Skip to content

Infos from Batch-size dimension will be mixed together into Core multiplications. #10

@LouiValley

Description

@LouiValley

In your implementaion , like tt.py: line 61 out = tf.reshape(out, [mat_ranks[i] * inp_modes[i], -1]).
It seems the different Infos from different batch_size dimensions will be mixed with others. Could it be OK?
Since usually different infos from different batch_size dimensions will be processed seperately.

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions