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 | youtube | WHRIA | 2016.09.30 | 39 |
138 | lvm [2] | WHRIA | 2020.01.09 | 39 |
137 | 회귀분석 종류 | WHRIA | 2020.04.14 | 39 |
136 | plum | WHRIA | 2020.04.03 | 38 |
135 | 너무도 많이 변해버린 c++ | WHRIA | 2016.08.15 | 37 |
134 | pytorch - caffe | WHRIA | 2019.12.19 | 37 |
133 | 윈도우 raid ahci 전환 | WHRIA | 2019.12.26 | 37 |
132 | android / capture and crop [5] | WHRIA | 2020.05.10 | 37 |
131 | calendar javascript dropdown | WHRIA | 2020.03.01 | 36 |
130 | 감가상각 계산 | WHRIA | 2015.11.30 | 35 |
129 | kaggle leakage | WHRIA | 2019.12.19 | 35 |
128 | raid 6 rebuild | WHRIA | 2020.01.07 | 35 |
127 | 의료영상분석장치 분류 코드 | WHRIA | 2020.04.22 | 35 |
126 | conflict of interest | WHRIA | 2020.05.03 | 35 |
125 | letencrypt - win | WHRIA | 2018.08.12 | 34 |
https://discuss.pytorch.org/t/combining-trained-models-in-pytorch/28383/2