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 |
---|---|---|---|---|
1566 | fast rcnn cudnn 5.0 | WHRIA | 2017.01.08 | 128 |
1565 | 역시 개원해서는 돈 버는 재미밖에 없다. | WHRIA | 2016.06.17 | 129 |
1564 | 나이 40에... | WHRIA | 2018.09.01 | 130 |
1563 | Google vs Microsoft: The good, bad, and ugly of the AI arms race | WHRIA | 2023.02.14 | 132 |
1562 | CORS | WHRIA | 2021.01.22 | 133 |
1561 | startup , 미국 | WHRIA | 2020.07.30 | 134 |
1560 | 모든 code 를 python3 로 migration 중 | WHRIA | 2019.06.08 | 138 |
1559 | kakao | WHRIA | 2018.02.25 | 139 |
1558 | 이궁 | WHRIA | 2019.03.12 | 139 |
1557 | Micro- and macro-averages | WHRIA | 2019.11.28 | 140 |
» | model split [1] | WHRIA | 2020.07.30 | 142 |
1555 | pROC package [3] | WHRIA | 2019.05.11 | 143 |
1554 | SAS controller SAS 9212-4i | WHRIA | 2019.12.08 | 143 |
1553 | 페이닥터 등록 | WHRIA | 2014.10.21 | 145 |
1552 | delayed network drive connect | WHRIA | 2018.10.07 | 145 |
https://discuss.pytorch.org/t/how-to-extract-features-of-an-image-from-a-trained-model/119/3