Shun Lin

Thanks for the pointers @DavidMChan will look into it!

Hi @LucaCappelletti94 , nothing yet, didn't get too much time to be able to dig deeper.

yay thanks @DavidMChan :) :) Very excited!

@DavidMChan for my use case my dimensions is roughly [128, 1M] (128 dimension, ~ million of examples), would `tfjs-tsne` perform better in this case? And I agree with @LucaCappelletti94 that...

Looks like TPU is supported as KerasTuner now supports TPU, here is an example: https://colab.research.google.com/drive/1AaFDTQaq8B5p3-FKtNDdMdhlmUHtwOIM?authuser=1#scrollTo=HUJ0LxZnbQnc and it's quite simple actually with only 2 lines of code: ``` resolver = tf.distribute.cluster_resolver.TPUClusterResolver(tpu=tpu_address)...

Thanks for finding this useful! In regards to loss stuck at margin, this is (almost) the equivalent of loss returning `NaN` for classification/regress problem as the loss for Triplet Loss...

You made a good point, the implementation of `EmbeddingHead` is very similar to `ClassificationHead`, is it possible for you to share a notebook where the error w/ `EmbeddingHead` occurs? Also...

Hi, it looks like the EmbeddingHead is callable (see screenshot below), does the EmbeddingHead in your implementation inherits from `head_module.Head`? This class has `__call__` implemented so should be callable. Sorry...

Hi, I think the above example notebook for Autokeras + Deep Metrics Learning has the example with cifar10 and it has tangible loss `0.4605` with only 2 epochs, may you...

and also @sidphbot about how many classes is your dataset? If you are not generating triplets from the input (instead of relying on the default sampling) you may want larger...