cs231n作业：Assignment2-Pytorch

https://blog.csdn.net/guangcheng0312q/article/details/100117794

import torch
import torch.nn as nn
import torch.optim as optim
from torch.utils.data import DataLoader
from torch.utils.data import sampler

import torchvision.datasets as dset
import torchvision.transforms as T

import numpy as np

NUM_TRAIN = 49000

# The torchvision.transforms package provides tools for preprocessing data
# and for performing data augmentation; here we set up a transform to
# preprocess the data by subtracting the mean RGB value and dividing by the
# standard deviation of each RGB value; we've hardcoded the mean and std.
transform = T.Compose([
                T.ToTensor(),
                T.Normalize((0.4914, 0.4822, 0.4465), (0.2023, 0.1994, 0.2010))
            ])

# We set up a Dataset object for each split (train / val / test); Datasets load
# training examples one at a time, so we wrap each Dataset in a DataLoader which
# iterates through the Dataset and forms minibatches. We divide the CIFAR-10
# training set into train and val sets by passing a Sampler object to the
# DataLoader telling how it should sample from the underlying Dataset.
cifar10_train = dset.CIFAR10('./cs231n/datasets', train=True, download=True,
                             transform=transform)
loader_train = DataLoader(cifar10_train, batch_size=64, 
                          sampler=sampler.SubsetRandomSampler(range(NUM_TRAIN)))

cifar10_val = dset.CIFAR10('./cs231n/datasets', train=True, download=True,
                           transform=transform)
loader_val = DataLoader(cifar10_val, batch_size=64, 
                        sampler=sampler.SubsetRandomSampler(range(NUM_TRAIN, 50000)))

cifar10_test = dset.CIFAR10('./cs231n/datasets', train=False, download=True, 
                            transform=transform)
loader_test = DataLoader(cifar10_test, batch_size=64)

USE_GPU = True

dtype = torch.float32 # we will be using float throughout this tutorial

if USE_GPU and torch.cuda.is_available():
    device = torch.device('cuda')
else:
    device = torch.device('cpu')

# Constant to control how frequently we print train loss
print_every = 100

print('using device:', device)

def check_accuracy_part34(loader, model):
    if loader.dataset.train:
        print('Checking accuracy on validation set')
    else:
        print('Checking accuracy on test set')   
    num_correct = 0
    num_samples = 0
    model.eval()  # set model to evaluation mode
    with torch.no_grad():
        for x, y in loader:
            x = x.to(device=device, dtype=dtype)  # move to device, e.g. GPU
            y = y.to(device=device, dtype=torch.long)
            scores = model(x)
            _, preds = scores.max(1)
            num_correct += (preds == y).sum()
            num_samples += preds.size(0)
        acc = float(num_correct) / num_samples
        print('Got %d / %d correct (%.2f)' % (num_correct, num_samples, 100 * acc))

def train_part34(model, optimizer, epochs=1):
    """
    Train a model on CIFAR-10 using the PyTorch Module API.
    
    Inputs:
    - model: A PyTorch Module giving the model to train.
    - optimizer: An Optimizer object we will use to train the model
    - epochs: (Optional) A Python integer giving the number of epochs to train for
    
    Returns: Nothing, but prints model accuracies during training.
    """
    model = model.to(device=device)  # move the model parameters to CPU/GPU
    for e in range(epochs):
        for t, (x, y) in enumerate(loader_train):
            model.train()  # put model to training mode
            x = x.to(device=device, dtype=dtype)  # move to device, e.g. GPU
            y = y.to(device=device, dtype=torch.long)

            scores = model(x)
            loss = F.cross_entropy(scores, y)

            # Zero out all of the gradients for the variables which the optimizer
            # will update.
            optimizer.zero_grad()

            # This is the backwards pass: compute the gradient of the loss with
            # respect to each  parameter of the model.
            loss.backward()

            # Actually update the parameters of the model using the gradients
            # computed by the backwards pass.
            optimizer.step()

            if t % print_every == 0:
                print('Iteration %d, loss = %.4f' % (t, loss.item()))
                check_accuracy_part34(loader_val, model)
                print()

class ThreeLayerConvNet(nn.Module):
    def __init__(self,in_channel,channel_1,channel_2,num_classes):
        super().__init__()
        self.conv1 = nn.Conv2d(in_channel,channel_1,stride=1,kernel_size=5,padding=2)
        nn.init.kaiming_normal_(self.conv1.weight)
        self.conv2 = nn.Conv2d(channel_1,channel_2,stride=1,kernel_size=3,padding=1)
        nn.init.kaiming_normal_(self.conv2.weight)
        self.fc = nn.Linear(channel_2*32*32,num_classes)
        nn.init.kaiming_normal_(self.fc.weight)
        
    def forward(self,x):
        x = self.conv1(x)
        x = F.relu(x)
        x = self.conv2(x)
        x = flatten(x)
        x = F.relu(x)
        scores = self.fc(x)
        pass
    
        return scores 

def test_ThreeLayerConvNet():
    x = torch.zeros((64,3,32,32),dtype=dtype)
    model = ThreeLayerConvNet(in_channel=3,channel_1=12,channel_2=8,num_classes=10)
    scores = model(x)
    print(scores.size())
    
test_ThreeLayerConvNet()

class Flatten(nn.Module):
    def forward(self, x):
        return flatten(x)


class ThreeConvNetwork(nn.Module):
    def __init__(self):
        super().__init__()
        self.feature = nn.Sequential(
            nn.Conv2d(3,32,5,padding=2,bias=True),
            nn.ReLU(),
            nn.MaxPool2d(2),
            nn.Conv2d(32,64,3,padding=1,bias=True),
            nn.ReLU(),
            nn.MaxPool2d(2),
            nn.Conv2d(64,128,3,padding=1,bias=True),
            nn.ReLU(),
            nn.MaxPool2d(2),
            Flatten(),
            nn.Linear(128*4*4,20,bias=True),
            nn.Linear(20,10,bias=True),
        )
    def forward(self,x):
        x = self.feature(x)
        return x
model = ThreeConvNetwork()
learning_rate = 1e-3
#学习率不能设置太
optimizer = optim.Adam(model.parameters(),lr=learning_rate)
train_part34(model,optimizer,epochs=10)