TensorFlow学习日记19_deep residual network. applying a deep residual ne-CSDN博客

本文链接：https://blog.csdn.net/ssw_1990/article/details/78408398

1. Highway Network

解析：

# -*- coding: utf-8 -*-
""" Deep Neural Network for MNIST dataset classification task using 
a highway network
"""
from __future__ import division, print_function, absolute_import

import tflearn

# Data loading and preprocessing
import tflearn.datasets.mnist as mnist

X, Y, testX, testY = mnist.load_data(one_hot=True)

# Building deep neural network
input_layer = tflearn.input_data(shape=[None, 784])
dense1 = tflearn.fully_connected(input_layer, 64, activation='elu',
                                 regularizer='L2', weight_decay=0.001)

# install a deep network of highway layers
highway = dense1
for i in range(10):
    highway = tflearn.highway(highway, 64, activation='elu',
                              regularizer='L2', weight_decay=0.001, transform_dropout=0.8)

softmax = tflearn.fully_connected(highway, 10, activation='softmax')

# Regression using SGD with learning rate decay and Top-3 accuracy
sgd = tflearn.SGD(learning_rate=0.1, lr_decay=0.96, decay_step=1000)
top_k = tflearn.metrics.Top_k(3)
net = tflearn.regression(softmax, optimizer=sgd, metric=top_k,
                         loss='categorical_crossentropy')

# Training
model = tflearn.DNN(net, tensorboard_verbose=0)
model.fit(X, Y, n_epoch=20, validation_set=(testX, testY),
          show_metric=True, run_id="highway_dense_model")

2. Highway Convolutional Network

解析：

# -*- coding: utf-8 -*-
""" Convolutional Neural Network for MNIST dataset classification task.
"""

from __future__ import division, print_function, absolute_import

import tflearn
from tflearn.layers.core import input_data, dropout, fully_connected
from tflearn.layers.conv import highway_conv_2d, max_pool_2d
from tflearn.layers.normalization import local_response_normalization, batch_normalization
from tflearn.layers.estimator import regression

# Data loading and preprocessing
import tflearn.datasets.mnist as mnist

X, Y, testX, testY = mnist.load_data(one_hot=True)
X = X.reshape([-1, 28, 28, 1])
testX = testX.reshape([-1, 28, 28, 1])

# Building convolutional network
network = input_data(shape=[None, 28, 28, 1], name='input')
# highway convolutions with pooling and dropout
for i in range(3):
    for j in [3, 2, 1]:
        network = highway_conv_2d(network, 16, j, activation='elu')
    network = max_pool_2d(network, 2)
    network = batch_normalization(network)

network = fully_connected(network, 128, activation='elu')
network = fully_connected(network, 256, activation='elu')
network = fully_connected(network, 10, activation='softmax')
network = regression(network, optimizer='adam', learning_rate=0.01,
                     loss='categorical_crossentropy', name='target')

# Training
model = tflearn.DNN(network, tensorboard_verbose=0)
model.fit(X, Y, n_epoch=20, validation_set=(testX, testY),
          show_metric=True, run_id='convnet_highway_mnist')

3. Residual Network (MNIST)

解析：

# -*- coding: utf-8 -*-
"""
Applying a Deep Residual Network to MNIST Dataset classification task.
"""

from __future__ import division, print_function, absolute_import

import tflearn
import tflearn.data_utils as du

# Data loading and preprocessing
import tflearn.datasets.mnist as mnist

X, Y, testX, testY = mnist.load_data(one_hot=True)
X = X.reshape([-1, 28, 28, 1])
testX = testX.reshape([-1, 28, 28, 1])
X, mean = du.featurewise_zero_center(X)
testX = du.featurewise_zero_center(testX, mean)

# Building Residual Network
net = tflearn.input_data(shape=[None, 28, 28, 1])
net = tflearn.conv_2d(net, 64, 3, activation='relu', bias=False)
# Residual blocks
net = tflearn.residual_bottleneck(net, 3, 16, 64)
net = tflearn.residual_bottleneck(net, 1, 32, 128, downsample=True)
net = tflearn.residual_bottleneck(net, 2, 32, 128)
net = tflearn.residual_bottleneck(net, 1, 64, 256, downsample=True)
net = tflearn.residual_bottleneck(net, 2, 64, 256)
net = tflearn.batch_normalization(net)
net = tflearn.activation(net, 'relu')
net = tflearn.global_avg_pool(net)
# Regression
net = tflearn.fully_connected(net, 10, activation='softmax')
net = tflearn.regression(net, optimizer='momentum',
                         loss='categorical_crossentropy',
                         learning_rate=0.1)
# Training
model = tflearn.DNN(net, checkpoint_path='model_resnet_mnist',
                    max_checkpoints=10, tensorboard_verbose=0)
model.fit(X, Y, n_epoch=100, validation_set=(testX, testY),
          show_metric=True, batch_size=256, run_id='resnet_mnist')

4. Residual Network (CIFAR-10)

解析：

# -*- coding: utf-8 -*-
"""
Applying a Deep Residual Network to CIFAR-10 Dataset classification task.
"""

from __future__ import division, print_function, absolute_import

import tflearn

# Residual blocks
# 32 layers: n=5, 56 layers: n=9, 110 layers: n=18
n = 5

# Data loading
from tflearn.datasets import cifar10

(X, Y), (testX, testY) = cifar10.load_data()
Y = tflearn.data_utils.to_categorical(Y)
testY = tflearn.data_utils.to_categorical(testY)

# Real-time data preprocessing
img_prep = tflearn.ImagePreprocessing()
img_prep.add_featurewise_zero_center(per_channel=True)

# Real-time data augmentation
img_aug = tflearn.ImageAugmentation()
img_aug.add_random_flip_leftright()
img_aug.add_random_crop([32, 32], padding=4)

# Building Residual Network
net = tflearn.input_data(shape=[None, 32, 32, 3],
                         data_preprocessing=img_prep,
                         data_augmentation=img_aug)
net = tflearn.conv_2d(net, 16, 3, regularizer='L2', weight_decay=0.0001)
net = tflearn.residual_block(net, n, 16)
net = tflearn.residual_block(net, 1, 32, downsample=True)
net = tflearn.residual_block(net, n - 1, 32)
net = tflearn.residual_block(net, 1, 64, downsample=True)
net = tflearn.residual_block(net, n - 1, 64)
net = tflearn.batch_normalization(net)
net = tflearn.activation(net, 'relu')
net = tflearn.global_avg_pool(net)
# Regression
net = tflearn.fully_connected(net, 10, activation='softmax')
mom = tflearn.Momentum(0.1, lr_decay=0.1, decay_step=32000, staircase=True)
net = tflearn.regression(net, optimizer=mom,
                         loss='categorical_crossentropy')
# Training
model = tflearn.DNN(net, checkpoint_path='model_resnet_cifar10',
                    max_checkpoints=10, tensorboard_verbose=0,
                    clip_gradients=0.)

model.fit(X, Y, n_epoch=200, validation_set=(testX, testY),
          snapshot_epoch=False, snapshot_step=500,
          show_metric=True, batch_size=128, shuffle=True,
          run_id='resnet_cifar10')

5. ResNeXt

解析：

# -*- coding: utf-8 -*-
"""
Applying a 'ResNeXT' to CIFAR-10 Dataset classification task.
"""

from __future__ import division, print_function, absolute_import

import tflearn

# Residual blocks
# 32 layers: n=5, 56 layers: n=9, 110 layers: n=18
n = 5

# Data loading
from tflearn.datasets import cifar10

(X, Y), (testX, testY) = cifar10.load_data()
Y = tflearn.data_utils.to_categorical(Y)
testY = tflearn.data_utils.to_categorical(testY)

# Real-time data preprocessing
img_prep = tflearn.ImagePreprocessing()
img_prep.add_featurewise_zero_center(per_channel=True)

# Real-time data augmentation
img_aug = tflearn.ImageAugmentation()
img_aug.add_random_flip_leftright()
img_aug.add_random_crop([32, 32], padding=4)

# Building Residual Network
net = tflearn.input_data(shape=[None, 32, 32, 3],
                         data_preprocessing=img_prep,
                         data_augmentation=img_aug)
net = tflearn.conv_2d(net, 16, 3, regularizer='L2', weight_decay=0.0001)
net = tflearn.resnext_block(net, n, 16, 32)
net = tflearn.resnext_block(net, 1, 32, 32, downsample=True)
net = tflearn.resnext_block(net, n - 1, 32, 32)
net = tflearn.resnext_block(net, 1, 64, 32, downsample=True)
net = tflearn.resnext_block(net, n - 1, 64, 32)
net = tflearn.batch_normalization(net)
net = tflearn.activation(net, 'relu')
net = tflearn.global_avg_pool(net)
# Regression
net = tflearn.fully_connected(net, 10, activation='softmax')
opt = tflearn.Momentum(0.1, lr_decay=0.1, decay_step=32000, staircase=True)
net = tflearn.regression(net, optimizer=opt,
                         loss='categorical_crossentropy')
# Training
model = tflearn.DNN(net, checkpoint_path='model_resnext_cifar10',
                    max_checkpoints=10, tensorboard_verbose=0,
                    clip_gradients=0.)

model.fit(X, Y, n_epoch=200, validation_set=(testX, testY),
          snapshot_epoch=False, snapshot_step=500,
          show_metric=True, batch_size=128, shuffle=True,
          run_id='resnext_cifar10')

6. DenseNet

解析：

# -*- coding: utf-8 -*-
"""
Applying a 'DenseNet' to CIFAR-10 Dataset classification task.
"""

from __future__ import division, print_function, absolute_import

import tflearn

# Growth Rate (12, 16, 32, ...)
k = 12

# Depth (40, 100, ...)
L = 40
nb_layers = int((L - 4) / 3)

# Data loading
from tflearn.datasets import cifar10

(X, Y), (testX, testY) = cifar10.load_data()
Y = tflearn.data_utils.to_categorical(Y)
testY = tflearn.data_utils.to_categorical(testY)

# Real-time data preprocessing
img_prep = tflearn.ImagePreprocessing()
img_prep.add_featurewise_zero_center(per_channel=True)

# Real-time data augmentation
img_aug = tflearn.ImageAugmentation()
img_aug.add_random_flip_leftright()
img_aug.add_random_crop([32, 32], padding=4)

# Building Residual Network
net = tflearn.input_data(shape=[None, 32, 32, 3],
                         data_preprocessing=img_prep,
                         data_augmentation=img_aug)
net = tflearn.conv_2d(net, 16, 3, regularizer='L2', weight_decay=0.0001)
net = tflearn.densenet_block(net, nb_layers, k)
net = tflearn.densenet_block(net, nb_layers, k)
net = tflearn.densenet_block(net, nb_layers, k)
net = tflearn.global_avg_pool(net)

# Regression
net = tflearn.fully_connected(net, 10, activation='softmax')
opt = tflearn.Nesterov(0.1, lr_decay=0.1, decay_step=32000, staircase=True)
net = tflearn.regression(net, optimizer=opt,
                         loss='categorical_crossentropy')
# Training
model = tflearn.DNN(net, checkpoint_path='model_densenet_cifar10',
                    max_checkpoints=10, tensorboard_verbose=0,
                    clip_gradients=0.)

model.fit(X, Y, n_epoch=200, validation_set=(testX, testY),
          snapshot_epoch=False, snapshot_step=500,
          show_metric=True, batch_size=128, shuffle=True,
          run_id='densenet_cifar10')

7. Google Inception (v3)

解析：

# -*- coding: utf-8 -*-
"""
Applying 'GoogLeNet' to Oxford's 17 Category Flower Dataset classification task.
"""

from __future__ import division, print_function, absolute_import

import tflearn
from tflearn.layers.core import input_data, dropout, fully_connected
from tflearn.layers.conv import conv_2d, max_pool_2d, avg_pool_2d
from tflearn.layers.normalization import local_response_normalization
from tflearn.layers.merge_ops import merge
from tflearn.layers.estimator import regression

import tflearn.datasets.oxflower17 as oxflower17

X, Y = oxflower17.load_data(one_hot=True, resize_pics=(227, 227))

network = input_data(shape=[None, 227, 227, 3])
conv1_7_7 = conv_2d(network, 64, 7, strides=2, activation='relu', name='conv1_7_7_s2')
pool1_3_3 = max_pool_2d(conv1_7_7, 3, strides=2)
pool1_3_3 = local_response_normalization(pool1_3_3)
conv2_3_3_reduce = conv_2d(pool1_3_3, 64, 1, activation='relu', name='conv2_3_3_reduce')
conv2_3_3 = conv_2d(conv2_3_3_reduce, 192, 3, activation='relu', name='conv2_3_3')
conv2_3_3 = local_response_normalization(conv2_3_3)
pool2_3_3 = max_pool_2d(conv2_3_3, kernel_size=3, strides=2, name='pool2_3_3_s2')

# 3a
inception_3a_1_1 = conv_2d(pool2_3_3, 64, 1, activation='relu', name='inception_3a_1_1')
inception_3a_3_3_reduce = conv_2d(pool2_3_3, 96, 1, activation='relu', name='inception_3a_3_3_reduce')
inception_3a_3_3 = conv_2d(inception_3a_3_3_reduce, 128, filter_size=3, activation='relu', name='inception_3a_3_3')
inception_3a_5_5_reduce = conv_2d(pool2_3_3, 16, filter_size=1, activation='relu', name='inception_3a_5_5_reduce')
inception_3a_5_5 = conv_2d(inception_3a_5_5_reduce, 32, filter_size=5, activation='relu', name='inception_3a_5_5')
inception_3a_pool = max_pool_2d(pool2_3_3, kernel_size=3, strides=1, name='inception_3a_pool')
inception_3a_pool_1_1 = conv_2d(inception_3a_pool, 32, filter_size=1, activation='relu', name='inception_3a_pool_1_1')
inception_3a_output = merge([inception_3a_1_1, inception_3a_3_3, inception_3a_5_5, inception_3a_pool_1_1],
                            mode='concat', axis=3)

# 3b
inception_3b_1_1 = conv_2d(inception_3a_output, 128, filter_size=1, activation='relu', name='inception_3b_1_1')
inception_3b_3_3_reduce = conv_2d(inception_3a_output, 128, filter_size=1, activation='relu',
                                  name='inception_3b_3_3_reduce')
inception_3b_3_3 = conv_2d(inception_3b_3_3_reduce, 192, filter_size=3, activation='relu', name='inception_3b_3_3')
inception_3b_5_5_reduce = conv_2d(inception_3a_output, 32, filter_size=1, activation='relu',
                                  name='inception_3b_5_5_reduce')
inception_3b_5_5 = conv_2d(inception_3b_5_5_reduce, 96, filter_size=5, name='inception_3b_5_5')
inception_3b_pool = max_pool_2d(inception_3a_output, kernel_size=3, strides=1, name='inception_3b_pool')
inception_3b_pool_1_1 = conv_2d(inception_3b_pool, 64, filter_size=1, activation='relu', name='inception_3b_pool_1_1')
inception_3b_output = merge([inception_3b_1_1, inception_3b_3_3, inception_3b_5_5, inception_3b_pool_1_1],
                            mode='concat', axis=3, name='inception_3b_output')
pool3_3_3 = max_pool_2d(inception_3b_output, kernel_size=3, strides=2, name='pool3_3_3')

# 4a
inception_4a_1_1 = conv_2d(pool3_3_3, 192, filter_size=1, activation='relu', name='inception_4a_1_1')
inception_4a_3_3_reduce = conv_2d(pool3_3_3, 96, filter_size=1, activation='relu', name='inception_4a_3_3_reduce')
inception_4a_3_3 = conv_2d(inception_4a_3_3_reduce, 208, filter_size=3, activation='relu', name='inception_4a_3_3')
inception_4a_5_5_reduce = conv_2d(pool3_3_3, 16, filter_size=1, activation='relu', name='inception_4a_5_5_reduce')
inception_4a_5_5 = conv_2d(inception_4a_5_5_reduce, 48, filter_size=5, activation='relu', name='inception_4a_5_5')
inception_4a_pool = max_pool_2d(pool3_3_3, kernel_size=3, strides=1, name='inception_4a_pool')
inception_4a_pool_1_1 = conv_2d(inception_4a_pool, 64, filter_size=1, activation='relu', name='inception_4a_pool_1_1')
inception_4a_output = merge([inception_4a_1_1, inception_4a_3_3, inception_4a_5_5, inception_4a_pool_1_1],
                            mode='concat', axis=3, name='inception_4a_output')

# 4b
inception_4b_1_1 = conv_2d(inception_4a_output, 160, filter_size=1, activation='relu', name='inception_4a_1_1')
inception_4b_3_3_reduce = conv_2d(inception_4a_output, 112, filter_size=1, activation='relu',
                                  name='inception_4b_3_3_reduce')
inception_4b_3_3 = conv_2d(inception_4b_3_3_reduce, 224, filter_size=3, activation='relu', name='inception_4b_3_3')
inception_4b_5_5_reduce = conv_2d(inception_4a_output, 24, filter_size=1, activation='relu',
                                  name='inception_4b_5_5_reduce')
inception_4b_5_5 = conv_2d(inception_4b_5_5_reduce, 64, filter_size=5, activation='relu', name='inception_4b_5_5')
inception_4b_pool = max_pool_2d(inception_4a_output, kernel_size=3, strides=1, name='inception_4b_pool')
inception_4b_pool_1_1 = conv_2d(inception_4b_pool, 64, filter_size=1, activation='relu', name='inception_4b_pool_1_1')
inception_4b_output = merge([inception_4b_1_1, inception_4b_3_3, inception_4b_5_5, inception_4b_pool_1_1],
                            mode='concat', axis=3, name='inception_4b_output')

# 4c
inception_4c_1_1 = conv_2d(inception_4b_output, 128, filter_size=1, activation='relu', name='inception_4c_1_1')
inception_4c_3_3_reduce = conv_2d(inception_4b_output, 128, filter_size=1, activation='relu',
                                  name='inception_4c_3_3_reduce')
inception_4c_3_3 = conv_2d(inception_4c_3_3_reduce, 256, filter_size=3, activation='relu', name='inception_4c_3_3')
inception_4c_5_5_reduce = conv_2d(inception_4b_output, 24, filter_size=1, activation='relu',
                                  name='inception_4c_5_5_reduce')
inception_4c_5_5 = conv_2d(inception_4c_5_5_reduce, 64, filter_size=5, activation='relu', name='inception_4c_5_5')
inception_4c_pool = max_pool_2d(inception_4b_output, kernel_size=3, strides=1)
inception_4c_pool_1_1 = conv_2d(inception_4c_pool, 64, filter_size=1, activation='relu', name='inception_4c_pool_1_1')
inception_4c_output = merge([inception_4c_1_1, inception_4c_3_3, inception_4c_5_5, inception_4c_pool_1_1],
                            mode='concat', axis=3, name='inception_4c_output')

# 4d
inception_4d_1_1 = conv_2d(inception_4c_output, 112, filter_size=1, activation='relu', name='inception_4d_1_1')
inception_4d_3_3_reduce = conv_2d(inception_4c_output, 144, filter_size=1, activation='relu',
                                  name='inception_4d_3_3_reduce')
inception_4d_3_3 = conv_2d(inception_4d_3_3_reduce, 288, filter_size=3, activation='relu', name='inception_4d_3_3')
inception_4d_5_5_reduce = conv_2d(inception_4c_output, 32, filter_size=1, activation='relu',
                                  name='inception_4d_5_5_reduce')
inception_4d_5_5 = conv_2d(inception_4d_5_5_reduce, 64, filter_size=5, activation='relu', name='inception_4d_5_5')
inception_4d_pool = max_pool_2d(inception_4c_output, kernel_size=3, strides=1, name='inception_4d_pool')
inception_4d_pool_1_1 = conv_2d(inception_4d_pool, 64, filter_size=1, activation='relu', name='inception_4d_pool_1_1')
inception_4d_output = merge([inception_4d_1_1, inception_4d_3_3, inception_4d_5_5, inception_4d_pool_1_1],
                            mode='concat', axis=3, name='inception_4d_output')

# 4e
inception_4e_1_1 = conv_2d(inception_4d_output, 256, filter_size=1, activation='relu', name='inception_4e_1_1')
inception_4e_3_3_reduce = conv_2d(inception_4d_output, 160, filter_size=1, activation='relu',
                                  name='inception_4e_3_3_reduce')
inception_4e_3_3 = conv_2d(inception_4e_3_3_reduce, 320, filter_size=3, activation='relu', name='inception_4e_3_3')
inception_4e_5_5_reduce = conv_2d(inception_4d_output, 32, filter_size=1, activation='relu',
                                  name='inception_4e_5_5_reduce')
inception_4e_5_5 = conv_2d(inception_4e_5_5_reduce, 128, filter_size=5, activation='relu', name='inception_4e_5_5')
inception_4e_pool = max_pool_2d(inception_4d_output, kernel_size=3, strides=1, name='inception_4e_pool')
inception_4e_pool_1_1 = conv_2d(inception_4e_pool, 128, filter_size=1, activation='relu', name='inception_4e_pool_1_1')
inception_4e_output = merge([inception_4e_1_1, inception_4e_3_3, inception_4e_5_5, inception_4e_pool_1_1], axis=3,
                            mode='concat')
pool4_3_3 = max_pool_2d(inception_4e_output, kernel_size=3, strides=2, name='pool_3_3')

# 5a
inception_5a_1_1 = conv_2d(pool4_3_3, 256, filter_size=1, activation='relu', name='inception_5a_1_1')
inception_5a_3_3_reduce = conv_2d(pool4_3_3, 160, filter_size=1, activation='relu', name='inception_5a_3_3_reduce')
inception_5a_3_3 = conv_2d(inception_5a_3_3_reduce, 320, filter_size=3, activation='relu', name='inception_5a_3_3')
inception_5a_5_5_reduce = conv_2d(pool4_3_3, 32, filter_size=1, activation='relu', name='inception_5a_5_5_reduce')
inception_5a_5_5 = conv_2d(inception_5a_5_5_reduce, 128, filter_size=5, activation='relu', name='inception_5a_5_5')
inception_5a_pool = max_pool_2d(pool4_3_3, kernel_size=3, strides=1, name='inception_5a_pool')
inception_5a_pool_1_1 = conv_2d(inception_5a_pool, 128, filter_size=1, activation='relu', name='inception_5a_pool_1_1')
inception_5a_output = merge([inception_5a_1_1, inception_5a_3_3, inception_5a_5_5, inception_5a_pool_1_1], axis=3,
                            mode='concat')

# 5b
inception_5b_1_1 = conv_2d(inception_5a_output, 384, filter_size=1, activation='relu', name='inception_5b_1_1')
inception_5b_3_3_reduce = conv_2d(inception_5a_output, 192, filter_size=1, activation='relu',
                                  name='inception_5b_3_3_reduce')
inception_5b_3_3 = conv_2d(inception_5b_3_3_reduce, 384, filter_size=3, activation='relu', name='inception_5b_3_3')
inception_5b_5_5_reduce = conv_2d(inception_5a_output, 48, filter_size=1, activation='relu',
                                  name='inception_5b_5_5_reduce')
inception_5b_5_5 = conv_2d(inception_5b_5_5_reduce, 128, filter_size=5, activation='relu', name='inception_5b_5_5')
inception_5b_pool = max_pool_2d(inception_5a_output, kernel_size=3, strides=1, name='inception_5b_pool')
inception_5b_pool_1_1 = conv_2d(inception_5b_pool, 128, filter_size=1, activation='relu', name='inception_5b_pool_1_1')
inception_5b_output = merge([inception_5b_1_1, inception_5b_3_3, inception_5b_5_5, inception_5b_pool_1_1], axis=3,
                            mode='concat')
pool5_7_7 = avg_pool_2d(inception_5b_output, kernel_size=7, strides=1)
pool5_7_7 = dropout(pool5_7_7, 0.4)

# fc
loss = fully_connected(pool5_7_7, 17, activation='softmax')
network = regression(loss, optimizer='momentum',
                     loss='categorical_crossentropy',
                     learning_rate=0.001)

# to train
model = tflearn.DNN(network, checkpoint_path='model_googlenet',
                    max_checkpoints=1, tensorboard_verbose=2)

model.fit(X, Y, n_epoch=1000, validation_set=0.1, shuffle=True,
          show_metric=True, batch_size=64, snapshot_step=200,
          snapshot_epoch=False, run_id='googlenet_oxflowers17')

参考文献：
[1] TFLearn Examples：https://github.com/tflearn/tflearn/tree/master/examples