VGG貓狗分類:

import tensorflow as tf
from tensorflow import keras
from tensorflow.keras import layers, regularizers
import numpy as np
import os
import cv2
import matplotlib.pyplot as plt

os.environ["CUDA_VISIBLE_DEVICES"] = "1"

resize = 224
path ="train/"

def load_data():
imgs = os.listdir(path)
num = len(imgs)
train_data = np.empty((5000, resize, resize, 3), dtype="int32")
train_label = np.empty((5000, ), dtype="int32")
test_data = np.empty((5000, resize, resize, 3), dtype="int32")
test_label = np.empty((5000, ), dtype="int32")
for i in range(5000):
if i % 2:
train_data[i] = cv2.resize(cv2.imread(path+'/'+ 'dog.' + str(i) + '.jpg'), (resize, resize))
train_label[i] = 1
else:
train_data[i] = cv2.resize(cv2.imread(path+'/' + 'cat.' + str(i) + '.jpg'), (resize, resize))
train_label[i] = 0
for i in range(5000, 10000):
if i % 2:
test_data[i-5000] = cv2.resize(cv2.imread(path+'/' + 'dog.' + str(i) + '.jpg'), (resize, resize))
test_label[i-5000] = 1
else:
test_data[i-5000] = cv2.resize(cv2.imread(path+'/' + 'cat.' + str(i) + '.jpg'), (resize, resize))
test_label[i-5000] = 0
return train_data, train_label, test_data, test_label

def vgg16():
weight_decay = 0.0005
nb_epoch = 100
batch_size = 32

# layer1
model = keras.Sequential()
model.add(layers.Conv2D(64, (3, 3), padding='same',
input_shape=(224, 224, 3), kernel_regularizer=regularizers.l2(weight_decay)))
model.add(layers.Activation('relu'))
model.add(layers.BatchNormalization())
model.add(layers.Dropout(0.3))
# layer2
model.add(layers.Conv2D(64, (3, 3), padding='same', kernel_regularizer=regularizers.l2(weight_decay)))
model.add(layers.Activation('relu'))
model.add(layers.BatchNormalization())
model.add(layers.MaxPooling2D(pool_size=(2, 2)))
# layer3
model.add(layers.Conv2D(128, (3, 3), padding='same', kernel_regularizer=regularizers.l2(weight_decay)))
model.add(layers.Activation('relu'))
model.add(layers.BatchNormalization())
model.add(layers.Dropout(0.4))
# layer4
model.add(layers.Conv2D(128, (3, 3), padding='same', kernel_regularizer=regularizers.l2(weight_decay)))
model.add(layers.Activation('relu'))
model.add(layers.BatchNormalization())
model.add(layers.MaxPooling2D(pool_size=(2, 2)))
# layer5
model.add(layers.Conv2D(256, (3, 3), padding='same', kernel_regularizer=regularizers.l2(weight_decay)))
model.add(layers.Activation('relu'))
model.add(layers.BatchNormalization())
model.add(layers.Dropout(0.4))
# layer6
model.add(layers.Conv2D(256, (3, 3), padding='same', kernel_regularizer=regularizers.l2(weight_decay)))
model.add(layers.Activation('relu'))
model.add(layers.BatchNormalization())
model.add(layers.Dropout(0.4))
# layer7
model.add(layers.Conv2D(256, (3, 3), padding='same', kernel_regularizer=regularizers.l2(weight_decay)))
model.add(layers.Activation('relu'))
model.add(layers.BatchNormalization())
model.add(layers.MaxPooling2D(pool_size=(2, 2)))
# layer8
model.add(layers.Conv2D(512, (3, 3), padding='same', kernel_regularizer=regularizers.l2(weight_decay)))
model.add(layers.Activation('relu'))
model.add(layers.BatchNormalization())
model.add(layers.Dropout(0.4))
# layer9
model.add(layers.Conv2D(512, (3, 3), padding='same', kernel_regularizer=regularizers.l2(weight_decay)))
model.add(layers.Activation('relu'))
model.add(layers.BatchNormalization())
model.add(layers.Dropout(0.4))
# layer10
model.add(layers.Conv2D(512, (3, 3), padding='same', kernel_regularizer=regularizers.l2(weight_decay)))
model.add(layers.Activation('relu'))
model.add(layers.BatchNormalization())
model.add(layers.MaxPooling2D(pool_size=(2, 2)))
# layer11
model.add(layers.Conv2D(512, (3, 3), padding='same', kernel_regularizer=regularizers.l2(weight_decay)))
model.add(layers.Activation('relu'))
model.add(layers.BatchNormalization())
model.add(layers.Dropout(0.4))
# layer12
model.add(layers.Conv2D(512, (3, 3), padding='same', kernel_regularizer=regularizers.l2(weight_decay)))
model.add(layers.Activation('relu'))
model.add(layers.BatchNormalization())
model.add(layers.Dropout(0.4))
# layer13
model.add(layers.Conv2D(512, (3, 3), padding='same', kernel_regularizer=regularizers.l2(weight_decay)))
model.add(layers.Activation('relu'))
model.add(layers.BatchNormalization())
model.add(layers.MaxPooling2D(pool_size=(2, 2)))
model.add(layers.Dropout(0.5))
# layer14
model.add(layers.Flatten())
model.add(layers.Dense(512, kernel_regularizer=regularizers.l2(weight_decay)))
model.add(layers.Activation('relu'))
model.add(layers.BatchNormalization())
# layer15
model.add(layers.Dense(512, kernel_regularizer=regularizers.l2(weight_decay)))
model.add(layers.Activation('relu'))
model.add(layers.BatchNormalization())
# layer16
model.add(layers.Dropout(0.5))
model.add(layers.Dense(2))
model.add(layers.Activation('softmax'))

return model

#if __name__ == '__main__':
train_data, train_label, test_data, test_label = load_data()
train_data = train_data.astype('float32')
test_data = test_data.astype('float32')
train_label = keras.utils.to_categorical(train_label, 2)
test_label = keras.utils.to_categorical(test_label, 2)

#定義訓練方法,超引數設定
model = vgg16()
sgd = tf.keras.optimizers.SGD(lr=0.01, decay=1e-6, momentum=0.9, nesterov=True) #設定優化器為SGD
model.compile(loss='categorical_crossentropy', optimizer=sgd, metrics=['accuracy'])
history = model.fit(train_data, train_label,
batch_size=20,
epochs=10,
validation_split=0.2, #把訓練集中的五分之一作為驗證集
shuffle=True)
scores = model.evaluate(test_data,test_label,verbose=1)
print(scores)
model.save('model/vgg16dogcat.h5')

acc = history.history['accuracy'] # 獲取訓練集準確性資料
val_acc = history.history['val_accuracy'] # 獲取驗證集準確性資料
loss = history.history['loss'] # 獲取訓練集錯誤值資料
val_loss = history.history['val_loss'] # 獲取驗證集錯誤值資料
epochs = range(1, len(acc) + 1)
plt.plot(epochs, acc, 'bo', label='Trainning acc') # 以epochs為橫座標，以訓練集準確性為縱座標
plt.plot(epochs, val_acc, 'b', label='Vaildation acc') # 以epochs為橫座標，以驗證集準確性為縱座標
plt.legend() # 繪製圖例，即標明圖中的線段代表何種含義

plt.show()

pytorch官網的程式碼：

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)
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 only specify a single number
x = F.max_pool2d(F.relu(self.conv2(x)), 2)
x = x.view(-1, self.num_flat_features(x))
x = F.relu(self.fc1(x))
x = F.relu(self.fc2(x))
x = self.fc3(x)
return x

def num_flat_features(self, x):
size = x.size()[1:] # all dimensions except the batch dimension
num_features = 1
for s in size:
num_features *= s
return num_features

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)
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