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 |
---|---|---|---|---|
51 | imagenet classification SOTA | WHRIA | 2020.06.27 | 1398 |
50 | tab 구조 html | WHRIA | 2020.06.28 | 79 |
49 | modprobe | WHRIA | 2020.06.29 | 6432 |
48 | sql python | WHRIA | 2020.07.01 | 180 |
47 | naver rexnet clova AI [1] | WHRIA | 2020.07.04 | 229 |
46 | git 특정 버젼 | WHRIA | 2020.07.11 | 34 |
45 | amp distributed pytorch [1] | WHRIA | 2020.07.14 | 51 |
44 | asyncio | WHRIA | 2020.07.23 | 286 |
43 | raid 6 | WHRIA | 2020.07.23 | 43 |
42 | 암호화 | WHRIA | 2020.07.26 | 1000 |
41 | FTC [1] | WHRIA | 2020.07.28 | 238 |
» | model split [1] | WHRIA | 2020.07.30 | 142 |
39 | consort , stard | WHRIA | 2020.07.30 | 81 |
38 | startup , 미국 | WHRIA | 2020.07.30 | 134 |
37 | pytorch optimize | WHRIA | 2020.08.01 | 126 |
https://discuss.pytorch.org/t/how-to-extract-features-of-an-image-from-a-trained-model/119/3