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 |
---|---|---|---|---|
1819 | Afrikaans - Afrikaans | WHRIA | 2024.05.24 | 0 |
1818 | Albanian - shqip | WHRIA | 2024.05.24 | 0 |
1817 | Amharic - አማርኛ | WHRIA | 2024.05.24 | 0 |
1816 | Arabic - العربية | WHRIA | 2024.05.24 | 0 |
1815 | Armenian - հայերեն | WHRIA | 2024.05.24 | 0 |
1814 | Azerbaijani - azərbaycan | WHRIA | 2024.05.24 | 0 |
1813 | Bangla - বাংলা | WHRIA | 2024.05.24 | 0 |
1812 | Basque - euskara | WHRIA | 2024.05.24 | 0 |
1811 | Belarusian - беларуская | WHRIA | 2024.05.24 | 0 |
1810 | Bosnian - bosanski | WHRIA | 2024.05.24 | 0 |
1809 | Bulgarian - български | WHRIA | 2024.05.24 | 0 |
1808 | Burmese - မြန်မာ | WHRIA | 2024.05.24 | 0 |
1807 | Catalan - català | WHRIA | 2024.05.24 | 0 |
1806 | Chinese (China) - 中文(中国) | WHRIA | 2024.05.24 | 0 |
1805 | Chinese (Taiwan) - Chinese (Taiwan) | WHRIA | 2024.05.24 | 0 |
https://discuss.pytorch.org/t/combining-trained-models-in-pytorch/28383/2