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 |
---|---|---|---|---|
1669 | melanoma awareness [1] | WHRIA | 2019.12.27 | 45 |
1668 | CIDR 표기법 [1] | WHRIA | 2020.03.12 | 45 |
1667 | mysql 암호화 [2] | WHRIA | 2020.04.24 | 45 |
1666 | annotation service | WHRIA | 2020.05.03 | 45 |
1665 | 식약청 메뉴 | WHRIA | 2020.05.14 | 45 |
1664 | linux raid | WHRIA | 2019.11.30 | 46 |
1663 | nvidia caffe | WHRIA | 2020.01.12 | 46 |
1662 | sql 중복제거 | WHRIA | 2020.02.10 | 46 |
1661 | DDR-WRT IPTV | WHRIA | 2016.06.15 | 47 |
1660 | test | WHRIA | 2020.12.03 | 47 |
1659 | insync | WHRIA | 2023.02.09 | 47 |
1658 | lvm 확장 [1] | WHRIA | 2019.12.25 | 48 |
1657 | disk error | WHRIA | 2023.02.16 | 48 |
1656 | rsynccp | WHRIA | 2023.02.20 | 49 |
1655 | color pallate | WHRIA | 2019.04.07 | 50 |
https://discuss.pytorch.org/t/how-to-extract-features-of-an-image-from-a-trained-model/119/3