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 |
---|---|---|---|---|
154 | imagenet classification SOTA | WHRIA | 2020.06.27 | 1427 |
153 | tab 구조 html | WHRIA | 2020.06.28 | 82 |
152 | modprobe | WHRIA | 2020.06.29 | 6440 |
151 | sql python | WHRIA | 2020.07.01 | 200 |
150 | naver rexnet clova AI [1] | WHRIA | 2020.07.04 | 268 |
149 | git 특정 버젼 | WHRIA | 2020.07.11 | 53 |
148 | amp distributed pytorch [1] | WHRIA | 2020.07.14 | 61 |
147 | asyncio | WHRIA | 2020.07.23 | 309 |
146 | raid 6 | WHRIA | 2020.07.23 | 53 |
145 | 암호화 | WHRIA | 2020.07.26 | 1018 |
144 | FTC [1] | WHRIA | 2020.07.28 | 243 |
» | model split [1] | WHRIA | 2020.07.30 | 149 |
142 | consort , stard | WHRIA | 2020.07.30 | 92 |
141 | startup , 미국 | WHRIA | 2020.07.30 | 154 |
140 | pytorch optimize | WHRIA | 2020.08.01 | 160 |
https://discuss.pytorch.org/t/how-to-extract-features-of-an-image-from-a-trained-model/119/3