Update AE and VAE documentation

[jeremyadamsfisher]

What does this PR do?

Previously, pretrained models were initialized with a static method. Now, they are initialized with an instance method. Upate docstring accordingly.

Fixes #543

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?
• Did you make sure to update the documentation with your changes?
• Did you write any new necessary tests? [not needed for typos/docs]
• Did you verify new and existing tests pass locally with your changes?

On the master and on this branch, I have the following test failures:

FAILED tests/models/test_scripts.py::test_cli_run_cpc[ --data_dir /home/j/Documents/pytorch-lightning-bolts/datasets --max_epochs 1 --limit_train_batches 2 --limit_val_batches 2 --batch_size 2 --encoder resnet18]
FAILED tests/models/self_supervised/test_models.py::test_byol - ValueError: not enough values to unpack (expected 3, got 2)
FAILED tests/models/self_supervised/test_scripts.py::test_cli_run_self_supervised_cpc[ --data_dir /home/j/Documents/pytorch-lightning-bolts/datasets --max_epochs 1 --max_steps 3 --fast_dev_run 1 --batch_size 2 --encoder resnet18 --num_workers 0]

They seem unrelated to this issue

• 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?

🚀🚀🚀

[codecov]

Codecov Report

Merging #557 (0c5981e) into master (86e3f52) will decrease coverage by 51.35%.
The diff coverage is n/a.

@@             Coverage Diff             @@
##           master     #557       +/-   ##
===========================================
- Coverage   77.58%   26.23%   -51.36%     
===========================================
  Files         115      115               
  Lines        6701     6675       -26     
===========================================
- Hits         5199     1751     -3448     
- Misses       1502     4924     +3422     

Flag	Coverage Δ
cpu	26.23% <ø> (ø)
pytest	26.23% <ø> (ø)
unittests	?

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

Impacted Files	Coverage Δ
...ts/models/autoencoders/basic_ae/basic_ae_module.py	26.66% <ø> (-61.50%)	⬇️
.../models/autoencoders/basic_vae/basic_vae_module.py	22.91% <ø> (-68.84%)	⬇️
pl_bolts/models/rl/__init__.py	0.00% <0.00%> (-100.00%)	⬇️
pl_bolts/models/rl/common/agents.py	0.00% <0.00%> (-100.00%)	⬇️
pl_bolts/models/rl/dueling_dqn_model.py	0.00% <0.00%> (-100.00%)	⬇️
pl_bolts/models/rl/double_dqn_model.py	0.00% <0.00%> (-95.66%)	⬇️
...l_bolts/models/rl/vanilla_policy_gradient_model.py	0.00% <0.00%> (-95.50%)	⬇️
pl_bolts/models/rl/common/networks.py	0.00% <0.00%> (-89.25%)	⬇️
pl_bolts/models/rl/reinforce_model.py	0.00% <0.00%> (-88.62%)	⬇️
pl_bolts/models/rl/per_dqn_model.py	0.00% <0.00%> (-86.67%)	⬇️
... and 65 more

---

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 86e3f52...2400a7c. Read the comment docs.

[akihironitta]

@jeremyadamsfisher Thank you for your contribution! LGTM!

[akihironitta]

@jeremyadamsfisher Would you mind fixing other places, too?
https://github.com/PyTorchLightning/pytorch-lightning-bolts/blob/c5b3c04c97239019e2a782189917276a43587be8/pl_bolts/models/autoencoders/basic_ae/basic_ae_module.py#L30

[jeremyadamsfisher]

@jeremyadamsfisher Would you mind fixing other places, too?

https://github.com/PyTorchLightning/pytorch-lightning-bolts/blob/c5b3c04c97239019e2a782189917276a43587be8/pl_bolts/models/autoencoders/basic_ae/basic_ae_module.py#L30

Done.

Other parts of the code don't have this issue because they don't have the API suggested in issue #200 . Here's where I've looked

• SimCLR (SimCLR.load_from_checkpoint(weight_path, strict=False))
• CPCV2 (CPCV2.load_from_checkpoint(weight_path, strict=False) or CPCV2(pretrained=True))
• SwAV (SwAV.load_from_checkpoint(weight_path, strict=True))

[akihironitta]

@jeremyadamsfisher Thank you for your swift action!