stack expects each tensor to be equal size

stack expects each tensor to be equal size, but got [4, 72, 120] at entry 0 and [4, 80, 112] at entry 2

I keep on getting this regardless how I set up batch size, gradient accumulation etc.

It goes aways when I have very few images, but at my current 5K + images, it has been a few days and frustrating.

Please help.

I am using more recent commit.

The report names no source file, test, or entry point; begin by reproducing the training run with the reported tensor shapes and inspect where image tensors are batched. Done means identifying the cause of the unequal dimensions or documenting a confirmed fix with a repeatable case using the larger image set.

Written by the indexing model from the issue text.