Deep Learning with PyTorch

Creating a simple linear model

We will create a simple linear model that will map the pre-convoluted features to the respective categories. In this case, the number of categories is two:

class FullyConnectedModel(nn.Module):        def __init__(self,in_size,out_size):        super().__init__()        self.fc = nn.Linear(in_size,out_size)    def forward(self,inp):        out = self.fc(inp)        return outfc_in_size = 8192fc = FullyConnectedModel(fc_in_size,classes)if is_cuda:    fc = fc.cuda()

Now, we are good to train our new model and validate the dataset.