Use PyTorch UAE utility class in imdb example

[ascillitoe]

Resolves #527 (comment).

For the PyTorch UAE model in the example, the output of

!pip install torchinfo
import torchinfo
torchinfo.summary(model.encoder.mlp, input_size=(5,768))

is now:

==========================================================================================
Layer (type:depth-idx)                   Output Shape              Param #
==========================================================================================
Sequential                               [5, 32]                   --
├─Flatten: 1-1                           [5, 768]                  --
├─Linear: 1-2                            [5, 522]                  401,418
├─ReLU: 1-3                              [5, 522]                  --
├─Linear: 1-4                            [5, 277]                  144,871
├─ReLU: 1-5                              [5, 277]                  --
├─Linear: 1-6                            [5, 32]                   8,896
==========================================================================================
Total params: 555,185
Trainable params: 555,185
Non-trainable params: 0
Total mult-adds (M): 2.78
==========================================================================================
Input size (MB): 0.02
Forward/backward pass size (MB): 0.03
Params size (MB): 2.22
Estimated Total Size (MB): 2.27
==========================================================================================

This matches the Tensorflow UAE model:

uae.encoder.layers[1].summary()

gives:

Model: "sequential_1"
_________________________________________________________________
 Layer (type)                Output Shape              Param #   
=================================================================
 flatten_1 (Flatten)         (5, 768)                  0         
                                                                 
 dense_3 (Dense)             (5, 522)                  401418    
                                                                 
 dense_4 (Dense)             (5, 277)                  144871    
                                                                 
 dense_5 (Dense)             (5, 32)                   8896      
                                                                 
=================================================================
Total params: 555,185
Trainable params: 555,185
Non-trainable params: 0      

[review-notebook-app]

Check out this pull request on 

See visual diffs & provide feedback on Jupyter Notebooks.

---

Powered by ReviewNB

[codecov-commenter]

Codecov Report

Merging #705 (89571db) into master (3daf62c) will decrease coverage by 0.12%.
The diff coverage is n/a.

Additional details and impacted files

@@            Coverage Diff             @@
##           master     #705      +/-   ##
==========================================
- Coverage   80.15%   80.03%   -0.13%     
==========================================
  Files         133      133              
  Lines        9177     9136      -41     
==========================================
- Hits         7356     7312      -44     
- Misses       1821     1824       +3     

Flag	Coverage Δ
macos-latest-3.10	?
ubuntu-latest-3.10	?
ubuntu-latest-3.7	79.87% <ø> (ø)
ubuntu-latest-3.8	?
windows-latest-3.9	76.58% <ø> (ø)

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

Impacted Files	Coverage Δ
alibi_detect/utils/keops/kernels.py	94.05% <0.00%> (-3.97%)	⬇️
alibi_detect/saving/validators.py	86.53% <0.00%> (-3.85%)	⬇️
alibi_detect/utils/missing_optional_dependency.py	94.28% <0.00%> (-0.16%)	⬇️
alibi_detect/datasets.py	68.55% <0.00%> (-0.14%)	⬇️
alibi_detect/saving/schemas.py	98.69% <0.00%> (-0.09%)	⬇️
alibi_detect/utils/fetching/fetching.py	0.00% <0.00%> (ø)
alibi_detect/cd/base.py	91.19% <0.00%> (+0.21%)	⬆️
alibi_detect/od/vae.py	90.36% <0.00%> (+1.07%)	⬆️

[mauicv]

LGTM!