Decouple DataModules from Models - CPCV2 #386

akihironitta · 2020-11-20T02:49:17Z

What does this PR do?

Partial fix of #207.

Before submitting

Was this discussed/approved via a Github issue? (no need for typos and docs improvements)
Did you read the contributor guideline, Pull Request section?
Did you make sure your PR does only one thing, instead of bundling different changes together? Otherwise, we ask you to create a separate PR for every change.
Did you make sure to update the documentation with your changes?
Did you write any new necessary tests?
Did you verify new and existing tests pass locally with your changes?
If you made a notable change (that affects users), did you update the CHANGELOG?

PR review

Is this pull request ready for review? (if not, please submit in draft mode)

Anyone in the community is free to review the PR once the tests have passed.
If we didn't discuss your PR in Github issues there's a high chance it will not be merged.

Did you have fun?

Make sure you had fun coding 🙃

codecov · 2020-11-20T02:50:45Z

Codecov Report

Merging #386 (f671de1) into master (70833f0) will decrease coverage by 0.84%.
The diff coverage is 0.00%.

@@            Coverage Diff             @@
##           master     #386      +/-   ##
==========================================
- Coverage   82.03%   81.18%   -0.85%     
==========================================
  Files         100      100              
  Lines        5639     5714      +75     
==========================================
+ Hits         4626     4639      +13     
- Misses       1013     1075      +62

Flag	Coverage Δ
cpu	`24.27% <0.00%> (-0.28%)`	⬇️
pytest	`24.27% <0.00%> (-0.28%)`	⬇️
unittests	`80.46% <0.00%> (-0.83%)`	⬇️

Flags with carried forward coverage won't be shown. Click here to find out more.

Impacted Files	Coverage Δ
pl_bolts/models/self_supervised/cpc/cpc_module.py	`20.31% <0.00%> (ø)`
..._bolts/models/self_supervised/simclr/transforms.py	`80.88% <0.00%> (-19.12%)`	⬇️
...lts/models/self_supervised/simclr/simclr_module.py	`71.49% <0.00%> (-11.32%)`	⬇️
pl_bolts/losses/self_supervised_learning.py	`71.33% <0.00%> (-6.37%)`	⬇️
pl_bolts/datasets/base_dataset.py	`95.45% <0.00%> (-4.55%)`	⬇️
...l_bolts/models/self_supervised/byol/byol_module.py	`83.90% <0.00%> (-1.04%)`	⬇️
pl_bolts/models/self_supervised/resnets.py	`92.04% <0.00%> (-0.74%)`	⬇️
pl_bolts/models/self_supervised/byol/models.py	`100.00% <0.00%> (ø)`
.../models/self_supervised/simclr/simclr_finetuner.py	`100.00% <0.00%> (ø)`

Continue to review full report at Codecov.

Legend - Click here to learn more
Δ = absolute <relative> (impact), ø = not affected, ? = missing data
Powered by Codecov. Last update 70833f0...f671de1. Read the comment docs.

akihironitta · 2020-11-20T02:59:02Z

pl_bolts/models/self_supervised/cpc/cpc_module.py

        self.encoder = self.init_encoder()

        # info nce loss
        c, h = self.__compute_final_nb_c(self.hparams.patch_size)
        self.contrastive_task = CPCTask(num_input_channels=c, target_dim=64, embed_scale=0.1)

        self.z_dim = c * h * h
-        self.num_classes = self.datamodule.num_classes
+        self.num_classes = num_classes


Since self.num_classes was already defined, I'm leaving it as is, but is this variable really necessary? As far as I understand the paper, it uses only images without any labels...

Is this variable self.num_classes useful/necessary for downstream tasks...?

Borda

lgtm cc: @ananyahjha93

* Decouple dms from CPCV2 * Update tests

@akihironitta

* Add DCGAN module * Undo black on conf.py * Add tests for DCGAN * Fix flake8 and codefactor * Add types and small refactoring * Make image sampler callback work * Upgrade DQN to use .log (#404) * Upgrade DQN to use .log * remove unused * pep8 * fixed other dqn * fix loss test case for batch size variation (#402) * Decouple DataModules from Models - CPCV2 (#386) * Decouple dms from CPCV2 * Update tests * Add docstrings, fix import, and update changelog * Update transforms * bugfix: batch_size parameter for DataModules remaining (#344) * bugfix: batch_size for DataModules remaining * Update sklearn datamodule tests * Fix default_transforms. Keep internal for every data module * fix typo on binary_mnist_datamodule thanks @akihironitta Co-authored-by: Akihiro Nitta <nitta@akihironitta.com> Co-authored-by: Akihiro Nitta <nitta@akihironitta.com> * Fix a typo/copy paste error (#415) * Just a Typo (#413) missing a ' at the end of dataset='stl10 * Remove unused arguments (#418) * tests: Use cached datasets in LitMNIST and the doctests (#414) * Use cached datasets * Use cached datasets in doctests * clear replay buffer after trajectory (#425) * stale: update label * bugfix: Add missing imports to pl_bolts/__init__.py (#430) * Add missing imports * Add missing imports * Apply isort * Fix CIFAR num_samples (#432) * Add static type checker mypy to the tests and pre-commit hooks (#433) * Add mypy check to GitHub Actions * Run mypy on pl_bolts only * Add mypy check to pre-commit * Add an empty line at the end of files * Update mypy config * Update mypy config * Update mypy config * show Co-authored-by: Jirka Borovec <Borda@users.noreply.github.com> * missing logo * Add type annotations to pl_bolts/__init__.py (#435) * Run mypy on pl_bolts only * Update mypy config * Add type hints to pl_bolts/__init__.py * mypy Co-authored-by: Jirka Borovec <jirka.borovec@seznam.cz> * skip hanging (#437) * Option to normalize latent interpolation images (#438) * add option to normalize latent interpolation images * linspace * update Co-authored-by: ananyahjha93 <ananya@pytorchlightning.ai> * 0.2.6rc1 * Warnings fix (#449) * Revert "Merge pull request #1 from ganprad/warnings_fix" This reverts commit 7c5aaf0. * Fixes warning related np.integer in SklearnDataModule Fixes this warning: ```DeprecationWarning: Converting `np.integer` or `np.signedinteger` to a dtype is deprecated. The current result is `np.dtype(np.int_)` which is not strictly correct. Note that the result depends on the system. To ensure stable results use may want to use `np.int64` or `np.int32```` * Refactor datamodules/datasets (#338) * Remove try: ... except: ... * Fix experience_source * Fix imagenet * Fix kitti * Fix sklearn * Fix vocdetection * Fix typo * Remove duplicate * Fix by flake8 * Add optional packages availability vars * binary_mnist * Use pl_bolts._SKLEARN_AVAILABLE * Apply isort * cifar10 * mnist * cityscapes * fashion mnist * ssl_imagenet * stl10 * cifar10 * dummy * fix city * fix stl10 * fix mnist * ssl_amdim * remove unused DataLoader and fix docs * use from ... import ... * fix pragma: no cover * Fix forward reference in annotations * binmnist * Same order as imports * Move vars from __init__ to utils/__init__ * Remove vars from __init__ * Update vars * Apply isort * update min requirements - PL 1.1.1 (#448) * update min requirements * rc0 * imports * isort * flake8 * 1.1.1 * flake8 * docs * Add missing optional packages to `requirements/*.txt` (#450) * Import matplotlib at the top * Add missing optional packages * Update wandb * Add mypy to requirements * update Isort (#457) * Adding flags to datamodules (#388) * Adding flags to datamodules * Finishing up changes * Fixing syntax error * More syntax errors * More * Adding drop_last flag to sklearn test * Adding drop_last flag to sklearn test * Updating doc for reflect drop_last=False * Adding flags to datamodules * Finishing up changes * Fixing syntax error * More syntax errors * More * Adding drop_last flag to sklearn test * Adding drop_last flag to sklearn test * Updating doc for reflect drop_last=False * Cleaning up parameters and docstring * Fixing syntax error * Fixing documentation * Hardcoding shuffle=False for val and test * Add DCGAN module * Small fixes * Remove DataModules * Update docs * Update docs * Update torchvision import * Import gym as optional package to build docs successfully (#458) * Import gym as optional package * Fix import * Apply isort * bugfix: batch_size parameter for DataModules remaining (#344) * bugfix: batch_size for DataModules remaining * Update sklearn datamodule tests * Fix default_transforms. Keep internal for every data module * fix typo on binary_mnist_datamodule thanks @akihironitta Co-authored-by: Akihiro Nitta <nitta@akihironitta.com> Co-authored-by: Akihiro Nitta <nitta@akihironitta.com> * Option to normalize latent interpolation images (#438) * add option to normalize latent interpolation images * linspace * update Co-authored-by: ananyahjha93 <ananya@pytorchlightning.ai> * update min requirements - PL 1.1.1 (#448) * update min requirements * rc0 * imports * isort * flake8 * 1.1.1 * flake8 * docs * Apply suggestions from code review * Apply suggestions from code review * Add docs * Use LSUN instead of CIFAR10 * Update TensorboardGenerativeModelImageSampler * Update docs with lsun * Update test * Revert TensorboardGenerativeModelImageSampler changes * Remove ModelCheckpoint callback and nrow=5 arg * Apply suggestions from code review * Fix test_dcgan * Apply yapf * Apply suggestions from code review Co-authored-by: Teddy Koker <teddy.koker@gmail.com> Co-authored-by: Sidhant Sundrani <sidhant96@outlook.com> Co-authored-by: Akihiro Nitta <nitta@akihironitta.com> Co-authored-by: Héctor Laria <hector_laria@hotmail.com> Co-authored-by: Bartol Karuza <bartol.k@gmail.com> Co-authored-by: Happy Sugar Life <777Jonathansum@gmail.com> Co-authored-by: Jirka Borovec <Borda@users.noreply.github.com> Co-authored-by: Jirka Borovec <jirka.borovec@seznam.cz> Co-authored-by: ananyahjha93 <ananya@pytorchlightning.ai> Co-authored-by: Pradeep Ganesan <ganprad@users.noreply.github.com> Co-authored-by: Brian Ko <briankosw@gmail.com> Co-authored-by: Christoph Clement <christoph.clement@artorg.unibe.ch>

akihironitta added 2 commits November 20, 2020 11:45

Decouple dms from CPCV2

2f0e3a6

Update tests

f671de1

akihironitta commented Nov 20, 2020

View reviewed changes

Borda added this to In progress in Self Supervised Learning Nov 20, 2020

Borda added model refactoring labels Nov 22, 2020

Borda approved these changes Nov 22, 2020

View reviewed changes

Borda merged commit 2e903c3 into Lightning-Universe:master Nov 26, 2020

Self Supervised Learning automation moved this from In progress to Done Nov 26, 2020

chris-clem pushed a commit to chris-clem/pytorch-lightning-bolts that referenced this pull request Nov 27, 2020

Decouple DataModules from Models - CPCV2 (Lightning-Universe#386)

ac56e5a

* Decouple dms from CPCV2 * Update tests

akihironitta mentioned this pull request Dec 1, 2020

Decouple DataModules from Models #207

Closed

chris-clem pushed a commit to chris-clem/pytorch-lightning-bolts that referenced this pull request Dec 9, 2020

Decouple DataModules from Models - CPCV2 (Lightning-Universe#386)

9a18028

* Decouple dms from CPCV2 * Update tests

Borda added this to the v0.3 milestone Jan 18, 2021

This was referenced Mar 13, 2021

[tune](deps): Bump pytorch-lightning-bolts from 0.2.5 to 0.3.0 in /python/requirements suquark/ray#8

Closed

[tune](deps): Bump pytorch-lightning-bolts from 0.2.5 to 0.3.0 in /python/requirements sven1977/ray#8

Closed

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Decouple DataModules from Models - CPCV2 #386

Decouple DataModules from Models - CPCV2 #386

akihironitta commented Nov 20, 2020 •

edited by Borda

codecov bot commented Nov 20, 2020 •

edited

akihironitta Nov 20, 2020

akihironitta Nov 23, 2020

Borda left a comment

Decouple DataModules from Models - CPCV2 #386

Decouple DataModules from Models - CPCV2 #386

Conversation

akihironitta commented Nov 20, 2020 • edited by Borda

What does this PR do?

Before submitting

PR review

Did you have fun?

codecov bot commented Nov 20, 2020 • edited

Codecov Report

akihironitta Nov 20, 2020

Choose a reason for hiding this comment

akihironitta Nov 23, 2020

Choose a reason for hiding this comment

Borda left a comment

Choose a reason for hiding this comment

akihironitta commented Nov 20, 2020 •

edited by Borda

codecov bot commented Nov 20, 2020 •

edited