I am trying to build an RNN that trains on YouTube comments. I am learning as I progress, I am struggling to correctly define the forward pass for my network. I have previously done a CNN but this current network is different and it is causing me confusion, I would appreciate any help!
Here is the network:
class EncoderCNN(nn.Module):
def init(self, embed_size):super(EncoderCNN, self).__init__() resnet = models.resnet152(pretrained=True) layers = list(resnet.children())[:-1] self.resnet = nn.Sequential(*layers) self.linear = nn.Linear(resnet.fc.in_features, embed_size) self.bn = nn.BatchNorm1d(embed_size, momentum=0.01) def forward(self, images): features = self.linear(features) return features