# Custom Ensemble approach

**URL:** <https://discuss.pytorch.org/t/custom-ensemble-approach/52024>\
**Category:** vision\
**Created:** [July 30, 2019, 8:48am UTC](https://discuss.pytorch.org/t/custom-ensemble-approach/52024 "2019-07-30T08:48:40Z")\
**Posts on this page:** 1\
**Showing post:** 4

<div class="post-metadata">

**Author:** ![ptrblck](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/ptrblck/32/1823_2.png) [@ptrblck](https://discuss.pytorch.org/u/ptrblck)\
**Post date:** [July 31, 2019, 8:26am UTC](https://discuss.pytorch.org/t/custom-ensemble-approach/52024/4 "2019-07-31T08:26:31Z")

</div>

Sure, we can just use the linked code as the base script:

```python
class MyEnsemble(nn.Module):
    def __init__ (self, modelA, modelB, nb_classes=10):
        super(MyEnsemble, self). __init__ ()
        self.modelA = modelA
        self.modelB = modelB
        # Remove last linear layer
        self.modelA.fc = nn.Identity()
        self.modelB.fc = nn.Identity()
        
        # Create new classifier
        self.classifier = nn.Linear(2048+512, nb_classes)
        
    def forward(self, x):
        x1 = self.modelA(x.clone()) # clone to make sure x is not changed by inplace methods
        x1 = x1.view(x1.size(0), -1)
        x2 = self.modelB(x)
        x2 = x2.view(x2.size(0), -1)
        x = torch.cat((x1, x2), dim=1)
        
        x = self.classifier(F.relu(x))
        return x

# Train your separate models
# ...
# We use pretrained torchvision models here
modelA = models.resnet50(pretrained=True)
modelB = models.resnet18(pretrained=True)

# Freeze these models
for param in modelA.parameters():
    param.requires_grad_(False)

for param in modelB.parameters():
    param.requires_grad_(False)

# Create ensemble model
model = MyEnsemble(modelA, modelB)
x = torch.randn(1, 3, 224, 224)
output = model(x)

```

---

_[View the full topic](https://discuss.pytorch.org/t/custom-ensemble-approach/52024)._