Forrás: A DEEP LEARNING WITH PYTORCH: A 60 MINUTE BLITZ tutorialból válogattam őket össze.
https://pytorch.org/tutorials/beginner/deep_learning_60min_blitz.html
Colab-es GPU-n való futtatáshoz: "Runtime" menüpont -> "Change runtime type" -> "Hardware accelerator": GPU
Ezután újraindul az environment, tehát minden addigi a sessionben lévő dolog elveszik.
import torch
import numpy as np
data = [[1, 2], [3, 4]]
x_data = torch.tensor(data)
print(x_data)
np_array = np.array(data)
x_np = torch.from_numpy(np_array)
print(x_np)
x_ones = torch.ones_like(x_data) # retains the properties of x_data
print(f"Ones Tensor: \n {x_ones} \n")
x_rand = torch.rand_like(x_data, dtype=torch.float) # overrides the datatype of x_data
print(f"Random Tensor: \n {x_rand} \n")
shape = (2, 3,)
rand_tensor = torch.rand(shape)
ones_tensor = torch.ones(shape)
zeros_tensor = torch.zeros(shape)
print(f"Random Tensor: \n {rand_tensor} \n")
print(f"Ones Tensor: \n {ones_tensor} \n")
print(f"Zeros Tensor: \n {zeros_tensor}")
tensor = torch.rand(3, 4)
print(f"Shape of tensor: {tensor.shape}")
print(f"Datatype of tensor: {tensor.dtype}")
print(f"Device tensor is stored on: {tensor.device}")
# We move our tensor to the GPU if available
if torch.cuda.is_available():
tensor = tensor.to('cuda')
print(f"Device tensor is stored on: {tensor.device}")
tensor = torch.ones(4, 4)
tensor[:,1] = 0
print(tensor)
t1 = torch.cat([tensor, tensor, tensor], dim=1)
print(t1)
# This computes the element-wise product
print(f"tensor.mul(tensor) \n {tensor.mul(tensor)} \n")
# Alternative syntax:
print(f"tensor * tensor \n {tensor * tensor}")
print(f"tensor.matmul(tensor.T) \n {tensor.matmul(tensor.T)} \n")
# Alternative syntax:
print(f"tensor @ tensor.T \n {tensor @ tensor.T}")
print(tensor, "\n")
tensor.add_(5)
print(tensor)
t = torch.ones(5)
print(f"t: {t}")
n = t.numpy()
print(f"n: {n}")
t.add_(1)
print(f"t: {t}")
print(f"n: {n}")
n = np.ones(5)
t = torch.from_numpy(n)
np.add(n, 1, out=n)
print(f"t: {t}")
print(f"n: {n}")
import torch, torchvision
model = torchvision.models.resnet18(pretrained=True)
data = torch.rand(1, 3, 64, 64)
labels = torch.rand(1, 1000)
prediction = model(data)
loss = (prediction - labels).sum()
loss.backward() # backward pass
optim = torch.optim.SGD(model.parameters(), lr=1e-2, momentum=0.9)
optim.step()
import torch
a = torch.tensor([2., 3.], requires_grad=True)
b = torch.tensor([6., 4.], requires_grad=True)
Q = 3*a**3 - b**2
Q
external_grad = torch.tensor([1., 1.])
Q.backward(gradient=external_grad)
Q.sum().backward()
# check if collected gradients are correct
print(9*a**2 == a.grad)
print(-2*b == b.grad)
x = torch.rand(5, 5)
y = torch.rand(5, 5)
z = torch.rand((5, 5), requires_grad=True)
a = x + y
print(f"Does `a` require gradients? : {a.requires_grad}")
b = x + z
print(f"Does `b` require gradients?: {b.requires_grad}")
from torch import nn, optim
model = torchvision.models.resnet18(pretrained=True)
# Freeze all the parameters in the network
for param in model.parameters():
param.requires_grad = False
model.fc = nn.Linear(512, 10)
optimizer = optim.SGD(model.parameters(), lr=1e-2, momentum=0.9)
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, 5x5 square convolution
# kernel
self.conv1 = nn.Conv2d(1, 6, 5)
self.conv2 = nn.Conv2d(6, 16, 5)
# an affine operation: y = Wx + b
self.fc1 = nn.Linear(16 * 5 * 5, 120) # 5*5 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 specify with a single number
x = F.max_pool2d(F.relu(self.conv2(x)), 2)
x = torch.flatten(x, 1) # flatten all dimensions except the batch dimension
x = F.relu(self.fc1(x))
x = F.relu(self.fc2(x))
x = self.fc3(x)
return x
net = Net()
print(net)
params = list(net.parameters())
print(len(params))
print(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))
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)
input -> conv2d -> relu -> maxpool2d -> conv2d -> relu -> maxpool2d -> flatten -> linear -> relu -> linear -> relu -> linear -> MSELoss -> loss
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
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)
learning_rate = 0.01
for f in net.parameters():
f.data.sub_(f.grad.data * learning_rate)
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
import torch
from torch import nn
from torch.utils.data import DataLoader
from torchvision import datasets
from torchvision.transforms import ToTensor, Lambda, Compose
import matplotlib.pyplot as plt
# Download training data from open datasets.
training_data = datasets.FashionMNIST(
root="data",
train=True,
download=True,
transform=ToTensor(),
)
# Download test data from open datasets.
test_data = datasets.FashionMNIST(
root="data",
train=False,
download=True,
transform=ToTensor(),
)
batch_size = 64
# Create data loaders.
train_dataloader = DataLoader(training_data, batch_size=batch_size)
test_dataloader = DataLoader(test_data, batch_size=batch_size)
for X, y in test_dataloader:
print("Shape of X [N, C, H, W]: ", X.shape)
print("Shape of y: ", y.shape, y.dtype)
break
# Get cpu or gpu device for training.
device = "cuda" if torch.cuda.is_available() else "cpu"
print("Using {} device".format(device))
# Define model
class NeuralNetwork(nn.Module):
def __init__(self):
super(NeuralNetwork, self).__init__()
self.flatten = nn.Flatten()
self.linear_relu_stack = nn.Sequential(
nn.Linear(28*28, 512),
nn.ReLU(),
nn.Linear(512, 512),
nn.ReLU(),
nn.Linear(512, 10)
)
def forward(self, x):
x = self.flatten(x)
logits = self.linear_relu_stack(x)
return logits
model = NeuralNetwork().to(device)
print(model)
loss_fn = nn.CrossEntropyLoss()
optimizer = torch.optim.SGD(model.parameters(), lr=1e-3)
def train(dataloader, model, loss_fn, optimizer):
size = len(dataloader.dataset)
model.train()
for batch, (X, y) in enumerate(dataloader):
X, y = X.to(device), y.to(device)
# Compute prediction error
pred = model(X)
loss = loss_fn(pred, y)
# Backpropagation
optimizer.zero_grad()
loss.backward()
optimizer.step()
if batch % 100 == 0:
loss, current = loss.item(), batch * len(X)
print(f"loss: {loss:>7f} [{current:>5d}/{size:>5d}]")
def test(dataloader, model, loss_fn):
size = len(dataloader.dataset)
num_batches = len(dataloader)
model.eval()
test_loss, correct = 0, 0
with torch.no_grad():
for X, y in dataloader:
X, y = X.to(device), y.to(device)
pred = model(X)
test_loss += loss_fn(pred, y).item()
correct += (pred.argmax(1) == y).type(torch.float).sum().item()
test_loss /= num_batches
correct /= size
print(f"Test Error: \n Accuracy: {(100*correct):>0.1f}%, Avg loss: {test_loss:>8f} \n")
epochs = 5
for t in range(epochs):
print(f"Epoch {t+1}\n-------------------------------")
train(train_dataloader, model, loss_fn, optimizer)
test(test_dataloader, model, loss_fn)
print("Done!")
torch.save(model.state_dict(), "model.pth")
print("Saved PyTorch Model State to model.pth")
model = NeuralNetwork()
model.load_state_dict(torch.load("model.pth"))
classes = [
"T-shirt/top",
"Trouser",
"Pullover",
"Dress",
"Coat",
"Sandal",
"Shirt",
"Sneaker",
"Bag",
"Ankle boot",
]
model.eval()
x, y = test_data[0][0], test_data[0][1]
with torch.no_grad():
pred = model(x)
predicted, actual = classes[pred[0].argmax(0)], classes[y]
print(f'Predicted: "{predicted}", Actual: "{actual}"')