Pytorch_basics_main

[Pytorch] First day

# import necessary packages
import torch
import torchvision
import torch.nn as nn
import numpy as np
import torchvision.transforms as transforms

Content one

# Basic autograd example 1

# Create tensors.
x = torch.tensor(1., requires_grad=True)
w = torch.tensor(2., requires_grad=True)
b = torch.tensor(3., requires_grad=True)

print(type(x), type(w), type(b))

<class 'torch.Tensor'> <class 'torch.Tensor'> <class 'torch.Tensor'>

# Build a computional graph.
y = w * x + b   # y = 2 * x + 3

# Compute gadients.
y.backward()

# Print out the gradients.
print(x.grad)   # x.grad = 2
print(w.grad)   # w.grad = 1
print(b.grad)   # b.grad = 1

tensor(2.)
tensor(1.)
tensor(1.)

Content two

# Basic autograd example 2

# Create tensors of shape (10, 3) and (10, 2).
x = torch.randn(10, 3)
y = torch.randn(10, 2)

# Build a fully connected layer.
linear = nn.Linear(3, 2)
print('w: ', linear.weight)
print('b: ', linear.bias)

w:  Parameter containing:
tensor([[ 0.2271,  0.4796, -0.4287],
        [ 0.3378, -0.5249,  0.2095]], requires_grad=True)
b:  Parameter containing:
tensor([0.4186, 0.1931], requires_grad=True)

# Build loss function and optimizer.
criterion = nn.MSELoss()
optimizer = torch.optim.SGD(linear.parameters(), lr=0.01)

# Forward pass.
pred = linear(x)

# Compute loss.
loss = criterion(pred, y)
print('loss:', loss.item())

loss: 1.1817594766616821

# Backward pass.
loss.backward()

# Print out the gradients.
print('dl/dw: ', linear.weight.grad)
print('dl/db: ', linear.bias.grad)

dl/dw:  tensor([[-0.5055,  0.2931, -0.8895],
        [ 0.0444,  0.0985,  0.4994]])
dl/db:  tensor([ 0.6998, -0.0333])

# 1-step gradient descent.
optimizer.step()

# We can also perform gradient descent at the low level.
# linear.weight.data.sub_(0.01 * linear.weight.grad.data)
# linear.bias.data.sub_(0.01 * linear.bias.grad.data)

# Print out the loss after 1-step gradient descent.
pred = linear(x)
loss = criterion(pred, y)
print('loss after 1 step optimization: ',loss.item())

loss after 1 step optimization:  1.1630728244781494

Content three

# Loading data from numpy

# Create a numpy array.
x = np.array([[1, 2], [3, 4]])

# Convert the numpy array to a torch tensor.
y = torch.from_numpy(x)

# Convert the torch tensor to a numpy array.
z = y.numpy()

print(type(x), type(y), type(z))

<class 'numpy.ndarray'> <class 'torch.Tensor'> <class 'numpy.ndarray'>

Content four

# Download and construct CIFAR-10 dataset.
train_dataset = torchvision.datasets.CIFAR10(root='../../data',
                                             train=True,
                                             transform=transforms.ToTensor(),
                                             download=True)
# Fetch one data pair (read data from disk).
print(type(train_dataset)) # <class 'torchvision.datasets.cifar.CIFAR10'>
image, label = train_dataset[0]

print(image.size)
print(label)

Files already downloaded and verified
<class 'torchvision.datasets.cifar.CIFAR10'>
<built-in method size of Tensor object at 0x7fbbe5e40f90>
6

# Data loader (this provides queues and threads in a very simple way).
train_loader = torch.utils.data.DataLoader(dataset=train_dataset,
                                           batch_size=64,
                                           shuffle=True)

# When iteration starts, queue and thread start to load data from files.
data_iter = iter(train_loader)

# Mini-batch images and labels.
images, labels = data_iter.__next__()

# Actual usage of the data loader is as below.
for images, labels in train_loader:
    # Training code should be written here.
    pass

Content five

# Input pipline for custom dataset

# We should build our custom dataset as below.
class CustomDataset(torch.utils.data.Dataset):
    def __init__(self):
        # TODO
        # 1.Initilize file paths or a list of file names.
        pass
    def __getitem__(self, index):
        # TODO
        # 1.Read one data from file (e.g.using numpy.fromfile, PIL.Image.open).
        # 2.Preprocess the data (e.g. torchvision.Transfrom).
        # 3.Return a data pair (e.g. image and label).
        pass
    def __len__(self):
        # We should change 0 to the total size of our dataset.
        return 0
    
# You can then use the prebuilt data loader.
custom_dataset = CustomDataset()
train_loader = torch.utils.data.DataLoader(dataset=custom_dataset,
                                           batch_size=64,
                                           shuffle=False)

Content six

# Pretrained model

# Download and load the pretrained ResNet-18.
resnet = torchvision.models.resnet18(pretrained=True)

# If we want to finetune only the top layer of the model, set as below.
for param in resnet.parameters():
    param.requires_grad = False

# Replace the top layer for fintuning.
resnet.fc = nn.Linear(resnet.fc.in_features, 100)   # 100 is an example.

# Forward pass
images = torch.randn(64, 3, 224, 224)
outputs = resnet(images)

print(outputs.size())   # result is torch.Size([64, 100])

/home/wsl_ubuntu/anaconda3/envs/xy_trans/lib/python3.8/site-packages/torchvision/models/_utils.py:208: UserWarning: The parameter 'pretrained' is deprecated since 0.13 and may be removed in the future, please use 'weights' instead.
  warnings.warn(
/home/wsl_ubuntu/anaconda3/envs/xy_trans/lib/python3.8/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and may be removed in the future. The current behavior is equivalent to passing `weights=ResNet18_Weights.IMAGENET1K_V1`. You can also use `weights=ResNet18_Weights.DEFAULT` to get the most up-to-date weights.
  warnings.warn(msg)
Downloading: "https://download.pytorch.org/models/resnet18-f37072fd.pth" to /home/wsl_ubuntu/.cache/torch/hub/checkpoints/resnet18-f37072fd.pth
100%|██████████| 44.7M/44.7M [00:20<00:00, 2.34MB/s]


torch.Size([64, 100])

Content seven

# Save and load the entire model.
torch.save(resnet, 'model.ckpt')
model = torch.load('model.ckpt')

# Save and load only the model parameters (recommended).
torch.save(resnet.state_dict(), 'params.ckpt')
resnet.load_state_dict(torch.load('params.ckpt'))

<All keys matched successfully>