{"html":"<iframe src=\"https://hatenablog-parts.com/embed?url=https%3A%2F%2Fhtn20190109.hatenablog.com%2Fentry%2F2025%2F10%2F19%2F002510\" title=\"AdaptiveAvgPool2d - HTN20190109\u306e\u65e5\u8a18\" class=\"embed-card embed-blogcard\" scrolling=\"no\" frameborder=\"0\" style=\"display: block; width: 100%; height: 190px; max-width: 500px; margin: 10px 0px;\"></iframe>","author_name":"HTN20190109","published":"2025-10-19 00:25:10","provider_name":"Hatena Blog","categories":["DL"],"blog_title":"HTN20190109\u306e\u65e5\u8a18","author_url":"https://blog.hatena.ne.jp/HTN20190109/","type":"rich","title":"AdaptiveAvgPool2d","blog_url":"https://htn20190109.hatenablog.com/","image_url":null,"description":"python3.11 import torchimport torch.nn as nn input = torch.Tensor([[[1,2,2,4], [5,3,1,7], [1,2,1,3], [1,5,2,1]]]) print(input)input = input.view(1,1,4,4)print(input) maxpool = nn.MaxPool2d(kernel_size = 2, stride = 2)output = maxpool(input)print(f'{input.shape} -> {output.shape}')print(output) maxpo\u2026","height":"190","url":"https://htn20190109.hatenablog.com/entry/2025/10/19/002510","version":"1.0","provider_url":"https://hatena.blog","width":"100%"}