元框架(metaframework)。
TFLearn。模块化深度学习框架，更高级API，快速实验，完全透明兼容。
TFLearn实现AlexNet。
https://github.com/tflearn/tflearn/blob/master/examples/images/alexnet.py
牛津大学鲜花数据集(Flower Dataset)。~vgg/data/flowers/17/ 。提供17个类别鲜花数据，每个类别80张图片，有大量姿态、光变化。
# -*- coding: utf-8 -*-
""" AlexNet.
Applying 'Alexnet' to Oxford's 17 Category Flower Dataset classification task.
References:
- Alex Krizhevsky, Ilya Sutskever & Geoffrey E. Hinton. ImageNet
Classification with Deep Convolutional Neural Networks. NIPS, 2012.
- 17 Category Flower Dataset. Maria-Elena Nilsback and Andrew Zisserman.
Links:
- [AlexNet Paper](http://papers.nips.cc/paper/4824-imagenet-classification-with-deep-convolutional-neural-networks.pdf)
- [Flower Dataset (17)](~vgg/data/flowers/17/)
"""
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
from tflearn.layers.normalization import local_response_normalization
from tflearn.layers.estimator import regression
import tflearn.datasets.oxflower17 as oxflower17
# 加载数据
X, Y = oxflower17.load_data(one_hot=True, resize_pics=(227, 227))
# Building 'AlexNet' 构建网络模型
network = input_data(shape=[None, 227, 227, 3])
network = conv_2d(network, 96, 11, strides=4, activation='relu')
network = max_pool_2d(network, 3, strides=2)
network = local_response_normalization(network)
network = conv_2d(network, 256, 5, activation='relu')
network = max_pool_2d(network, 3, strides=2)
network = local_response_normalization(network)
network = conv_2d(network, 384, 3, activation='relu')
network = conv_2d(network, 384, 3, activation='relu')
network = conv_2d(network, 256, 3, activation='relu')
network = max_pool_2d(network, 3, strides=2)
network = local_response_normalization(network)
network = fully_connected(network, 4096, activation='tanh')
network = dropout(network, 0.5)
network = fully_connected(network, 4096, activation='tanh')
network = dropout(network, 0.5)
network = fully_connected(network, 17, activation='softmax')
network = regression(network, optimizer='momentum',
loss='categorical_crossentropy',
learning_rate=0.001)
# Training 训练模型 载入AlexNet模型检查点文件
model = tflearn.DNN(network, checkpoint_path='model_alexnet',
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='alexnet_oxflowers17')
Keras。高级Python神经网络框架。。TensorFlow默认框架。快速搭建原型。兼容Theano和TensorFlow。Keras高度封装，适合新手，代码更新快，示例代码多，文档、讨论区完善。自动调用GPU并行计算。模块化，模型神经层、成本函数、优化器、初始化、激活函数、规范化模块，组合创建模型。极简。易扩展，容易添加新模块。Python语言。
Keras模型。Keras核心数据结构是模型。模型组织网络层。Sequential模型，网络层顺序构成栈，单输入单输出，层间只有相邻关系，简单模型。Model模型建立复杂模型。
Sequential模型。加载完数据，X_train,Y_train,X_test,Y_test。构建模型：
from keras.models import Sequential
from keras.layers.core import Dense, Dropout,Activation
model = Sequential()
model.add(Dense(output_dim=64, input_dim=100))
model.add(Activation('relu'))
model.add(Dense(output_dim=10))
model.add(Activation('softmax'))
model.compile(loss='categorical_crossentropy', optimizer='sgd', metrics='accuracy')
model.fit(X_train, Y_train, batch_size=32, nb_epoch=5)
loss_and_metrics = model.evaluate(X_test, Y_test, batch_size=32)
Keras源码示例 ：CIFAR10-图片分类(CNN、实时数据)、IMDB-电影评论观点分类(LSTM)、Reuters-新闻主题分类(多层感知器)、MNIST-手写数字识别(多层感知器、CNN)、OCR-识别字符级文本生成(LSTM)。
安装。pip install keras 。选择依赖后端，~/.keras/keras.json 修改最后一行"backend":"fensorflow" 。
Keras实现卷积神经网络。
。
#!/usr/bin/python
# -*- coding:utf8 -*-
'''Trains a simple convnet on the MNIST dataset.
Gets to 99.25% test accuracy after 12 epochs
(there is still a lot of margin for parameter tuning).
16 seconds per epoch on a GRID K520 GPU.
'''
from __future__ import print_function
import keras
from keras.datasets import mnist
from keras.models import Sequential
from keras.layers import Dense, Dropout, Flatten
from keras.layers import Conv2D, MaxPooling2D
from keras import backend as K
batch_size = 128
num_classes = 10 # 分类数
epochs = 12 # 训练轮数
# input image dimensions 输入图片维度
img_rows, img_cols = 28, 28
# the data, shuffled and split between train and test sets
# 加载数据
(x_train, y_train), (x_test, y_test) = mnist.load_data()
if K.image_data_format() == 'channels_first':
#使用Theano顺序:(conv_dim1,channels,conv_dim2,conv_dim3)
x_train = x_train.reshape(x_train.shape[0], 1, img_rows, img_cols)
x_test = x_test.reshape(x_test.shape[0], 1, img_rows, img_cols)
input_shape = (1, img_rows, img_cols)
else:
#使用TensorFlow顺序:(conv_dim1conv_dim2,conv_dim3,channels,)
x_train = x_train.reshape(x_train.shape[0], img_rows, img_cols, 1)
x_test = x_test.reshape(x_test.shape[0], img_rows, img_cols, 1)
input_shape = (img_rows, img_cols, 1)
x_train = x_train.astype('float32')
x_test = x_test.astype('float32')
x_train /= 255
x_test /= 255
print('x_train shape:', x_train.shape)
print(x_train.shape[0], 'train samples')
print(x_test.shape[0], 'test samples')
# convert class vectors to binary class matrices 将类向量转换为二进制类矩阵
y_train = keras.utils.to_categorical(y_train, num_classes)
y_test = keras.utils.to_categorical(y_test, num_classes)
#模型构建:2个卷积层、1个池化层、2个全连接层
model = Sequential()
model.add(Conv2D(32, kernel_size=(3, 3),
activation='relu',
input_shape=input_shape))
model.add(Conv2D(64, (3, 3), activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.25))
model.add(Flatten())
model.add(Dense(128, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(num_classes, activation='softmax'))
# 模型编译
model.compile(loss=keras.losses.categorical_crossentropy,
optimizer=keras.optimizers.Adadelta(),
metrics=['accuracy'])
# 模型训练
model.fit(x_train, y_train,
batch_size=batch_size,
epochs=epochs,
verbose=1,
validation_data=(x_test, y_test))
# 模型评估
score = model.evaluate(x_test, y_test, verbose=0)
print('Test loss:', score[0])
print('Test accuracy:', score[1])
模型加载保存。 /blob/master/tests/test_model_saving.py 。
Keras的save_model、load_model方法将模型、权重保存到HDF5文件。包括模型结构、权重、训练配置(损失函数、优化器)。方便中断后再继续训练。
from keras.models import save_model, load_model
def test_sequential_model_saving():
model = Sequential()
model.add(Dense(2, input_shape=(3,)))
model.add(RepeatVector(3))
model.add(TimeDistributed(Dense(3)))
model.compile(loss=losses.MSE,
optimizer=optimizers.RMSprop(lr=0.0001),
metrics=[metrics.categorical_accuracy],
sample_weight_mode='temporal')
x = np.random.random((1, 3))
y = np.random.random((1, 3, 3))
model.train_on_batch(x, y)
out = model.predict(x)
_, fname = tempfile.mkstemp('.h5') # 创建HDFS 5文件
save_model(model, fname)
new_model = load_model(fname)
os.remove(fname)
out2 = new_model.predict(x)
assert_allclose(out, out2, atol=1e-05)
# test that new updates are the same with both models
# 检测新保存的模型和之前定义的模型是否一致
x = np.random.random((1, 3))
y = np.random.random((1, 3, 3))
model.train_on_batch(x, y)
new_model.train_on_batch(x, y)
out = model.predict(x)
out2 = new_model.predict(x)
assert_allclose(out, out2, atol=1e-05)
只保存模型结构。
json_string = model.to_jsion()
yaml_string = model.to_yaml()
手动编辑。
from keras.models import model_from_json
model = model_from_json(json_string)
model = model_from_yaml(yaml_string)
只保存模型权重。
model.save_weights('my_model_weights.h5')
model.load_weights('my_model_weights.h5')
参考资料：
《TensorFlow技术解析与实战》
欢迎推荐上海机器学习工作机会，我的微信：qingxingfengzi
阅读(926) | 评论(0) | 转发(0) |
