import torch
import torch.nn as nn
import torch.nn.functional as F
class Net(nn.Module):
def __init__(self):
super(Net,self).__init__()
self.conv1 = nn.Conv2d(1,6,5)
self.conv2 = nn.Conv2d(6,16,5)
self.fc1 = nn.Linear(16*5*5, 120)
self.fc2 = nn.Linear(120,84)
self.fc3 = nn.Linear(84,10)
def forward(self,x):
x= F.max_pool2d(F.relu(self.conv1(x)),(2,2))
x= F.max_pool2d(F.relu(self.conv2(x)),2)
x= x.view(-1,self.num_flat_feature(x))
x = F.relu(self.fc1(x))
x= F.relu(self.fc2(x))
x = self.fc3(x)
return x
def num_flat_feature(self,x):
size = x.size()[1:]
num_features=1
for s in size:
num_features *=s
return num_features
net = Net()
print(net)
input = torch.randn(1,1,32,32)
out = net(input)
print(out)
Set all parameter gradient buffers to zero and use random gradients to backpropagate
net.zero_grad()
out.backward(torch.randn(1, 10))
Output
Here, we have completed:
1. Define a neural network
2. Processing input and calling backpropagation
Remaining:
1. Calculate the loss value
2. Update the weights in the network