Inconsistency in conv+bn fusion and addition of useless reshapes in tf2onnx==1.16.1

[riccardoalberghi]

Describe the bug
When I convert a u-net architecture a Conv operator and a BN operator are not fused together and 2 Reshape operators are added which reshape to the same shape [-1, 512, 1, 1].

Urgency
none

System information

• OS Platform and Distribution: macos 14.2.1 arm64
• TensorFlow Version: 2.13.1
• Python version: 3.10.13
• ONNX version: 1.15
• ONNXRuntime version: 1.16
• tf2onnx version: 1.16.1 (from github)

To Reproduce
https://drive.google.com/file/d/1xzaAXWxUqXUTBVgDSiyrbjs_TSHXuhwW

by running python -m tf2onnx.convert --saved-model bg_model --output bg_model.onnx

Screenshots
from the top the first conv+bn is fused correctly, then the following is not.

Additional context
Every other conv+bn is fused correctly except one.

[riccardoalberghi]

I conducted a little more testing.
Downgrading to onnx==1.14 and tf2onnx==1.15.1/37820d solves the issue. With tf2onnx==1.16.0 the issue reappears, I dont know if this helps for identifying the problem.

[riccardoalberghi]

@fatcat-z any news?

[fatcat-z]

This is a regression bug brought by PR #2272 . @Rikyf3 , could you please share a code snippet of this module so I can prepare a test to cover it?