ageron/handson-mlp

[bug] The final shape after a tensor [2, 32, 70, 120] is going through the depthwise max pooling is incorrect

开放

#40 创建于 2026年5月23日

 (0 条评论) (0 个反应) (1 位负责人)Jupyter Notebook (592 个派生)github user discovery
bughelp wanted

仓库指标

星标
 (1,827 个星标)
PR 合并指标
 (30 天内没有已合并 PR)

描述

Enter the chapter number

Chapter 12 Deep Computer Vision using CNNs

Enter the page number

Page 433

What is the cell's number in the notebook

Line 11 or the last bullet point

Enter the environment you are using to run the notebook

None

Describe your issue

The final shape after a tensor [2, 32, 70, 120] is going through the depthwise max pooling is not [2,8,50,100].

Enter what you expected to happen

The final tensor should be [2,8,70,120], not [2,8,50,100]

If you found a workaround, describe it here

The final tensor should be [2,8,70,120]

贡献者指南