Jovian
⭐️
Sign In
In [1]:
import torch
import torch.nn as nn
import torch.nn.functional as F
In [2]:
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)
        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

In [3]:
net = Net()
print(net)
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) )
In [4]:
params = list(net.parameters())
print(len(params))
print(params[0].size())
10 torch.Size([6, 1, 3, 3])
In [5]:
input = torch.randn(1, 1, 32, 32)
out = net(input)
print(out)
tensor([[ 0.0165, -0.0147, 0.0626, 0.1247, 0.0019, 0.0735, 0.0325, -0.0198, -0.1629, -0.0529]], grad_fn=<AddmmBackward>)
In [6]:
net.zero_grad()
out.backward(torch.randn(1, 10))
In [7]:
output = net(input)
target = torch.randn(10)  # a dummy target, for example
target = target.view(1, -1)  # make it the same shape as output
criterion = nn.MSELoss()

loss = criterion(output, target)
print(loss)
tensor(0.8524, grad_fn=<MseLossBackward>)
In [8]:
print(loss.grad_fn)  # MSELoss
print(loss.grad_fn.next_functions[0][0])  # Linear
print(loss.grad_fn.next_functions[0][0].next_functions[0][0])  # ReLU
<MseLossBackward object at 0x1283ffc50> <AddmmBackward object at 0x1283ffe50> <AccumulateGrad object at 0x1283ffc50>
In [9]:
net.zero_grad()     # zeroes the gradient buffers of all parameters

print('conv1.bias.grad before backward')
print(net.conv1.bias.grad)

loss.backward()

print('conv1.bias.grad after backward')
print(net.conv1.bias.grad)
conv1.bias.grad before backward tensor([0., 0., 0., 0., 0., 0.]) conv1.bias.grad after backward tensor([-0.0373, -0.0146, -0.0021, 0.0157, 0.0195, -0.0064])
In [21]:
import torch.optim as optim

# create your optimizer
optimizer = optim.SGD(net.parameters(), lr=0.01)

# in your training loop:
optimizer.zero_grad()   # zero the gradient buffers
output = net(input)
loss = criterion(output, target)
loss.backward()
optimizer.step()    # Does the update
In [25]:

import torch
import torchvision
import torchvision.transforms as transforms

transform = transforms.Compose([transforms.ToTensor(),transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))])
trainset = torchvision.datasets.CIFAR10(root='./data', train=True,download=True, transform=transform)
trainloader = torch.utils.data.DataLoader(trainset, batch_size=4,shuffle=True, num_workers=2)
testset = torchvision.datasets.CIFAR10(root='./data', train=False,download=True, transform=transform)
testloader = torch.utils.data.DataLoader(testset, batch_size=4,shuffle=False, num_workers=2)

classes = ('plane', 'car', 'bird', 'cat','deer', 'dog', 'frog', 'horse', 'ship', 'truck')

Files already downloaded and verified
--------------------------------------------------------------------------- TypeError Traceback (most recent call last) <ipython-input-25-925a3d5a7796> in <module> 5 transform = transforms.Compose([transforms.ToTensor(),transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))]) 6 trainset = torchvision.datasets.CIFAR10(root='./data', train=True,download=True, transform=transform) ----> 7 trainloader = torch.utils.data.DataLoader(trainset, batch_size=4,shuffle=True, num_workers=2) 8 testset = torchvision.datasets.CIFAR10(root='./data', train=False,download=True, transform=transform) 9 testloader = torch.utils.data.DataLoader(testset, batch_size=4,shuffle=False, num_workers=2) TypeError: 'int' object is not callable
In [ ]:
 
In [ ]: