model split
2020.07.30 08:15
https://forums.fast.ai/t/pytorch-best-way-to-get-at-intermediate-layers-in-vgg-and-resnet/5707/2
class ResNet50Bottom(nn.Module): def __init__(self, original_model): super(ResNet50Bottom, self).__init__() self.features = nn.Sequential(*list(original_model.children())[:-2]) def forward(self, x): x = self.features(x) return x res50_model = models.resnet50(pretrained=True) res50_conv2 = ResNet50Bottom(res50_model) outputs = res50_conv2(inputs) outputs.data.shape # => torch.Size([4, 2048, 7, 7])
번호 | 제목 | 글쓴이 | 날짜 | 조회 수 |
---|---|---|---|---|
1819 | mAP 계산법 | WHRIA | 2019.02.24 | 45576 |
1818 | epitope spreading | han | 2006.05.09 | 41032 |
1817 | encfs | WHRIA | 2020.05.17 | 36012 |
1816 | Heinrich Law (1:29:300 Law) | WHRIA | 2007.08.12 | 25001 |
1815 | 일본 주소 [2] | WHRIA | 2008.06.28 | 24031 |
1814 |
사주팔자 프로그램
![]() | 한승석 | 2003.02.16 | 20336 |
1813 |
simple adblock
![]() | WHRIA | 2012.04.13 | 18118 |
1812 | 도란사민 | WHRIA | 2011.04.19 | 18104 |
1811 |
탤런트 이윤지씨와 함께
![]() | WHRIA | 2010.02.04 | 17047 |
1810 | penicillin | han | 2003.12.10 | 15717 |
1809 | SSH tunnel | WHRIA | 2007.10.01 | 15088 |
1808 | geexbox [1] | han | 2006.12.01 | 14611 |
1807 | 아이피부과 개원 | WHRIA | 2010.01.18 | 14442 |
1806 | 세무회계 | WHRIA | 2010.01.31 | 14404 |
1805 | 증명사진 | WHRIA | 2010.03.14 | 14337 |
https://discuss.pytorch.org/t/how-to-extract-features-of-an-image-from-a-trained-model/119/3