Keras 2.1.x incompatibilty

描述

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)
...

贡献者指南

技术栈

python

领域

machine learningai

议题类型

bug

难度面向新贡献者的预计实现难度，1 表示很小改动，5 表示专家级工作。

3

预计时间有经验贡献者完成调查、实现、测试并准备 pull request 的粗略时间范围。

1-3 hours

活动状态议题当前的可参与程度：新鲜、活跃、陈旧、阻塞或等待维护者输入。

stale

清晰度议题是否清楚说明期望改动、验收标准和下一步。

clear

前置要求

Python programmingKeras basicsNeural network shape concepts

新手友好度1-100 的估计分数，表示该议题对首次贡献者的友好程度。

40

研究方向

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.