pytorch nn model

https://pytorch.org/docs/stable/nn.html

 

me@me:~/me$ cat 0702.py
import torch
import torch.nn as nn
import torch.nn.functional as F


class Net(nn.Module):

    def __init__(self):
        super(Net, self).__init__()
        # 1 input image channel, 6 output channels, 3x3 square convolution
        # kernel
        self.conv1 = nn.Conv2d(1, 6, 3)  # 1 means 1 channel
        self.conv2 = nn.Conv2d(6, 16, 3)
        # an affine operation: y = Wx + b
        self.fc1 = nn.Linear(16 * 6 * 6, 120)  # 6*6 from image dimension
        self.fc2 = nn.Linear(120, 84)
        self.fc3 = nn.Linear(84, 10)


    def forward(self, x):
        # Max pooling over a (2, 2) window
        x = F.max_pool2d(F.relu(self.conv1(x)), (2, 2))
        # If the size is a square you can only specify a single number
        x = F.max_pool2d(F.relu(self.conv2(x)), 2)
        x = x.view(-1, self.num_flat_features(x))
        x = F.relu(self.fc1(x))
        x = F.relu(self.fc2(x))
        x = self.fc3(x)
        return x

    def num_flat_features(self, x):
        size = x.size()[1:]  # all dimensions except the batch dimension
        num_features = 1
        for s in size:
            num_features *= s
        return num_features


net = Net()
print(net)

params = list(net.parameters())
print("Total params are {}".format(len(params)))
print("conv1's .weight is: {}".format(params[0].size()))  # conv1's .weight


input = torch.randn(1, 1, 32, 32)
out = net(input)
print(out)


net.zero_grad()
out.backward(torch.randn(1, 10))
print(out)


me@me:~/me$ python 0702.py
Net(
  (conv1): Conv2d(1, 6, kernel_size=(3, 3), stride=(1, 1))
  (conv2): Conv2d(6, 16, kernel_size=(3, 3), stride=(1, 1))
  (fc1): Linear(in_features=576, out_features=120, bias=True)
  (fc2): Linear(in_features=120, out_features=84, bias=True)
  (fc3): Linear(in_features=84, out_features=10, bias=True)
)
Total params are 10
conv1's .weight is: torch.Size([6, 1, 3, 3])
tensor([[ 0.0102,  0.0036, -0.0183,  0.0757, -0.0053, -0.0685,  0.1568, -0.0227,
         -0.0635,  0.0711]], grad_fn=<AddmmBackward>)
tensor([[ 0.0102,  0.0036, -0.0183,  0.0757, -0.0053, -0.0685,  0.1568, -0.0227,
         -0.0635,  0.0711]], grad_fn=<AddmmBackward>)