Add PyTorch utility, implement PyTorch VAE and AutoEncoder

[RaymondY]

All Submissions Basics:

• Have you followed the guidelines in our Contributing document?
• Have you checked all Issues to tie the PR to a specific one?

All Submissions Cores:

• Have you added an explanation of what your changes do and why you'd like us to include them?
• Have you written new tests for your core changes, as applicable?
• Have you successfully ran tests with your changes locally?

New Model Submissions:

• Have you created a .py in ~/pyod/models/?
• Have you created a _example.py in ~/examples/?
• Have you created a test_.py in ~/pyod/test/?
• Have you lint your code locally prior to submission?

[coveralls]

Pull Request Test Coverage Report for Build 9139621159

Details

• 362 of 392 (92.35%) changed or added relevant lines in 5 files are covered.
• No unchanged relevant lines lost coverage.
• Overall coverage decreased (-0.08%) to 93.673%

---

Changes Missing Coverage	Covered Lines	Changed/Added Lines	%
pyod/test/test_vae_torch.py	99	100	99.0%
pyod/models/auto_encoder_torch.py	53	56	94.64%
pyod/models/vae_torch.py	144	149	96.64%
pyod/utils/torch_utility.py	59	80	73.75%

Totals
Change from base Build 8309419980:	-0.08%
Covered Lines:	9297
Relevant Lines:	9925

---

💛 - Coveralls

[yzhao062]

it appears that mac tests failed -- maybe take a look but I could also help!

[RaymondY]

torch_utility includes:

• class PyODDataset, custom PyTorch dataset
• class LinearBlock, includes linear layer, batch normalization, activation function, dropout layer, and linear layer weight init
• func get_activation_by_name, includes 7 common activation functions
• func init_weights, includes all weight initialization methods

Utility functions and classes are applied in VAE and AutoEncoder.

Note:

• Add torch.compile() to speed up (not used by default). Available for PyTorch version >=2.0.0 and Python version < 3.12.