CNN卷积神经网络

1.作业代码及结果截图：

 

 

 

 

2.代码详情

import torch
from PIL import Image
import numpy as np
from torchvision import transforms
import torch.optim as optim
import torch.nn.functional as F
import matplotlib.pyplot as plt
import math
from torchtext.vocab import vocab
import sys
import os
os.environ["KMP_DUPLICATE_LIB_OK"]="TRUE"

# third-party library
import torch.nn as nn
import torch.utils.data as Data
import torchvision



# torch.manual_seed(1)    # reproducible

# Hyper Parameters
EPOCH = 1               # train the training data n times, to save time, we just train 1 epoch
BATCH_SIZE = 50
LR = 0.001              # learning rate
DOWNLOAD_MNIST = False


# Mnist digits dataset
if not(os.path.exists('./mnist/')) or not os.listdir('./mnist/'):
    # not mnist dir or mnist is empyt dir
    DOWNLOAD_MNIST = True

train_data = torchvision.datasets.MNIST(
    root='./mnist/',
    train=True,                                     # this is training data
    transform=torchvision.transforms.ToTensor(),    # Converts a PIL.Image or numpy.ndarray to
                                                    # torch.FloatTensor of shape (C x H x W) and normalize in the range [0.0, 1.0]
    download=DOWNLOAD_MNIST,
)

# plot one example
print(train_data.train_data.size())                 # (60000, 28, 28)
print(train_data.train_labels.size())               # (60000)
plt.imshow(train_data.train_data[0].numpy(), cmap='gray')
plt.title('%i' % train_data.train_labels[0])
plt.show()

# Data Loader for easy mini-batch return in training, the image batch shape will be (50, 1, 28, 28)
train_loader = Data.DataLoader(dataset=train_data, batch_size=BATCH_SIZE, shuffle=True)

# pick 2000 samples to speed up testing
test_data = torchvision.datasets.MNIST(root='./mnist/', train=False)
test_x = torch.unsqueeze(test_data.test_data, dim=1).type(torch.FloatTensor)[:2000]/255.   # shape from (2000, 28, 28) to (2000, 1, 28, 28), value in range(0,1)
test_y = test_data.test_labels[:2000]


class CNN(nn.Module):
    def __init__(self):
        super(CNN, self).__init__()
        self.conv1 = torch.nn.Sequential(  # input_size = 227*227*3
            torch.nn.Conv2d(in_channels=3, out_channels=96, kernel_size=11, stride=4, padding=0),
            torch.nn.ReLU(),
            torch.nn.MaxPool2d(kernel_size=3, stride=2)  # output_size = 27*27*96
        )
        self.conv2 = torch.nn.Sequential(  # input_size = 27*27*96
            torch.nn.Conv2d(96, 256, 5, 1, 2),
            torch.nn.ReLU(),
            torch.nn.MaxPool2d(3, 2)  # output_size = 13*13*256
        )
        self.conv3 = torch.nn.Sequential(  # input_size = 13*13*256
            torch.nn.Conv2d(256, 384, 3, 1, 1),
            torch.nn.ReLU(),  # output_size = 13*13*384
        )
        self.conv4 = torch.nn.Sequential(  # input_size = 13*13*384
            torch.nn.Conv2d(384, 384, 3, 1, 1),
            torch.nn.ReLU(),  # output_size = 13*13*384
        )
        self.conv5 = torch.nn.Sequential(  # input_size = 13*13*384
            torch.nn.Conv2d(384, 256, 3, 1, 1),
            torch.nn.ReLU(),
            torch.nn.MaxPool2d(3, 2)  # output_size = 6*6*256
        )

    self.dense = torch.nn.Sequential(
        torch.nn.Linear(9216, 4096),
        torch.nn.ReLU(),
        torch.nn.Dropout(0.5),
        torch.nn.Linear(4096, 4096),
        torch.nn.ReLU(),
        torch.nn.Dropout(0.5),
        torch.nn.Linear(4096, 50)
    )

    self.out = nn.Linear(32 * 7 * 7, 10)   # fully connected layer, output 10 classes

    def forward(self, x):
        x = self.conv1(x)
        x = self.conv2(x)
        x = x.view(x.size(0), -1)           # flatten the output of conv2 to (batch_size, 32 * 7 * 7)
        output = self.out(x)
        return output, x    # return x for visualization


cnn = CNN()
print(cnn)  # net architecture

optimizer = torch.optim.Adam(cnn.parameters(), lr=LR)   # optimize all cnn parameters
loss_func = nn.CrossEntropyLoss()                       # the target label is not one-hotted

# following function (plot_with_labels) is for visualization, can be ignored if not interested
from matplotlib import cm
try: from sklearn.manifold import TSNE; HAS_SK = True
except: HAS_SK = False; print('Please install sklearn for layer visualization')
def plot_with_labels(lowDWeights, labels):
    plt.cla()
    X, Y = lowDWeights[:, 0], lowDWeights[:, 1]
    for x, y, s in zip(X, Y, labels):
        c = cm.rainbow(int(255 * s / 9)); plt.text(x, y, s, backgroundcolor=c, fontsize=9)
    plt.xlim(X.min(), X.max()); plt.ylim(Y.min(), Y.max()); plt.title('Visualize last layer'); plt.show(); plt.pause(0.01)

plt.ion()
# training and testing
for epoch in range(EPOCH):
    for step, (b_x, b_y) in enumerate(train_loader):   # gives batch data, normalize x when iterate train_loader

        output = cnn(b_x)[0]               # cnn output
        loss = loss_func(output, b_y)   # cross entropy loss
        optimizer.zero_grad()           # clear gradients for this training step
        loss.backward()                 # backpropagation, compute gradients
        optimizer.step()                # apply gradients

        if step % 50 == 0:
            test_output, last_layer = cnn(test_x)
            pred_y = torch.max(test_output, 1)[1].data.numpy()
            accuracy = float((pred_y == test_y.data.numpy()).astype(int).sum()) / float(test_y.size(0))
            print('Epoch: ', epoch, '| train loss: %.4f' % loss.data.numpy(), '| test accuracy: %.2f' % accuracy)
            if HAS_SK:
                # Visualization of trained flatten layer (T-SNE)
                tsne = TSNE(perplexity=30, n_components=2, init='pca', n_iter=5000)
                plot_only = 500
                low_dim_embs = tsne.fit_transform(last_layer.data.numpy()[:plot_only, :])
                labels = test_y.numpy()[:plot_only]
                plot_with_labels(low_dim_embs, labels)
plt.ioff()

# print 10 predictions from test data
test_output, _ = cnn(test_x[:10])
pred_y = torch.max(test_output, 1)[1].data.numpy()
print(pred_y, 'prediction number')
print(test_y[:10].numpy(), 'real number')