concat network
2020.08.27 00:19
https://discuss.pytorch.org/t/concatenate-layer-output-with-additional-input-data/20462
댓글 3
-
WHRIA
2020.09.05 11:08
-
WHRIA
2020.09.05 11:17
class MyModelA(nn.Module): def __init__(self): super(MyModelA, self).__init__() self.fc1 = nn.Linear(10, 2) def forward(self, x): x = self.fc1(x) return x class MyModelB(nn.Module): def __init__(self): super(MyModelB, self).__init__() self.fc1 = nn.Linear(20, 2) def forward(self, x): x = self.fc1(x) return x class MyEnsemble(nn.Module): def __init__(self, modelA, modelB): super(MyEnsemble, self).__init__() self.modelA = modelA self.modelB = modelB self.classifier = nn.Linear(4, 2) def forward(self, x1, x2): x1 = self.modelA(x1) x2 = self.modelB(x2) x = torch.cat((x1, x2), dim=1) x = self.classifier(F.relu(x)) return x # Create models and load state_dicts modelA = MyModelA() modelB = MyModelB() # Load state dicts modelA.load_state_dict(torch.load(PATH)) modelB.load_state_dict(torch.load(PATH)) model = MyEnsemble(modelA, modelB) x1, x2 = torch.randn(1, 10), torch.randn(1, 20) output = model(x1, x2)
-
WHRIA
2020.10.08 13:08
https://gist.github.com/andrewjong/6b02ff237533b3b2c554701fb53d5c4d
번호 | 제목 | 글쓴이 | 날짜 | 조회 수 |
---|---|---|---|---|
139 | raid 6 | WHRIA | 2020.07.23 | 55 |
138 | lvm 확장 [1] | WHRIA | 2019.12.25 | 54 |
137 | multiple NIC ubuntu [6] | WHRIA | 2020.03.10 | 54 |
136 | annotation service | WHRIA | 2020.05.03 | 54 |
135 | CE | WHRIA | 2020.05.17 | 54 |
134 | 너무도 많이 변해버린 c++ | WHRIA | 2016.08.15 | 53 |
133 | MedicalPhoto MSVC 2015 와 최신 boost 로... | WHRIA | 2016.08.26 | 53 |
132 | nvidia caffe | WHRIA | 2020.01.12 | 53 |
131 | exif javascript orientation | WHRIA | 2020.04.30 | 53 |
130 | git 특정 버젼 | WHRIA | 2020.07.11 | 53 |
129 | nvidia docker | WHRIA | 2020.01.15 | 52 |
128 | Visual Studio 설치후 Excel 2002 (XP) 종료시 에러 문제 | WHRIA | 2015.11.20 | 51 |
127 | DDR-WRT IPTV | WHRIA | 2016.06.15 | 51 |
126 | sql replication 성공 [1] | WHRIA | 2020.02.20 | 50 |
125 | conflict of interest | WHRIA | 2020.05.03 | 50 |
https://discuss.pytorch.org/t/combining-trained-models-in-pytorch/28383/2