论文翻译:https://blog.csdn.net/qq_41295976/article/details/88249740
总结:https://www.jianshu.com/p/274d050d517e
代码来源:https://www.jianshu.com/p/274d050d517e
from keras.layers import *
import keras.backend as K
from keras.regularizers import l2
from keras.layers.merge import concatenate
from keras import Model
def conv_block(input, nb_filter, bottleneck=False, dropout_rate=None, weight_decay=1e-4):
''' Apply BatchNorm, Relu, 3x3 Conv2D, optional bottleneck block and dropout
Args:
input: Input keras tensor
nb_filter: number of filters
bottleneck: add bottleneck block
dropout_rate: dropout rate
weight_decay: weight decay factor
Returns: keras tensor with batch_norm, relu and convolution2d added (optional bottleneck)
'''
concat_axis = 1 if K.image_data_format() == 'channel_first' else -1 #默认的图像的维度顺序,若从未设置过,则为“channels_last
x = BatchNormalization(axis=concat_axis, epsilon=1.1e-5)(input)
x = Activation('relu')(x)
if bottleneck:
inter_channel = nb_filter * 4
x = Conv2D(inter_channel, (1, 1), kernel_initializer='he_normal', padding='same', use_bias=False,
kernel_regularizer=l2(weight_decay))(x)
x = BatchNormalization(axis=concat_axis, epsilon=1.1e-5)(x)
x = Activation('relu')(x)
x = Conv2D(nb_filter, (3, 3), kernel_initializer='he_normal', padding='same', use_bias=False)(x)
if dropout_rate:
x = Dropout(dropout_rate)(x)
return x
def transition_block(input, nb_filter, compression=1.0, weight_decay=1e-4):
'''Apply BatchNorm, ReLU, Conv2d, optional compressoin, dropout and Maxpooling2D
Args:
input: keras tensor
nb_filter: number of filters
compression: caculated as 1 - reduction. Reduces the number of features maps in the transition block
dropout_rate: dropout rate
weight_decay: weight decay factor
Returns:
keras tensor, after applying batch_norm, relu-conv, dropout, maxpool
'''
concat_axis = 1 if K.image_data_format() == 'channels_first' else -1
x = BatchNormalization(axis=concat_axis, epsilon=1.1e-5)(input)
x = Activation('relu')(x)
x = Conv2D(int(nb_filter * compression), (1, 1), kernel_initializer='he_normal', padding='same', use_bias=False,
kernel_regularizer=l2(weight_decay))(x)
x = AveragePooling2D((2, 2), strides=(2, 2))(x)
return x
def dense_block(x, nb_layers, nb_filter, growth_rate, bottleneck=False, dropout_rate=None, weight_decay=1e-4,
grow_nb_filters=True, return_concat_list=False):
'''Build a dense_block where the output of ench conv_block is fed t subsequent ones
Args:
x: keras tensor
nb_layser: the number of layers of conv_block to append to the model
nb_filter: number of filters
growth_rate: growth rate
bottleneck: bottleneck block
dropout_rate: dropout rate
weight_decay: weight decay factor
grow_nb_filters: flag to decide to allow number of filters to grow
return_concat_list: return the list of feature maps along with the actual output
Returns:
keras tensor with nb_layers of conv_block appened
'''
concat_axis = 1 if K.image_data_format() == 'channels_first' else -1
x_list = [x]
for i in range(nb_layers):
cb = conv_block(x, growth_rate, bottleneck, dropout_rate, weight_decay)
x_list.append(cb)
x = concatenate([x, cb], axis=concat_axis)
if grow_nb_filters:
nb_filter += growth_rate
if return_concat_list:
return x, nb_filter, x_list
else:
return x, nb_filter
def create_dense_net(nb_classes, img_input, include_top, depth=40, nb_dense_block=3, growth_rate=12, nb_filter=-1,
nb_layers_per_block=[1], bottleneck=False, reduction=0.0, dropout_rate=None, weight_decay=1e-4,
subsample_initial_block=False, activation='softmax'):
''' Build the DenseNet model
Args:
nb_classes: number of classes
img_input: tuple of shape (channels, rows, columns) or (rows, columns, channels)
include_top: flag to include the final Dense layer
depth: number or layers
nb_dense_block: number of dense blocks to add to end (generally = 3)
growth_rate: number of filters to add per dense block
nb_filter: initial number of filters. Default -1 indicates initial number of filters is 2 * growth_rate
nb_layers_per_block: list, number of layers in each dense block
bottleneck: add bottleneck blocks
reduction: reduction factor of transition blocks. Note : reduction value is inverted to compute compression
dropout_rate: dropout rate
weight_decay: weight decay rate
subsample_initial_block: Set to True to subsample the initial convolution and
add a MaxPool2D before the dense blocks are added.
subsample_initial:
activation: Type of activation at the top layer. Can be one of 'softmax' or 'sigmoid'.
Note that if sigmoid is used, classes must be 1.
Returns: keras tensor with nb_layers of conv_block appended
'''
concat_axis = 1 if K.image_data_format() == 'channel_first' else -1
if type(nb_layers_per_block) is not list:
print('nb_layers_per_block should be a list!!!')
return 0
final_nb_layer = nb_layers_per_block[-1]
nb_layers = nb_layers_per_block[:-1]
if nb_filter <= 0:
nb_filter = 2 * growth_rate
compression = 1.0 - reduction
if subsample_initial_block:
initial_kernel = (7, 7)
initial_strides = (2, 2)
else:
initial_kernel = (3, 3)
initial_strides = (1, 1)
x = Conv2D(nb_filter, initial_kernel, kernel_initializer='he_normal', padding='same',
strides=initial_strides, use_bias=False, kernel_regularizer=l2(weight_decay))(img_input)
if subsample_initial_block:
x = BatchNormalization(axis=concat_axis, epsilon=1.1e-5)(x)
x = Activation('relu')(x)
x = MaxPooling2D((3, 3), strides=(2, 2), padding='same')(x)
for block_index in range(nb_dense_block - 1):
x, nb_filter = dense_block(x, nb_layers[block_index], nb_filter, growth_rate, bottleneck=bottleneck,
dropout_rate=dropout_rate, weight_decay=weight_decay)
x = transition_block(x, nb_filter, compression=compression, weight_decay=weight_decay)
nb_filter = int(nb_filter * compression)
# 最后一个block没有transition_block
x, nb_filter = dense_block(x, final_nb_layer, nb_filter, growth_rate, bottleneck=bottleneck,
dropout_rate=dropout_rate, weight_decay=weight_decay)
x = BatchNormalization(axis=concat_axis, epsilon=1.1e-5)(x)
x = Activation('relu')(x)
x = GlobalAveragePooling2D()(x)
if include_top:
x = Dense(nb_classes, activation=activation)(x)
return x
import matplotlib.pyplot as plt
import pickle
from keras.preprocessing import image
from PIL import Image
from sklearn.model_selection import train_test_split
import numpy as np
from keras import optimizers
def load_file(filename):
with open(filename, 'rb') as fo:
data = pickle.load(fo, encoding='latin1')
return data
def get_data():
data = load_file('test_batch')
img = data['data']
img = np.reshape(img, (-1, 3, 32, 32 )) # 只是测试,没有采用循环导出全部图像,这里导出第10幅图
imgs = np.zeros((n_size,64,64,3))
for i in range(n_size):
r = img[i][0]
g = img[i][1]
b = img[i][2]
ir = Image.fromarray(r)
ig = Image.fromarray(g)
ib = Image.fromarray(b)
temp = Image.merge("RGB", (ir, ig, ib))
temp = temp.resize((64,64))
imgs[i] = temp
imgs = imgs.astype(np.int)
labels = np.zeros((n_size,10))
for i, lb in enumerate(data['labels'][:n_size]):
labels[i][lb] = 1
return imgs,labels
n_size = 5000
input_shape = (64,64,3)
if __name__ == '__main__':
X,Y = get_data()
X_train, X_vaild, y_train, y_vaild = train_test_split(X, Y, test_size=0.2)
inputs = Input(shape=input_shape)
# inputs = Input(shape=input_shape)
x = create_dense_net(nb_classes=10, img_input=inputs, include_top=True, depth=169, nb_dense_block=4,
growth_rate=32, nb_filter=64, nb_layers_per_block=[6, 12, 32, 32], bottleneck=True, reduction=0.5,
dropout_rate=0.0, weight_decay=1e-4, subsample_initial_block=True, activation='softmax')
model = Model(inputs, x, name='densenet169')#output = x
sgd = optimizers.SGD(lr=0.05, decay=1e-6, momentum=0.9, nesterov=True)
model.compile(loss='mean_squared_error', optimizer=sgd,metrics=['accuracy'])
h = model.fit(X_train, y_train, epochs=12, batch_size=64)
preds = model.evaluate(X_vaild, y_vaild)
print('Loss = ' + str(preds[0]))
print('Test Accuracy =' + str(preds[1]))
#
print(h.history)
plt.figure(figsize=[10, 4])
plt.subplot(1, 2, 1)
plt.plot(h.history['loss'])
# plt.plot(h.history['val_loss'])
# plt.legend(['loss', 'val_loss'])
plt.ylabel('loss')
# plt.xlabel('epoch')
plt.subplot(1, 2, 2)
plt.plot(h.history['acc'])
# plt.plot(h.history['val_acc'])
# plt.legend(['acc', 'val_acc'])
plt.ylabel('acc')
plt.xlabel('epoch')
plt.show()