Ashley Scillitoe

Hi @gunja8 I've double-checked this and it looks like there is a minor issue here as you said. I've run some tests on `cd_spot_the_diff_mnist_wine.ipynb` example notebook, and tried to set...

Hi @francoispichard, thank you for the very nicely stated issue! I agree with you, the PyTorch and TensorFlow dimension reduction steps are functionally similar, but they are not identical. `print(uae.encoder.layers[1].summary())`...

> At the very least we should reword the notebook to make that clearer, but as you hinted, really **we should add a `UAE` class for PyTorch**. PR https://github.com/SeldonIO/alibi-detect/pull/656 will...

Coming back to this. The only issue with skipping the test when a URL is down is that CI won't pick up cases where URL's are permanently dead or changed....

Reopening this since we missed a utility function in `alibi_detect.datasets`; the `corruption_types_cifar10c` function causes a CI failure if `https://storage.googleapis.com/seldon-datasets` is down (see https://github.com/SeldonIO/alibi-detect/runs/6662544833). We should add the `try-except` logic added...

We should also review the intention behind the `data_type` kwarg, and whether it is even needed.

Hi @KevinRyu, that is strange. I would have thought that 10GB of memory would be enough for this example, and as you point out, it is with `backend='tensorflow'`. Do you...

Thanks for looking into this @KevinRyu! I've just tried to reproduce on our end by simply taking the `cd_mmd_cifar10.ipynb` notebook and running it on a GPU in Google colab, with...

p.s. @KevinRyu locally we currently use RTX 5000's and 2080Ti's. Notwithstanding the issue you've discovered, your GPU should be enough for most of the Alibi Detect examples. If you do...

Hi @KevinRyu, just opening this again to ensure we don't miss the above.