利用knn svm cnn 逻辑回归 mlp rnn等方法实现mnist数据集分类（pytorch实现及源码解析）(1)

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):

losses = []

acc = []

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, 'Step: ', step/50,  ‘| train loss: %.4f’ % loss.data.numpy(), ‘| test accuracy: %.2f’ % accuracy)

losses.append(loss.data.numpy())

acc.append(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()

plt.figure()

f, axes = plt.subplots(1, 1)

axes.clear()

axes.plot([x for x in range(24)], losses)  ###range(1,11)

axes.set_xlabel(“训练步数”)

axes.set_ylabel(“损失值”)

axes.set_title(“MNIST”)

axes.set_ylim((0, max(losses)))  ###1

axes.set_xlim((1, 24))

​

row_labels = [‘准确率：’]

col_labels = [‘数值’]

value = max(acc)

table_vals = [[‘{:.2f}%’.format(value*100)]]

row_colors = [‘gold’]

my_table = plt.table(cellText=table_vals, colWidths=[0.1] * 5,

rowLabels=row_labels, rowColours=row_colors, loc=‘best’)

plt.savefig(“CNN” + “.png”)

plt.show()

​

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’)

3.knn实现

​

from future import print_function

​

import os

​

third-party library

import torch

import torch.nn as nn

import torch.utils.data as Data

import torchvision

import time

import matplotlib.pyplot as plt

localtime = time.asctime( time.localtime(time.time()) )

print(“本地时间为 :”, localtime)

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()

​

pick 2000 samples to speed up testing

​

train_data = torchvision.datasets.MNIST