.
+
+**Consequence**: A warning with consequences for continued behavior. No
+interaction with the people involved, including unsolicited interaction with
+those enforcing the Code of Conduct, for a specified period of time. This
+includes avoiding interactions in community spaces as well as external channels
+like social media. Violating these terms may lead to a temporary or permanent
+ban.
+
+### 3. Temporary Ban
+
+**Community Impact**: A serious violation of community standards, including
+sustained inappropriate behavior.
+
+**Consequence**: A temporary ban from any sort of interaction or public
+communication with the community for a specified period of time. No public or
+private interaction with the people involved, including unsolicited interaction
+with those enforcing the Code of Conduct, is allowed during this period.
+Violating these terms may lead to a permanent ban.
+
+### 4. Permanent Ban
+
+**Community Impact**: Demonstrating a pattern of violation of community
+standards, including sustained inappropriate behavior, harassment of an
+individual, or aggression toward or disparagement of classes of individuals.
+
+**Consequence**: A permanent ban from any sort of public interaction within the
+community.
+
+## Attribution
+
+This Code of Conduct is adapted from the [Contributor Covenant][homepage],
+version 2.1, available at
+[https://www.contributor-covenant.org/version/2/1/code_of_conduct.html][v2.1].
+
+Community Impact Guidelines were inspired by
+[Mozilla's code of conduct enforcement ladder][Mozilla CoC].
+
+For answers to common questions about this code of conduct, see the FAQ at
+[https://www.contributor-covenant.org/faq][FAQ]. Translations are available at
+[https://www.contributor-covenant.org/translations][translations].
+
+[homepage]: https://www.contributor-covenant.org
+[v2.1]: https://www.contributor-covenant.org/version/2/1/code_of_conduct.html
+[Mozilla CoC]: https://github.com/mozilla/diversity
+[FAQ]: https://www.contributor-covenant.org/faq
+[translations]: https://www.contributor-covenant.org/translations
diff --git a/.github/CONTRIBUTING.md b/.github/CONTRIBUTING.md
@@ -0,0 +1,35 @@
+# Contributing to solo-learn
+We want to make contributing to this project as easy and transparent as possible. Also, we encourage the community to help and improve the library.
+
+## Our Development Process
+We fix issues as we discover them, either by running the code or by checking the issues tab on github. Major changes (e.g., new methods, other downstream tasks, additional features etc), are added periodically and based on how we judge its priority.
+
+## Issues
+We use GitHub issues to track public bugs and questions. We will make templates for each type of issue in [issue templates](https://github.com/vturrisi/solo-learn/issues/new/choose), but for now, check if your issue has a fitting template or please be as verbose and clear as possible. Also, provide ways to reproduce the issue (e.g., bash script).
+
+
+## Pull Requests
+We actively welcome pull requests.
+
+Before you start implementing a new method, make sure that the method has an accompaning paper (arxiv versions are fine) with competitive experimental results.
+
+When implementing the new method:
+1. Fork the repo and create your branch from `main`.
+2. Extend the available `BaseMethod` and `BaseMomentumMethod` classes, or even the methods that are already implemented. Your new method should reuse our base structures or provide enough justification for changing/incrementing the base structures if needed.
+3. Provide a clear and simple implementation following our code style.
+4. Provide unit tests.
+5. Modify the documentation to add the new method and accompanying features. We use Sphinx for that.
+6. Provide bash files for running the method.
+7. Reproduce competitive results on at least CIFAR-10 and CIFAR-100. Imagenet-100/Imagenet results are also desirable, but we can run those eventually.
+8. Ensure that your tests by running `python -m pytest --cov=solo tests`.
+
+If you are fixing a bug, please open an issue beforehand. If should also modify the library as minimally as possible.
+
+When implementing extensions for the library, detail why this is important by providing use cases.
+
+## Coding Style
+
+Please follow our coding style and use [black](https://github.com/psf/black) with line length of 100. We will update this section with a more hands-on guide.
+
+## License
+By contributing to solo-learn, you agree that your contributions will be licensed under the LICENSE file in the root directory of this source tree.
diff --git a/.github/ISSUE_TEMPLATE/bugs.md b/.github/ISSUE_TEMPLATE/bugs.md
@@ -0,0 +1,35 @@
+<!-- Adapted from https://github.com/facebookresearch/vissl/blob/main/.github/ISSUE_TEMPLATE/bugs.md -->
+
+---
+name: "🐛 Bugs"
+about: Report bugs in solo-learn
+title: Please read & provide the following
+
+---
+
+## Instructions To Reproduce the 🐛 Bug:
+
+1. what changes you made (`git diff`) or what code you wrote
+```
+<put diff or code here>
+```
+2. what exact command you run:
+3. what you observed (including __full logs__):
+```
+<put logs here>
+```
+4. please simplify the steps as much as possible so they do not require additional resources to
+   run, such as a private dataset.
+
+## Expected behavior:
+
+If there are no obvious error in "what you observed" provided above,
+please tell us the expected behavior.
+
+## Environment:
+
+Provide information about your environment.
+
+## When to expect Triage
+
+We try to answer as soon as possible, but time may vary according to other deadlines and the importance of the bug reported.
diff --git a/.github/ISSUE_TEMPLATE/new_method.md b/.github/ISSUE_TEMPLATE/new_method.md
@@ -0,0 +1,26 @@
+<!-- Adapted from https://github.com/facebookresearch/vissl/blob/main/.github/ISSUE_TEMPLATE/new-ssl-approach.md -->
+
+---
+name: "\U0001F31F New SSL method addition"
+about: Submit a proposal of implementation/request to implement a new SSL method in solo-learn.
+
+---
+
+# 🌟 New SSL method addition
+
+## Approach description
+
+Important information only describing the approach, link to the arXiv paper.
+
+## Status of the current implement
+
+Information regarding stuff that you have already implemented for the method.
+As a general checklist, you should have:
+* [ ] the method implemented as new file in `solo/methods` and added to `solo/methods/__init__.py`
+* [ ] the loss implemented as new file in `solo/losses` and added to `solo/losses/__init__.py`
+* [ ] bash files to run experiments
+* [ ] tests for the method and the loss(es) in  `tests/methods` and `tests/losses`.
+* [ ] add documentation to `docs/source/solo/methods` and `docs/source/solo/losses`, and modify `docs/source/index.rst` to reference the new files (use alphabetical order).
+* [ ] check if all tests pass by running `python -m pytest --cov=solo tests`.
+* [ ] reproduce competitive results on at least CIFAR10/CIFAR100 (possibly Imagenet-100 and Imagenet).
+
diff --git a/.gitignore b/.gitignore
@@ -17,12 +17,27 @@ datasets/
 *.tar
 *.pkl
 
-*.png
-*.jpg
-*.jpeg
+bash_files/*.png
+bash_files/*.jpg
+bash_files/*.jpeg
+
+downstream/*.png
+downstream/*.jpg
+downstream/*.jpeg
+
+solo/*.png
+solo/*.jpg
+solo/*.jpeg
+
+tests/*.png
+tests/*.jpg
+tests/*.jpeg
+
+zoo/*.png
+zoo/*.jpg
+zoo/*.jpeg
 
 saved_models/
-model_storage/
 model_storage*/
 lightning_logs/
 
@@ -141,10 +156,10 @@ dmypy.json
 
 ### VisualStudioCode ###
 .vscode/*
-!.vscode/settings.json
-!.vscode/tasks.json
-!.vscode/launch.json
-!.vscode/extensions.json
+# !.vscode/settings.json
+# !.vscode/tasks.json
+# !.vscode/launch.json
+# !.vscode/extensions.json
 
 ### VisualStudioCode Patch ###
 # Ignore all local history of files

diff --git a/README.md b/README.md
@@ -15,6 +15,10 @@ While the library is self-contained, it is possible to use the models outside of
 ---
 
 ## News
+* **[Nov 29 2021]**: :bangbang: Breaking changes! Update your versions!!!
+* **[Nov 29 2021]**: :book: New tutorials!
+* **[Nov 29 2021]**: :rotating_light: Updated PyTorch and PyTorch Lightning versions. 10% faster.
+* **[Nov 29 2021]**: :beers: Added code of conduct, contribution instructions, issue templates and UMAP tutorial.
 * **[Nov 23 2021]**: :space_invader: Added [VIbCReg](https://arxiv.org/abs/2109.00783).
 * **[Oct 21 2021]**: :triumph: Added support for object recognition via Detectron v2 and auto resume functionally that automatically tries to resume an experiment that crashed/reached a timeout.
 * **[Oct 10 2021]**: :japanese_ogre: Restructured augmentation pipelines to allow more flexibility and multicrop. Also added multicrop for BYOL.
@@ -72,22 +76,30 @@ While the library is self-contained, it is possible to use the models outside of
 ## Requirements
 
 * torch
+* torchvision
 * tqdm
 * einops
 * wandb
 * pytorch-lightning
 * lightning-bolts
+* torchmetrics
+* scipy
+* timm
 
 **Optional**:
 * nvidia-dali
-
-**NOTE:** if you are using CUDA 10.X change `nvidia-dali-cuda110` to `nvidia-dali-cuda100` in `setup.py`, line 7.
+* matplotlib
+* seaborn
+* pandas
+* umap-learn
 
 ---
 
 ## Installation
 
-To install the repository with Dali and/or UMAP support, use:
+First clone the repo.
+
+Then, to install solo-learn with Dali and/or UMAP support, use:
 ```
 pip3 install .[dali,umap]
 ```
@@ -97,9 +109,11 @@ If no Dali/UMAP support is needed, the repository can be installed as:
 pip3 install .
 ```
 
-**NOTE:** If you want to modify the library, install it in dev mode with `-e`.
+**NOTE:** if you are having trouble with dali, install it with `pip install --extra-index-url https://developer.download.nvidia.com/compute/redist --upgrade nvidia-dali-cuda110` or with your specific cuda version.
+
+**NOTE 2:** If you want to modify the library, install it in dev mode with `-e`.
 
-**NOTE 2:** Soon to be on pip.
+**NOTE 3:** Soon to be on pip.
 
 ---
 
@@ -113,6 +127,25 @@ After that, for offline linear evaluation, follow the examples on `bash_files/li
 
 ---
 
+## Tutorials
+Please, check out our [documentation](https://solo-learn.readthedocs.io/en/latest) and tutorials:
+* [Overview](https://solo-learn.readthedocs.io/en/latest/tutorials/overview.html)
+* [Offline linear eval](https://solo-learn.readthedocs.io/en/latest/tutorials/offline_linear_eval.html)
+* [Object detection](https://github.com/vturrisi/solo-learn/blob/main/downstream/object_detection/README.md)
+* [Adding a new method](https://github.com/vturrisi/solo-learn/blob/main/docs/source/tutorials/add_new_method.rst)
+* [Adding a new momentum method](https://github.com/vturrisi/solo-learn/blob/main/docs/source/tutorials/add_new_method_momentum.rst)
+* [Visualizing features with UMAP](https://github.com/vturrisi/solo-learn/blob/main/docs/source/tutorials/umap.rst)
+* [Offline k-NN](https://github.com/vturrisi/solo-learn/blob/main/docs/source/tutorials/knn.rst)
+
+---
+
+## Model Zoo
+
+All pretrained models avaiable can be downloaded directly via the tables below or programmatically by running one of the following scripts
+`zoo/cifar10.sh`, `zoo/cifar100.sh`, `zoo/imagenet100.sh` and `zoo/imagenet.sh`.
+
+---
+
 ## Results
 
 **Note:** hyperparameters may not be the best, we will be re-running the methods with lower performance eventually.

diff --git a/bash_files/knn/imagenet-100/knn.sh b/bash_files/knn/imagenet-100/knn.sh
@@ -0,0 +1,12 @@
+python3 ../../../main_knn.py \
+    --dataset imagenet100 \
+    --data_dir /datasets \
+    --train_dir imagenet-100/train \
+    --val_dir imagenet-100/val \
+    --batch_size 16 \
+    --num_workers 10 \
+    --pretrained_checkpoint_dir PATH \
+    --k 1 2 5 10 20 50 100 200 \
+    --temperature 0.01 0.02 0.05 0.07 0.1 0.2 0.5 1 \
+    --feature_type backbone projector \
+    --distance_function euclidean cosine
diff --git a/bash_files/linear/imagenet-100/general_linear.sh b/bash_files/linear/imagenet-100/general_linear.sh
@@ -6,7 +6,7 @@ python3 ../../../main_linear.py \
     --val_dir imagenet-100/val \
     --max_epochs 100 \
     --gpus 0,1 \
-    --distributed_backend ddp \
+    --strategy ddp \
     --sync_batchnorm \
     --precision 16 \
     --optimizer sgd \

diff --git a/bash_files/linear/imagenet/byol.sh b/bash_files/linear/imagenet/byol.sh
@@ -6,7 +6,8 @@ python3 ../../../main_linear.py \
     --val_dir ILSVRC2012/val \
     --max_epochs 100 \
     --gpus 0 \
-    --accelerator ddp \
+    --accelerator gpu \
+    --strategy ddp \
     --sync_batchnorm \
     --precision 16 \
     --optimizer sgd \