Implement tf.layers.dot() for 4D (Dot Merge Layer)

[caisq]

The PyKeras code is at: https://github.com/keras-team/keras/blob/master/keras/layers/merge.py#L408

[HassanAzzam]

When will it be available?

[caisq]

Thanks, @HassanAzzam

Just for my curiosity: what model are you planning to write or port that requires Dot?

[HassanAzzam]

Currently, trying to practice it on a skip-gram model.

[caisq]

Thanks, @HassanAzzam . We'll prioritize adding Dot.

[HassanAzzam]

Thanks alot, @caisq😃

[euler16]

is anyone working on this issue? if not then I would like to try working on it. In that case @caisq could you give me some pointers to start.

[caisq]

@euler16 The just released v0.13.2 should have tf.layers.dot included. Please give it a try. Note that it currently doesn't support 4D or higher dimensions as inputs.

[caisq]

I'm leaving this issue open because the support for 4D+ cases is not implemented yet.

[gaikwadrahul8]

Hi, @caisq

Apologize for the delayed response and I was trying to use tensors of 4D or higher rank and I was getting this error message Dot layer does not support tensors of 4D or higher rank yet. so it seems like we haven't implemented this feature request yet. Thank you!

[gaikwadrahul8]

Hi, @caisq

Thank you for opening this issue for tracking purposes. Since this issue has been open for a long time, the code/debug information for this issue may not be relevant with the current state of the code base.

The TFJs team is constantly improving the framework by fixing bugs and adding new features. We suggest you try the latest TFJs version with the latest compatible hardware configuration which could potentially resolve the issue. We can keep the issue open if it is still relevant. Please confirm if we need to keep the issue open.

Thank you for your support and cooperation.

[gaikwadrahul8]

Hi, @caisq

We have not received any confirmation from you, so we are closing this issue now. If the issue is still relevant, please let us know, either we'll re-open this issue or please feel free to create new issue after trying with latest version of Tensorflow.js. Thank you!