Keras 2.1.x incompatibilty

Description

Starting training
Epoch 1/3000
Exception: Error when checking target: expected rpn_out_class to have shape (None, None, None, 9) but got array with shape (1, 56, 38, 18)
Exception: Error when checking target: expected rpn_out_class to have shape (None, None, None, 9) but got array with shape (1, 50, 38, 18)
Exception: Error when checking target: expected rpn_out_class to have shape (None, None, None, 9) but got array with shape (1, 43, 38, 18)
Exception: Error when checking target: expected rpn_out_class to have shape (None, None, None, 9) but got array with shape (1, 38, 38, 18)
...

Contributor guide

Tech stack

python

Domain

machine learningai

Issue type

bug

DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.

3

Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.

1-3 hours

Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.

stale

ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.

clear

Prerequisites

Python programmingKeras basicsNeural network shape concepts

Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.

40

Research direction

Investigate the model definition for rpn out class, likely in the main model file (e.g., model.py). The error suggests the expected shape is (None, None, None, 9) but received different shapes. Check Keras version 2.1.x changes in Conv2D or Reshape layers. The issue has 4 comments; review them for any identified root cause. Test with a simple fix like adjusting the output number of filters or using a different layer configuration.