0e52f273bc0158e05af766e2d1006b3c5198e9c3,models/densenet.py,_DenseLayer,forward,#_DenseLayer#,24

Before Change

        self.drop_rate = drop_rate

    def forward(self, *prev_features):
        concated_features = torch.cat(prev_features, 1)
        bottleneck_output = self.conv1(self.relu1(self.norm1(concated_features)))
        new_features = self.conv2(self.relu2(self.norm2(bottleneck_output)))
        if self.drop_rate > 0:
            new_features = F.dropout(new_features, p=self.drop_rate, training=self.training)
        return new_features

After Change

    def forward(self, *prev_features):
        bn_function = _bn_function_factory(self.norm1, self.relu1, self.conv1)
        if self.efficient and any(prev_feature.requires_grad for prev_feature in prev_features):
            bottleneck_output = cp.checkpoint(bn_function, *prev_features)
        else:
            bottleneck_output = bn_function(*prev_features)
        new_features = self.conv2(self.relu2(self.norm2(bottleneck_output)))
        if self.drop_rate > 0:
            new_features = F.dropout(new_features, p=self.drop_rate, training=self.training)
        return new_features

Instances