1. Compile
在训练模型之前，我们需要通过compile来对学习过程进行配置。compile接收三个参数：
优化器optimizer
该参数可指定为已预定义的优化器名，如rmsprop、adagrad，或一个Optimizer类的对象，详情见optimizers损失函数loss
该参数为模型试图最小化的目标函数，它可为预定义的损失函数名，如categorical_crossentropy、mse，也可以为一个损失函数。详情见losses指标列表metrics
对分类问题，我们一般将该列表设置为metrics=['accuracy']。指标可以是一个预定义指标的名字,也可以是一个用户定制的函数.指标函数应该返回单个张量,或一个完成metric_name - > metric_value映射的字典.请参考性能评估.
# 多分类问题
model.compile(optimizer='rmsprop',
loss='categorical_crossentropy',
metrics=['accuracy'])
# 二分类问题
model.compile(optimizer='rmsprop',
loss='binary_crossentropy',
metrics=['accuracy'])
# 回归问题
model.compile(optimizer='rmsprop',
loss='mse')
# 自定义metrics
import keras.backend as K
def mean_pred(y_true, y_pred):
return K.mean(y_pred)
model.compile(optimizer='rmsprop',
loss='binary_crossentropy',
metrics=['accuracy', mean_pred])
2. Fit
# 构建与编译模型
model = Sequential()
model.add(Dense(32, activation='relu', input_dim=100))
model.add(Dense(1, activation='sigmoid'))
model.compile(optimizer='rmsprop',
loss='binary_crossentropy',
metrics=['accuracy'])
# 查出数据
import numpy as np
data = np.random.random((1000, 100))
labels = np.random.randint(2, size=(1000, 1))
# 训练与数据拟合
model.fit(data, labels, epochs=10, batch_size=32)
def generate_arrays_from_file(path):
while 1:
f = open(path)
for line in f:
x, y = process_line(line)
img = load_images(x)
yield (img, y)
f.close()
model.fit_generator(generate_arrays_from_file('/my_file.txt'),
samples_per_epoch=10000, nb_epoch=10)
3. Case
from keras.models import Sequential
from keras.layers import Dense, Dropout, Activation
from keras.optimizers import SGD
# Generate dummy data
import numpy as np
x_train = np.random.random((1000, 20))
y_train = keras.utils.to_categorical(np.random.randint(10, size=(1000, 1)), num_classes=10)
x_test = np.random.random((100, 20))
y_test = keras.utils.to_categorical(np.random.randint(10, size=(100, 1)), num_classes=10)
model = Sequential()
model.add(Dense(64, activation='relu', input_dim=20))
model.add(Dropout(0.5))
model.add(Dense(64, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(10, activation='softmax'))
sgd = SGD(lr=0.01, decay=1e-6, momentum=0.9, nesterov=True)
model.compile(loss='categorical_crossentropy',
optimizer=sgd,
metrics=['accuracy'])
model.fit(x_train, y_train,
epochs=20,
batch_size=128)
score = model.evaluate(x_test, y_test, batch_size=128)
import numpy as np
import keras
from keras.models import Sequential
from keras.layers import Dense, Dropout, Flatten
from keras.layers import Conv2D, MaxPooling2D
from keras.optimizers import SGD
x_train = np.random.random((100, 100, 100, 3))
y_train = keras.utils.to_categorical(np.random.randint(10, size=(100, 1)), num_classes=10)
x_test = np.random.random((20, 100, 100, 3))
y_test = keras.utils.to_categorical(np.random.randint(10, size=(20, 1)), num_classes=10)
model = Sequential()
# input: 100x100 images with 3 channels -> (100, 100, 3) tensors.
# this applies 32 convolution filters of size 3x3 each.
model.add(Conv2D(32, (3, 3), activation='relu', input_shape=(100, 100, 3)))
model.add(Conv2D(32, (3, 3), activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.25))
model.add(Conv2D(64, (3, 3), activation='relu'))
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(256, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(10, activation='softmax'))
sgd = SGD(lr=0.01, decay=1e-6, momentum=0.9, nesterov=True)
model.compile(loss='categorical_crossentropy', optimizer=sgd)
model.fit(x_train, y_train, batch_size=32, epochs=10)
score = model.evaluate(x_test, y_test, batch_size=32)
from keras.models import Sequential
from keras.layers import Dense, Dropout
from keras.layers import Embedding
from keras.layers import LSTM
model = Sequential()
model.add(Embedding(max_features, output_dim=256))
model.add(LSTM(128))
model.add(Dropout(0.5))
model.add(Dense(1, activation='sigmoid'))
model.compile(loss='binary_crossentropy',
optimizer='rmsprop',
metrics=['accuracy'])
model.fit(x_train, y_train, batch_size=16, epochs=10)
score = model.evaluate(x_test, y_test, batch_size=16)
4. functional
Keras函数式模型接口是用户定义多输出模型、非循环有向模型或具有共享层的模型等复杂模型的途径。一句话，只要你的模型不是类似VGG一样一条路走到黑的模型，或者你的模型需要多于一个的输出，那么你总应该选择函数式模型。函数式模型是最广泛的一类模型，序贯模型（Sequential）只是它的一种特殊情况。因为序贯模型是函数式模型的一个特例，所以我们从一个简单的序贯模型开始，看看函数式模型是如何完成的。
from keras.layers import Input, Dense
from keras.models import Model
inputs = Input(shape=(784,))
x = Dense(64, activation='relu')(inputs)
x = Dense(64, activation='relu')(x)
predictions = Dense(10, activation='softmax')(x)
model = Model(inputs=inputs, outputs=predictions)
model.compile(optimizer='rmsprop',
loss='categorical_crossentropy',
metrics=['accuracy'])
model.fit(data, labels)
使用函数式模型的一个典型场景是搭建多输入、多输出的模型。考虑这样一个模型。
from keras.layers import Input, Embedding, LSTM, Dense
from keras.models import Model
# Headline input: meant to receive sequences of 100 integers, between 1 and 10000.
# Note that we can name any layer by passing it a "name" argument.
main_input = Input(shape=(100,), dtype='int32', name='main_input')
# This embedding layer will encode the input sequence
# into a sequence of dense 512-dimensional vectors.
x = Embedding(output_dim=512, input_dim=10000, input_length=100)(main_input)
# A LSTM will transform the vector sequence into a single vector,
# containing information about the entire sequence
lstm_out = LSTM(32)(x)
auxiliary_output = Dense(1, activation='sigmoid', name='aux_output')(lstm_out)
auxiliary_input = Input(shape=(5,), name='aux_input')
x = keras.layers.concatenate([lstm_out, auxiliary_input])
# We stack a deep densely-connected network on top
x = Dense(64, activation='relu')(x)
x = Dense(64, activation='relu')(x)
x = Dense(64, activation='relu')(x)
# And finally we add the main logistic regression layer
main_output = Dense(1, activation='sigmoid', name='main_output')(x)
model = Model(inputs=[main_input, auxiliary_input], outputs=[main_output, auxiliary_output])
model.compile(optimizer='rmsprop', loss='binary_crossentropy',
loss_weights=[1., 0.2])
model.fit([headline_data, additional_data], [labels, labels],
epochs=50, batch_size=32)
model.compile(optimizer='rmsprop',
loss={'main_output': 'binary_crossentropy', 'aux_output': 'binary_crossentropy'},
loss_weights={'main_output': 1., 'aux_output': 0.2})
# And trained it via:
model.fit({'main_input': headline_data, 'aux_input': additional_data},
{'main_output': labels, 'aux_output': labels},
epochs=50, batch_size=32)
4.1 VGG
from keras.layers import Conv2D, MaxPooling2D, Input
input_img = Input(shape=(3, 256, 256))
tower_1 = Conv2D(64, (1, 1), padding='same', activation='relu')(input_img)
tower_1 = Conv2D(64, (3, 3), padding='same', activation='relu')(tower_1)
tower_2 = Conv2D(64, (1, 1), padding='same', activation='relu')(input_img)
tower_2 = Conv2D(64, (5, 5), padding='same', activation='relu')(tower_2)
tower_3 = MaxPooling2D((3, 3), strides=(1, 1), padding='same')(input_img)
tower_3 = Conv2D(64, (1, 1), padding='same', activation='relu')(tower_3)
output = keras.layers.concatenate([tower_1, tower_2, tower_3], axis=1)
4.2 ResNet
from keras.layers import Conv2D, Input
# input tensor for a 3-channel 256x256 image
x = Input(shape=(3, 256, 256))
# 3x3 conv with 3 output channels (same as input channels)
y = Conv2D(3, (3, 3), padding='same')(x)
# this returns x + y.
z = keras.layers.add([x, y])
5. Net
5.1 MLP
from keras.datasets imp'''Trains and evaluate a simple MLP
on the Reuters newswire topic classification task.
'''
from __future__ import print_function
import numpy as np
import kerasort reuters
from keras.models import Sequential
from keras.layers import Dense, Dropout, Activation
from keras.preprocessing.text import Tokenizer
max_words = 1000
batch_size = 32
epochs = 5
print('Loading data...')
(x_train, y_train), (x_test, y_test) = reuters.load_data(num_words=max_words,
test_split=0.2)
print(len(x_train), 'train sequences')
print(len(x_test), 'test sequences')
num_classes = np.max(y_train) + 1
print(num_classes, 'classes')
print('Vectorizing sequence data...')
tokenizer = Tokenizer(num_words=max_words)
x_train = tokenizer.sequences_to_matrix(x_train, mode='binary')
x_test = tokenizer.sequences_to_matrix(x_test, mode='binary')
print('x_train shape:', x_train.shape)
print('x_test shape:', x_test.shape)
print('Convert class vector to binary class matrix '
'(for use with categorical_crossentropy)')
y_train = keras.utils.to_categorical(y_train, num_classes)
y_test = keras.utils.to_categorical(y_test, num_classes)
print('y_train shape:', y_train.shape)
print('y_test shape:', y_test.shape)
print('Building model...')
model = Sequential()
model.add(Dense(512, input_shape=(max_words,)))
model.add(Activation('relu'))
model.add(Dropout(0.5))
model.add(Dense(num_classes))
model.add(Activation('softmax'))
model.compile(loss='categorical_crossentropy',
optimizer='adam',
metrics=['accuracy'])
history = model.fit(x_train, y_train,
batch_size=batch_size,
epochs=epochs,
verbose=1,
validation_split=0.1)
score = model.evaluate(x_test, y_test,
batch_size=batch_size, verbose=1)
print('Test score:', score[0])
print('Test accuracy:', score[1]
5.2 vgg16
# -*- coding: utf-8 -*-
'''VGG16 model for Keras.
# Reference:
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://arxiv.org/abs/1409.1556)
'''
from __future__ import print_function
import numpy as np
import warnings
from keras.models import Model
from keras.layers import Flatten
from keras.layers import Dense
from keras.layers import Input
from keras.layers import Conv2D
from keras.layers import MaxPooling2D
from keras.layers import GlobalMaxPooling2D
from keras.layers import GlobalAveragePooling2D
from keras.preprocessing import image
from keras.utils import layer_utils
from keras.utils.data_utils import get_file
from keras import backend as K
from keras.applications.imagenet_utils import decode_predictions
from keras.applications.imagenet_utils import preprocess_input
from keras.applications.imagenet_utils import _obtain_input_shape
from keras.engine.topology import get_source_inputs
WEIGHTS_PATH = 'https://github.com/fchollet/deep-learning-models/releases/download/v0.1/vgg16_weights_tf_dim_ordering_tf_kernels.h5'
WEIGHTS_PATH_NO_TOP = 'https://github.com/fchollet/deep-learning-models/releases/download/v0.1/vgg16_weights_tf_dim_ordering_tf_kernels_notop.h5'
def VGG16(include_top=True, weights='imagenet',
input_tensor=None, input_shape=None,
pooling=None,
classes=1000):
"""Instantiates the VGG16 architecture.
Optionally loads weights pre-trained
on ImageNet. Note that when using TensorFlow,
for best performance you should set
`image_data_format="channels_last"` in your Keras config
at ~/.keras/keras.json.
The model and the weights are compatible with both
TensorFlow and Theano. The data format
convention used by the model is the one
specified in your Keras config file.
# Arguments
include_top: whether to include the 3 fully-connected
layers at the top of the network.
weights: one of `None` (random initialization)
or "imagenet" (pre-training on ImageNet).
input_tensor: optional Keras tensor (i.e. output of `layers.Input()`)
to use as image input for the model.
input_shape: optional shape tuple, only to be specified
if `include_top` is False (otherwise the input shape
has to be `(224, 224, 3)` (with `channels_last` data format)
or `(3, 224, 244)` (with `channels_first` data format).
It should have exactly 3 inputs channels,
and width and height should be no smaller than 48.
E.g. `(200, 200, 3)` would be one valid value.
pooling: Optional pooling mode for feature extraction
when `include_top` is `False`.
- `None` means that the output of the model will be
the 4D tensor output of the
last convolutional layer.
- `avg` means that global average pooling
will be applied to the output of the
last convolutional layer, and thus
the output of the model will be a 2D tensor.
- `max` means that global max pooling will
be applied.
classes: optional number of classes to classify images
into, only to be specified if `include_top` is True, and
if no `weights` argument is specified.
# Returns
A Keras model instance.
# Raises
ValueError: in case of invalid argument for `weights`,
or invalid input shape.
"""
if weights not in {'imagenet', None}:
raise ValueError('The `weights` argument should be either '
'`None` (random initialization) or `imagenet` '
'(pre-training on ImageNet).')
if weights == 'imagenet' and include_top and classes != 1000:
raise ValueError('If using `weights` as imagenet with `include_top`'
' as true, `classes` should be 1000')
# Determine proper input shape
input_shape = _obtain_input_shape(input_shape,
default_size=224,
min_size=48,
data_format=K.image_data_format(),
include_top=include_top)
if input_tensor is None:
img_input = Input(shape=input_shape)
else:
if not K.is_keras_tensor(input_tensor):
img_input = Input(tensor=input_tensor, shape=input_shape)
else:
img_input = input_tensor
# Block 1
x = Conv2D(64, (3, 3), activation='relu', padding='same', name='block1_conv1')(img_input)
x = Conv2D(64, (3, 3), activation='relu', padding='same', name='block1_conv2')(x)
x = MaxPooling2D((2, 2), strides=(2, 2), name='block1_pool')(x)
# Block 2
x = Conv2D(128, (3, 3), activation='relu', padding='same', name='block2_conv1')(x)
x = Conv2D(128, (3, 3), activation='relu', padding='same', name='block2_conv2')(x)
x = MaxPooling2D((2, 2), strides=(2, 2), name='block2_pool')(x)
# Block 3
x = Conv2D(256, (3, 3), activation='relu', padding='same', name='block3_conv1')(x)
x = Conv2D(256, (3, 3), activation='relu', padding='same', name='block3_conv2')(x)
x = Conv2D(256, (3, 3), activation='relu', padding='same', name='block3_conv3')(x)
x = MaxPooling2D((2, 2), strides=(2, 2), name='block3_pool')(x)
# Block 4
x = Conv2D(512, (3, 3), activation='relu', padding='same', name='block4_conv1')(x)
x = Conv2D(512, (3, 3), activation='relu', padding='same', name='block4_conv2')(x)
x = Conv2D(512, (3, 3), activation='relu', padding='same', name='block4_conv3')(x)
x = MaxPooling2D((2, 2), strides=(2, 2), name='block4_pool')(x)
# Block 5
x = Conv2D(512, (3, 3), activation='relu', padding='same', name='block5_conv1')(x)
x = Conv2D(512, (3, 3), activation='relu', padding='same', name='block5_conv2')(x)
x = Conv2D(512, (3, 3), activation='relu', padding='same', name='block5_conv3')(x)
x = MaxPooling2D((2, 2), strides=(2, 2), name='block5_pool')(x)
if include_top:
# Classification block
x = Flatten(name='flatten')(x)
x = Dense(4096, activation='relu', name='fc1')(x)
x = Dense(4096, activation='relu', name='fc2')(x)
x = Dense(classes, activation='softmax', name='predictions')(x)
else:
if pooling == 'avg':
x = GlobalAveragePooling2D()(x)
elif pooling == 'max':
x = GlobalMaxPooling2D()(x)
# Ensure that the model takes into account
# any potential predecessors of `input_tensor`.
if input_tensor is not None:
inputs = get_source_inputs(input_tensor)
else:
inputs = img_input
# Create model.
model = Model(inputs, x, name='vgg16')
# load weights
if weights == 'imagenet':
if include_top:
weights_path = get_file('vgg16_weights_tf_dim_ordering_tf_kernels.h5',
WEIGHTS_PATH,
cache_subdir='models')
else:
weights_path = get_file('vgg16_weights_tf_dim_ordering_tf_kernels_notop.h5',
WEIGHTS_PATH_NO_TOP,
cache_subdir='models')
model.load_weights(weights_path)
if K.backend() == 'theano':
layer_utils.convert_all_kernels_in_model(model)
if K.image_data_format() == 'channels_first':
if include_top:
maxpool = model.get_layer(name='block5_pool')
shape = maxpool.output_shape[1:]
dense = model.get_layer(name='fc1')
layer_utils.convert_dense_weights_data_format(dense, shape, 'channels_first')
if K.backend() == 'tensorflow':
warnings.warn('You are using the TensorFlow backend, yet you '
'are using the Theano '
'image data format convention '
'(`image_data_format="channels_first"`). '
'For best performance, set '
'`image_data_format="channels_last"` in '
'your Keras config '
'at ~/.keras/keras.json.')
return model
if __name__ == '__main__':
model = VGG16(include_top=True, weights='imagenet')
img_path = 'elephant.jpg'
img = image.load_img(img_path, target_size=(224, 224))
x = image.img_to_array(img)
x = np.expand_dims(x, axis=0)
x = preprocess_input(x)
print('Input image shape:', x.shape)
preds = model.predict(x)
print('Predicted:', decode_predictions(preds))
5.3 inception v3
# -*- coding: utf-8 -*-
"""Inception V3 model for Keras.
Note that the input image format for this model is different than for
the VGG16 and ResNet models (299x299 instead of 224x224),
and that the input preprocessing function is also different (same as Xception).
# Reference
- [Rethinking the Inception Architecture for Computer Vision](http://arxiv.org/abs/1512.00567)
"""
from __future__ import print_function
from __future__ import absolute_import
import warnings
import numpy as np
from keras.models import Model
from keras import layers
from keras.layers import Activation
from keras.layers import Dense
from keras.layers import Input
from keras.layers import BatchNormalization
from keras.layers import Conv2D
from keras.layers import MaxPooling2D
from keras.layers import AveragePooling2D
from keras.layers import GlobalAveragePooling2D
from keras.layers import GlobalMaxPooling2D
from keras.engine.topology import get_source_inputs
from keras.utils.layer_utils import convert_all_kernels_in_model
from keras.utils.data_utils import get_file
from keras import backend as K
from keras.applications.imagenet_utils import decode_predictions
from keras.applications.imagenet_utils import _obtain_input_shape
from keras.preprocessing import image
WEIGHTS_PATH = 'https://github.com/fchollet/deep-learning-models/releases/download/v0.5/inception_v3_weights_tf_dim_ordering_tf_kernels.h5'
WEIGHTS_PATH_NO_TOP = 'https://github.com/fchollet/deep-learning-models/releases/download/v0.5/inception_v3_weights_tf_dim_ordering_tf_kernels_notop.h5'
def conv2d_bn(x,
filters,
num_row,
num_col,
padding='same',
strides=(1, 1),
name=None):
"""Utility function to apply conv + BN.
Arguments:
x: input tensor.
filters: filters in `Conv2D`.
num_row: height of the convolution kernel.
num_col: width of the convolution kernel.
padding: padding mode in `Conv2D`.
strides: strides in `Conv2D`.
name: name of the ops; will become `name + '_conv'`
for the convolution and `name + '_bn'` for the
batch norm layer.
Returns:
Output tensor after applying `Conv2D` and `BatchNormalization`.
"""
if name is not None:
bn_name = name + '_bn'
conv_name = name + '_conv'
else:
bn_name = None
conv_name = None
if K.image_data_format() == 'channels_first':
bn_axis = 1
else:
bn_axis = 3
x = Conv2D(
filters, (num_row, num_col),
strides=strides,
padding=padding,
use_bias=False,
name=conv_name)(x)
x = BatchNormalization(axis=bn_axis, scale=False, name=bn_name)(x)
x = Activation('relu', name=name)(x)
return x
def InceptionV3(include_top=True,
weights='imagenet',
input_tensor=None,
input_shape=None,
pooling=None,
classes=1000):
"""Instantiates the Inception v3 architecture.
Optionally loads weights pre-trained
on ImageNet. Note that when using TensorFlow,
for best performance you should set
`image_data_format="channels_last"` in your Keras config
at ~/.keras/keras.json.
The model and the weights are compatible with both
TensorFlow and Theano. The data format
convention used by the model is the one
specified in your Keras config file.
Note that the default input image size for this model is 299x299.
Arguments:
include_top: whether to include the fully-connected
layer at the top of the network.
weights: one of `None` (random initialization)
or "imagenet" (pre-training on ImageNet).
input_tensor: optional Keras tensor (i.e. output of `layers.Input()`)
to use as image input for the model.
input_shape: optional shape tuple, only to be specified
if `include_top` is False (otherwise the input shape
has to be `(299, 299, 3)` (with `channels_last` data format)
or `(3, 299, 299)` (with `channels_first` data format).
It should have exactly 3 inputs channels,
and width and height should be no smaller than 139.
E.g. `(150, 150, 3)` would be one valid value.
pooling: Optional pooling mode for feature extraction
when `include_top` is `False`.
- `None` means that the output of the model will be
the 4D tensor output of the
last convolutional layer.
- `avg` means that global average pooling
will be applied to the output of the
last convolutional layer, and thus
the output of the model will be a 2D tensor.
- `max` means that global max pooling will
be applied.
classes: optional number of classes to classify images
into, only to be specified if `include_top` is True, and
if no `weights` argument is specified.
Returns:
A Keras model instance.
Raises:
ValueError: in case of invalid argument for `weights`,
or invalid input shape.
"""
if weights not in {'imagenet', None}:
raise ValueError('The `weights` argument should be either '
'`None` (random initialization) or `imagenet` '
'(pre-training on ImageNet).')
if weights == 'imagenet' and include_top and classes != 1000:
raise ValueError('If using `weights` as imagenet with `include_top`'
' as true, `classes` should be 1000')
# Determine proper input shape
input_shape = _obtain_input_shape(
input_shape,
default_size=299,
min_size=139,
data_format=K.image_data_format(),
include_top=include_top)
if input_tensor is None:
img_input = Input(shape=input_shape)
else:
img_input = Input(tensor=input_tensor, shape=input_shape)
if K.image_data_format() == 'channels_first':
channel_axis = 1
else:
channel_axis = 3
x = conv2d_bn(img_input, 32, 3, 3, strides=(2, 2), padding='valid')
x = conv2d_bn(x, 32, 3, 3, padding='valid')
x = conv2d_bn(x, 64, 3, 3)
x = MaxPooling2D((3, 3), strides=(2, 2))(x)
x = conv2d_bn(x, 80, 1, 1, padding='valid')
x = conv2d_bn(x, 192, 3, 3, padding='valid')
x = MaxPooling2D((3, 3), strides=(2, 2))(x)
# mixed 0, 1, 2: 35 x 35 x 256
branch1x1 = conv2d_bn(x, 64, 1, 1)
branch5x5 = conv2d_bn(x, 48, 1, 1)
branch5x5 = conv2d_bn(branch5x5, 64, 5, 5)
branch3x3dbl = conv2d_bn(x, 64, 1, 1)
branch3x3dbl = conv2d_bn(branch3x3dbl, 96, 3, 3)
branch3x3dbl = conv2d_bn(branch3x3dbl, 96, 3, 3)
branch_pool = AveragePooling2D((3, 3), strides=(1, 1), padding='same')(x)
branch_pool = conv2d_bn(branch_pool, 32, 1, 1)
x = layers.concatenate(
[branch1x1, branch5x5, branch3x3dbl, branch_pool],
axis=channel_axis,
name='mixed0')
# mixed 1: 35 x 35 x 256
branch1x1 = conv2d_bn(x, 64, 1, 1)
branch5x5 = conv2d_bn(x, 48, 1, 1)
branch5x5 = conv2d_bn(branch5x5, 64, 5, 5)
branch3x3dbl = conv2d_bn(x, 64, 1, 1)
branch3x3dbl = conv2d_bn(branch3x3dbl, 96, 3, 3)
branch3x3dbl = conv2d_bn(branch3x3dbl, 96, 3, 3)
branch_pool = AveragePooling2D((3, 3), strides=(1, 1), padding='same')(x)
branch_pool = conv2d_bn(branch_pool, 64, 1, 1)
x = layers.concatenate(
[branch1x1, branch5x5, branch3x3dbl, branch_pool],
axis=channel_axis,
name='mixed1')
# mixed 2: 35 x 35 x 256
branch1x1 = conv2d_bn(x, 64, 1, 1)
branch5x5 = conv2d_bn(x, 48, 1, 1)
branch5x5 = conv2d_bn(branch5x5, 64, 5, 5)
branch3x3dbl = conv2d_bn(x, 64, 1, 1)
branch3x3dbl = conv2d_bn(branch3x3dbl, 96, 3, 3)
branch3x3dbl = conv2d_bn(branch3x3dbl, 96, 3, 3)
branch_pool = AveragePooling2D((3, 3), strides=(1, 1), padding='same')(x)
branch_pool = conv2d_bn(branch_pool, 64, 1, 1)
x = layers.concatenate(
[branch1x1, branch5x5, branch3x3dbl, branch_pool],
axis=channel_axis,
name='mixed2')
# mixed 3: 17 x 17 x 768
branch3x3 = conv2d_bn(x, 384, 3, 3, strides=(2, 2), padding='valid')
branch3x3dbl = conv2d_bn(x, 64, 1, 1)
branch3x3dbl = conv2d_bn(branch3x3dbl, 96, 3, 3)
branch3x3dbl = conv2d_bn(
branch3x3dbl, 96, 3, 3, strides=(2, 2), padding='valid')
branch_pool = MaxPooling2D((3, 3), strides=(2, 2))(x)
x = layers.concatenate(
[branch3x3, branch3x3dbl, branch_pool], axis=channel_axis, name='mixed3')
# mixed 4: 17 x 17 x 768
branch1x1 = conv2d_bn(x, 192, 1, 1)
branch7x7 = conv2d_bn(x, 128, 1, 1)
branch7x7 = conv2d_bn(branch7x7, 128, 1, 7)
branch7x7 = conv2d_bn(branch7x7, 192, 7, 1)
branch7x7dbl = conv2d_bn(x, 128, 1, 1)
branch7x7dbl = conv2d_bn(branch7x7dbl, 128, 7, 1)
branch7x7dbl = conv2d_bn(branch7x7dbl, 128, 1, 7)
branch7x7dbl = conv2d_bn(branch7x7dbl, 128, 7, 1)
branch7x7dbl = conv2d_bn(branch7x7dbl, 192, 1, 7)
branch_pool = AveragePooling2D((3, 3), strides=(1, 1), padding='same')(x)
branch_pool = conv2d_bn(branch_pool, 192, 1, 1)
x = layers.concatenate(
[branch1x1, branch7x7, branch7x7dbl, branch_pool],
axis=channel_axis,
name='mixed4')
# mixed 5, 6: 17 x 17 x 768
for i in range(2):
branch1x1 = conv2d_bn(x, 192, 1, 1)
branch7x7 = conv2d_bn(x, 160, 1, 1)
branch7x7 = conv2d_bn(branch7x7, 160, 1, 7)
branch7x7 = conv2d_bn(branch7x7, 192, 7, 1)
branch7x7dbl = conv2d_bn(x, 160, 1, 1)
branch7x7dbl = conv2d_bn(branch7x7dbl, 160, 7, 1)
branch7x7dbl = conv2d_bn(branch7x7dbl, 160, 1, 7)
branch7x7dbl = conv2d_bn(branch7x7dbl, 160, 7, 1)
branch7x7dbl = conv2d_bn(branch7x7dbl, 192, 1, 7)
branch_pool = AveragePooling2D(
(3, 3), strides=(1, 1), padding='same')(x)
branch_pool = conv2d_bn(branch_pool, 192, 1, 1)
x = layers.concatenate(
[branch1x1, branch7x7, branch7x7dbl, branch_pool],
axis=channel_axis,
name='mixed' + str(5 + i))
# mixed 7: 17 x 17 x 768
branch1x1 = conv2d_bn(x, 192, 1, 1)
branch7x7 = conv2d_bn(x, 192, 1, 1)
branch7x7 = conv2d_bn(branch7x7, 192, 1, 7)
branch7x7 = conv2d_bn(branch7x7, 192, 7, 1)
branch7x7dbl = conv2d_bn(x, 192, 1, 1)
branch7x7dbl = conv2d_bn(branch7x7dbl, 192, 7, 1)
branch7x7dbl = conv2d_bn(branch7x7dbl, 192, 1, 7)
branch7x7dbl = conv2d_bn(branch7x7dbl, 192, 7, 1)
branch7x7dbl = conv2d_bn(branch7x7dbl, 192, 1, 7)
branch_pool = AveragePooling2D((3, 3), strides=(1, 1), padding='same')(x)
branch_pool = conv2d_bn(branch_pool, 192, 1, 1)
x = layers.concatenate(
[branch1x1, branch7x7, branch7x7dbl, branch_pool],
axis=channel_axis,
name='mixed7')
# mixed 8: 8 x 8 x 1280
branch3x3 = conv2d_bn(x, 192, 1, 1)
branch3x3 = conv2d_bn(branch3x3, 320, 3, 3,
strides=(2, 2), padding='valid')
branch7x7x3 = conv2d_bn(x, 192, 1, 1)
branch7x7x3 = conv2d_bn(branch7x7x3, 192, 1, 7)
branch7x7x3 = conv2d_bn(branch7x7x3, 192, 7, 1)
branch7x7x3 = conv2d_bn(
branch7x7x3, 192, 3, 3, strides=(2, 2), padding='valid')
branch_pool = MaxPooling2D((3, 3), strides=(2, 2))(x)
x = layers.concatenate(
[branch3x3, branch7x7x3, branch_pool], axis=channel_axis, name='mixed8')
# mixed 9: 8 x 8 x 2048
for i in range(2):
branch1x1 = conv2d_bn(x, 320, 1, 1)
branch3x3 = conv2d_bn(x, 384, 1, 1)
branch3x3_1 = conv2d_bn(branch3x3, 384, 1, 3)
branch3x3_2 = conv2d_bn(branch3x3, 384, 3, 1)
branch3x3 = layers.concatenate(
[branch3x3_1, branch3x3_2], axis=channel_axis, name='mixed9_' + str(i))
branch3x3dbl = conv2d_bn(x, 448, 1, 1)
branch3x3dbl = conv2d_bn(branch3x3dbl, 384, 3, 3)
branch3x3dbl_1 = conv2d_bn(branch3x3dbl, 384, 1, 3)
branch3x3dbl_2 = conv2d_bn(branch3x3dbl, 384, 3, 1)
branch3x3dbl = layers.concatenate(
[branch3x3dbl_1, branch3x3dbl_2], axis=channel_axis)
branch_pool = AveragePooling2D(
(3, 3), strides=(1, 1), padding='same')(x)
branch_pool = conv2d_bn(branch_pool, 192, 1, 1)
x = layers.concatenate(
[branch1x1, branch3x3, branch3x3dbl, branch_pool],
axis=channel_axis,
name='mixed' + str(9 + i))
if include_top:
# Classification block
x = GlobalAveragePooling2D(name='avg_pool')(x)
x = Dense(classes, activation='softmax', name='predictions')(x)
else:
if pooling == 'avg':
x = GlobalAveragePooling2D()(x)
elif pooling == 'max':
x = GlobalMaxPooling2D()(x)
# Ensure that the model takes into account
# any potential predecessors of `input_tensor`.
if input_tensor is not None:
inputs = get_source_inputs(input_tensor)
else:
inputs = img_input
# Create model.
model = Model(inputs, x, name='inception_v3')
# load weights
if weights == 'imagenet':
if K.image_data_format() == 'channels_first':
if K.backend() == 'tensorflow':
warnings.warn('You are using the TensorFlow backend, yet you '
'are using the Theano '
'image data format convention '
'(`image_data_format="channels_first"`). '
'For best performance, set '
'`image_data_format="channels_last"` in '
'your Keras config '
'at ~/.keras/keras.json.')
if include_top:
weights_path = get_file(
'inception_v3_weights_tf_dim_ordering_tf_kernels.h5',
WEIGHTS_PATH,
cache_subdir='models',
md5_hash='9a0d58056eeedaa3f26cb7ebd46da564')
else:
weights_path = get_file(
'inception_v3_weights_tf_dim_ordering_tf_kernels_notop.h5',
WEIGHTS_PATH_NO_TOP,
cache_subdir='models',
md5_hash='bcbd6486424b2319ff4ef7d526e38f63')
model.load_weights(weights_path)
if K.backend() == 'theano':
convert_all_kernels_in_model(model)
return model
def preprocess_input(x):
x /= 255.
x -= 0.5
x *= 2.
return x
if __name__ == '__main__':
model = InceptionV3(include_top=True, weights='imagenet')
img_path = 'elephant.jpg'
img = image.load_img(img_path, target_size=(299, 299))
x = image.img_to_array(img)
x = np.expand_dims(x, axis=0)
x = preprocess_input(x)
preds = model.predict(x)
print('Predicted:', decode_predictions(preds))
5.4 ResNet-50
# -*- coding: utf-8 -*-
'''ResNet50 model for Keras.
# Reference:
- [Deep Residual Learning for Image Recognition](https://arxiv.org/abs/1512.03385)
Adapted from code contributed by BigMoyan.
'''
from __future__ import print_function
import numpy as np
import warnings
from keras.layers import Input
from keras import layers
from keras.layers import Dense
from keras.layers import Activation
from keras.layers import Flatten
from keras.layers import Conv2D
from keras.layers import MaxPooling2D
from keras.layers import GlobalMaxPooling2D
from keras.layers import ZeroPadding2D
from keras.layers import AveragePooling2D
from keras.layers import GlobalAveragePooling2D
from keras.layers import BatchNormalization
from keras.models import Model
from keras.preprocessing import image
import keras.backend as K
from keras.utils import layer_utils
from keras.utils.data_utils import get_file
from keras.applications.imagenet_utils import decode_predictions
from keras.applications.imagenet_utils import preprocess_input
from keras.applications.imagenet_utils import _obtain_input_shape
from keras.engine.topology import get_source_inputs
WEIGHTS_PATH = 'https://github.com/fchollet/deep-learning-models/releases/download/v0.2/resnet50_weights_tf_dim_ordering_tf_kernels.h5'
WEIGHTS_PATH_NO_TOP = 'https://github.com/fchollet/deep-learning-models/releases/download/v0.2/resnet50_weights_tf_dim_ordering_tf_kernels_notop.h5'
def identity_block(input_tensor, kernel_size, filters, stage, block):
"""The identity block is the block that has no conv layer at shortcut.
# Arguments
input_tensor: input tensor
kernel_size: defualt 3, the kernel size of middle conv layer at main path
filters: list of integers, the filterss of 3 conv layer at main path
stage: integer, current stage label, used for generating layer names
block: 'a','b'..., current block label, used for generating layer names
# Returns
Output tensor for the block.
"""
filters1, filters2, filters3 = filters
if K.image_data_format() == 'channels_last':
bn_axis = 3
else:
bn_axis = 1
conv_name_base = 'res' + str(stage) + block + '_branch'
bn_name_base = 'bn' + str(stage) + block + '_branch'
x = Conv2D(filters1, (1, 1), name=conv_name_base + '2a')(input_tensor)
x = BatchNormalization(axis=bn_axis, name=bn_name_base + '2a')(x)
x = Activation('relu')(x)
x = Conv2D(filters2, kernel_size,
padding='same', name=conv_name_base + '2b')(x)
x = BatchNormalization(axis=bn_axis, name=bn_name_base + '2b')(x)
x = Activation('relu')(x)
x = Conv2D(filters3, (1, 1), name=conv_name_base + '2c')(x)
x = BatchNormalization(axis=bn_axis, name=bn_name_base + '2c')(x)
x = layers.add([x, input_tensor])
x = Activation('relu')(x)
return x
def conv_block(input_tensor, kernel_size, filters, stage, block, strides=(2, 2)):
"""conv_block is the block that has a conv layer at shortcut
# Arguments
input_tensor: input tensor
kernel_size: defualt 3, the kernel size of middle conv layer at main path
filters: list of integers, the filterss of 3 conv layer at main path
stage: integer, current stage label, used for generating layer names
block: 'a','b'..., current block label, used for generating layer names
# Returns
Output tensor for the block.
Note that from stage 3, the first conv layer at main path is with strides=(2,2)
And the shortcut should have strides=(2,2) as well
"""
filters1, filters2, filters3 = filters
if K.image_data_format() == 'channels_last':
bn_axis = 3
else:
bn_axis = 1
conv_name_base = 'res' + str(stage) + block + '_branch'
bn_name_base = 'bn' + str(stage) + block + '_branch'
x = Conv2D(filters1, (1, 1), strides=strides,
name=conv_name_base + '2a')(input_tensor)
x = BatchNormalization(axis=bn_axis, name=bn_name_base + '2a')(x)
x = Activation('relu')(x)
x = Conv2D(filters2, kernel_size, padding='same',
name=conv_name_base + '2b')(x)
x = BatchNormalization(axis=bn_axis, name=bn_name_base + '2b')(x)
x = Activation('relu')(x)
x = Conv2D(filters3, (1, 1), name=conv_name_base + '2c')(x)
x = BatchNormalization(axis=bn_axis, name=bn_name_base + '2c')(x)
shortcut = Conv2D(filters3, (1, 1), strides=strides,
name=conv_name_base + '1')(input_tensor)
shortcut = BatchNormalization(axis=bn_axis, name=bn_name_base + '1')(shortcut)
x = layers.add([x, shortcut])
x = Activation('relu')(x)
return x
def ResNet50(include_top=True, weights='imagenet',
input_tensor=None, input_shape=None,
pooling=None,
classes=1000):
"""Instantiates the ResNet50 architecture.
Optionally loads weights pre-trained
on ImageNet. Note that when using TensorFlow,
for best performance you should set
`image_data_format="channels_last"` in your Keras config
at ~/.keras/keras.json.
The model and the weights are compatible with both
TensorFlow and Theano. The data format
convention used by the model is the one
specified in your Keras config file.
# Arguments
include_top: whether to include the fully-connected
layer at the top of the network.
weights: one of `None` (random initialization)
or "imagenet" (pre-training on ImageNet).
input_tensor: optional Keras tensor (i.e. output of `layers.Input()`)
to use as image input for the model.
input_shape: optional shape tuple, only to be specified
if `include_top` is False (otherwise the input shape
has to be `(224, 224, 3)` (with `channels_last` data format)
or `(3, 224, 244)` (with `channels_first` data format).
It should have exactly 3 inputs channels,
and width and height should be no smaller than 197.
E.g. `(200, 200, 3)` would be one valid value.
pooling: Optional pooling mode for feature extraction
when `include_top` is `False`.
- `None` means that the output of the model will be
the 4D tensor output of the
last convolutional layer.
- `avg` means that global average pooling
will be applied to the output of the
last convolutional layer, and thus
the output of the model will be a 2D tensor.
- `max` means that global max pooling will
be applied.
classes: optional number of classes to classify images
into, only to be specified if `include_top` is True, and
if no `weights` argument is specified.
# Returns
A Keras model instance.
# Raises
ValueError: in case of invalid argument for `weights`,
or invalid input shape.
"""
if weights not in {'imagenet', None}:
raise ValueError('The `weights` argument should be either '
'`None` (random initialization) or `imagenet` '
'(pre-training on ImageNet).')
if weights == 'imagenet' and include_top and classes != 1000:
raise ValueError('If using `weights` as imagenet with `include_top`'
' as true, `classes` should be 1000')
# Determine proper input shape
input_shape = _obtain_input_shape(input_shape,
default_size=224,
min_size=197,
data_format=K.image_data_format(),
include_top=include_top)
if input_tensor is None:
img_input = Input(shape=input_shape)
else:
if not K.is_keras_tensor(input_tensor):
img_input = Input(tensor=input_tensor, shape=input_shape)
else:
img_input = input_tensor
if K.image_data_format() == 'channels_last':
bn_axis = 3
else:
bn_axis = 1
x = ZeroPadding2D((3, 3))(img_input)
x = Conv2D(64, (7, 7), strides=(2, 2), name='conv1')(x)
x = BatchNormalization(axis=bn_axis, name='bn_conv1')(x)
x = Activation('relu')(x)
x = MaxPooling2D((3, 3), strides=(2, 2))(x)
x = conv_block(x, 3, [64, 64, 256], stage=2, block='a', strides=(1, 1))
x = identity_block(x, 3, [64, 64, 256], stage=2, block='b')
x = identity_block(x, 3, [64, 64, 256], stage=2, block='c')
x = conv_block(x, 3, [128, 128, 512], stage=3, block='a')
x = identity_block(x, 3, [128, 128, 512], stage=3, block='b')
x = identity_block(x, 3, [128, 128, 512], stage=3, block='c')
x = identity_block(x, 3, [128, 128, 512], stage=3, block='d')
x = conv_block(x, 3, [256, 256, 1024], stage=4, block='a')
x = identity_block(x, 3, [256, 256, 1024], stage=4, block='b')
x = identity_block(x, 3, [256, 256, 1024], stage=4, block='c')
x = identity_block(x, 3, [256, 256, 1024], stage=4, block='d')
x = identity_block(x, 3, [256, 256, 1024], stage=4, block='e')
x = identity_block(x, 3, [256, 256, 1024], stage=4, block='f')
x = conv_block(x, 3, [512, 512, 2048], stage=5, block='a')
x = identity_block(x, 3, [512, 512, 2048], stage=5, block='b')
x = identity_block(x, 3, [512, 512, 2048], stage=5, block='c')
x = AveragePooling2D((7, 7), name='avg_pool')(x)
if include_top:
x = Flatten()(x)
x = Dense(classes, activation='softmax', name='fc1000')(x)
else:
if pooling == 'avg':
x = GlobalAveragePooling2D()(x)
elif pooling == 'max':
x = GlobalMaxPooling2D()(x)
# Ensure that the model takes into account
# any potential predecessors of `input_tensor`.
if input_tensor is not None:
inputs = get_source_inputs(input_tensor)
else:
inputs = img_input
# Create model.
model = Model(inputs, x, name='resnet50')
# load weights
if weights == 'imagenet':
if include_top:
weights_path = get_file('resnet50_weights_tf_dim_ordering_tf_kernels.h5',
WEIGHTS_PATH,
cache_subdir='models',
md5_hash='a7b3fe01876f51b976af0dea6bc144eb')
else:
weights_path = get_file('resnet50_weights_tf_dim_ordering_tf_kernels_notop.h5',
WEIGHTS_PATH_NO_TOP,
cache_subdir='models',
md5_hash='a268eb855778b3df3c7506639542a6af')
model.load_weights(weights_path)
if K.backend() == 'theano':
layer_utils.convert_all_kernels_in_model(model)
if K.image_data_format() == 'channels_first':
if include_top:
maxpool = model.get_layer(name='avg_pool')
shape = maxpool.output_shape[1:]
dense = model.get_layer(name='fc1000')
layer_utils.convert_dense_weights_data_format(dense, shape, 'channels_first')
if K.backend() == 'tensorflow':
warnings.warn('You are using the TensorFlow backend, yet you '
'are using the Theano '
'image data format convention '
'(`image_data_format="channels_first"`). '
'For best performance, set '
'`image_data_format="channels_last"` in '
'your Keras config '
'at ~/.keras/keras.json.')
return model
if __name__ == '__main__':
model = ResNet50(include_top=True, weights='imagenet')
img_path = 'elephant.jpg'
img = image.load_img(img_path, target_size=(224, 224))
x = image.img_to_array(img)
x = np.expand_dims(x, axis=0)
x = preprocess_input(x)
print('Input image shape:', x.shape)
preds = model.predict(x)
print('Predicted:', decode_predictions(preds))
5.5 LSTM
'''Example script to generate text from Nietzsche's writings.
At least 20 epochs are required before the generated text
starts sounding coherent.
It is recommended to run this script on GPU, as recurrent
networks are quite computationally intensive.
If you try this script on new data, make sure your corpus
has at least ~100k characters. ~1M is better.
'''
from __future__ import print_function
from keras.models import Sequential
from keras.layers import Dense, Activation
from keras.layers import LSTM
from keras.optimizers import RMSprop
from keras.utils.data_utils import get_file
import numpy as np
import random
import sys
path = get_file('nietzsche.txt', origin='https://s3.amazonaws.com/text-datasets/nietzsche.txt')
text = open(path).read().lower()
print('corpus length:', len(text))
chars = sorted(list(set(text)))
print('total chars:', len(chars))
char_indices = dict((c, i) for i, c in enumerate(chars))
indices_char = dict((i, c) for i, c in enumerate(chars))
# cut the text in semi-redundant sequences of maxlen characters
maxlen = 40
step = 3
sentences = []
next_chars = []
for i in range(0, len(text) - maxlen, step):
sentences.append(text[i: i + maxlen])
next_chars.append(text[i + maxlen])
print('nb sequences:', len(sentences))
print('Vectorization...')
X = np.zeros((len(sentences), maxlen, len(chars)), dtype=np.bool)
y = np.zeros((len(sentences), len(chars)), dtype=np.bool)
for i, sentence in enumerate(sentences):
for t, char in enumerate(sentence):
X[i, t, char_indices[char]] = 1
y[i, char_indices[next_chars[i]]] = 1
# build the model: a single LSTM
print('Build model...')
model = Sequential()
model.add(LSTM(128, input_shape=(maxlen, len(chars))))
model.add(Dense(len(chars)))
model.add(Activation('softmax'))
optimizer = RMSprop(lr=0.01)
model.compile(loss='categorical_crossentropy', optimizer=optimizer)
def sample(preds, temperature=1.0):
# helper function to sample an index from a probability array
preds = np.asarray(preds).astype('float64')
preds = np.log(preds) / temperature
exp_preds = np.exp(preds)
preds = exp_preds / np.sum(exp_preds)
probas = np.random.multinomial(1, preds, 1)
return np.argmax(probas)
# train the model, output generated text after each iteration
for iteration in range(1, 60):
print()
print('-' * 50)
print('Iteration', iteration)
model.fit(X, y,
batch_size=128,
epochs=1)
start_index = random.randint(0, len(text) - maxlen - 1)
for diversity in [0.2, 0.5, 1.0, 1.2]:
print()
print('----- diversity:', diversity)
generated = ''
sentence = text[start_index: start_index + maxlen]
generated += sentence
print('----- Generating with seed: "' + sentence + '"')
sys.stdout.write(generated)
for i in range(400):
x = np.zeros((1, maxlen, len(chars)))
for t, char in enumerate(sentence):
x[0, t, char_indices[char]] = 1.
preds = model.predict(x, verbose=0)[0]
next_index = sample(preds, diversity)
next_char = indices_char[next_index]
generated += next_char
sentence = sentence[1:] + next_char
sys.stdout.write(next_char)
sys.stdout.flush()
print()
5.6 GAN
'''
DCGAN on MNIST using Keras
Dependencies: tensorflow 1.0 and keras 2.0
Usage: python dcgan_mnist.py
'''
import numpy as np
import time
from tensorflow.examples.tutorials.mnist import input_data
from keras.models import Sequential
from keras.layers import Dense, Activation, Flatten, Reshape
from keras.layers import Conv2D, Conv2DTranspose, UpSampling2D
from keras.layers import LeakyReLU, Dropout
from keras.layers import BatchNormalization
from keras.optimizers import Adam, RMSprop
import matplotlib.pyplot as plt
class ElapsedTimer(object):
def __init__(self):
self.start_time = time.time()
def elapsed(self,sec):
if sec < 60:
return str(sec) + " sec"
elif sec < (60 * 60):
return str(sec / 60) + " min"
else:
return str(sec / (60 * 60)) + " hr"
def elapsed_time(self):
print("Elapsed: %s " % self.elapsed(time.time() - self.start_time) )
class DCGAN(object):
def __init__(self, img_rows=28, img_cols=28, channel=1):
self.img_rows = img_rows
self.img_cols = img_cols
self.channel = channel
self.D = None # discriminator
self.G = None # generator
self.AM = None # adversarial model
self.DM = None # discriminator model
# (W−F+2P)/S+1
def discriminator(self):
if self.D:
return self.D
self.D = Sequential()
depth = 64
dropout = 0.4
# In: 28 x 28 x 1, depth = 1
# Out: 14 x 14 x 1, depth=64
input_shape = (self.img_rows, self.img_cols, self.channel)
self.D.add(Conv2D(depth*1, 5, strides=2, input_shape=input_shape,\
padding='same'))
self.D.add(LeakyReLU(alpha=0.2))
self.D.add(Dropout(dropout))
self.D.add(Conv2D(depth*2, 5, strides=2, padding='same'))
self.D.add(LeakyReLU(alpha=0.2))
self.D.add(Dropout(dropout))
self.D.add(Conv2D(depth*4, 5, strides=2, padding='same'))
self.D.add(LeakyReLU(alpha=0.2))
self.D.add(Dropout(dropout))
self.D.add(Conv2D(depth*8, 5, strides=1, padding='same'))
self.D.add(LeakyReLU(alpha=0.2))
self.D.add(Dropout(dropout))
# Out: 1-dim probability
self.D.add(Flatten())
self.D.add(Dense(1))
self.D.add(Activation('sigmoid'))
self.D.summary()
return self.D
def generator(self):
if self.G:
return self.G
self.G = Sequential()
dropout = 0.4
depth = 64+64+64+64
dim = 7
# In: 100
# Out: dim x dim x depth
self.G.add(Dense(dim*dim*depth, input_dim=100))
self.G.add(BatchNormalization(momentum=0.9))
self.G.add(Activation('relu'))
self.G.add(Reshape((dim, dim, depth)))
self.G.add(Dropout(dropout))
# In: dim x dim x depth
# Out: 2*dim x 2*dim x depth/2
self.G.add(UpSampling2D())
self.G.add(Conv2DTranspose(int(depth/2), 5, padding='same'))
self.G.add(BatchNormalization(momentum=0.9))
self.G.add(Activation('relu'))
self.G.add(UpSampling2D())
self.G.add(Conv2DTranspose(int(depth/4), 5, padding='same'))
self.G.add(BatchNormalization(momentum=0.9))
self.G.add(Activation('relu'))
self.G.add(Conv2DTranspose(int(depth/8), 5, padding='same'))
self.G.add(BatchNormalization(momentum=0.9))
self.G.add(Activation('relu'))
# Out: 28 x 28 x 1 grayscale image [0.0,1.0] per pix
self.G.add(Conv2DTranspose(1, 5, padding='same'))
self.G.add(Activation('sigmoid'))
self.G.summary()
return self.G
def discriminator_model(self):
if self.DM:
return self.DM
optimizer = RMSprop(lr=0.0002, decay=6e-8)
self.DM = Sequential()
self.DM.add(self.discriminator())
self.DM.compile(loss='binary_crossentropy', optimizer=optimizer,\
metrics=['accuracy'])
return self.DM
def adversarial_model(self):
if self.AM:
return self.AM
optimizer = RMSprop(lr=0.0001, decay=3e-8)
self.AM = Sequential()
self.AM.add(self.generator())
self.AM.add(self.discriminator())
self.AM.compile(loss='binary_crossentropy', optimizer=optimizer,\
metrics=['accuracy'])
return self.AM
class MNIST_DCGAN(object):
def __init__(self):
self.img_rows = 28
self.img_cols = 28
self.channel = 1
self.x_train = input_data.read_data_sets("mnist",\
one_hot=True).train.images
self.x_train = self.x_train.reshape(-1, self.img_rows,\
self.img_cols, 1).astype(np.float32)
self.DCGAN = DCGAN()
self.discriminator = self.DCGAN.discriminator_model()
self.adversarial = self.DCGAN.adversarial_model()
self.generator = self.DCGAN.generator()
def train(self, train_steps=2000, batch_size=256, save_interval=0):
noise_input = None
if save_interval>0:
noise_input = np.random.uniform(-1.0, 1.0, size=[16, 100])
for i in range(train_steps):
images_train = self.x_train[np.random.randint(0,
self.x_train.shape[0], size=batch_size), :, :, :]
noise = np.random.uniform(-1.0, 1.0, size=[batch_size, 100])
images_fake = self.generator.predict(noise)
x = np.concatenate((images_train, images_fake))
y = np.ones([2*batch_size, 1])
y[batch_size:, :] = 0
d_loss = self.discriminator.train_on_batch(x, y)
y = np.ones([batch_size, 1])
noise = np.random.uniform(-1.0, 1.0, size=[batch_size, 100])
a_loss = self.adversarial.train_on_batch(noise, y)
log_mesg = "%d: [D loss: %f, acc: %f]" % (i, d_loss[0], d_loss[1])
log_mesg = "%s [A loss: %f, acc: %f]" % (log_mesg, a_loss[0], a_loss[1])
print(log_mesg)
if save_interval>0:
if (i+1)%save_interval==0:
self.plot_images(save2file=True, samples=noise_input.shape[0],\
noise=noise_input, step=(i+1))
def plot_images(self, save2file=False, fake=True, samples=16, noise=None, step=0):
filename = 'mnist.png'
if fake:
if noise is None:
noise = np.random.uniform(-1.0, 1.0, size=[samples, 100])
else:
filename = "mnist_%d.png" % step
images = self.generator.predict(noise)
else:
i = np.random.randint(0, self.x_train.shape[0], samples)
images = self.x_train[i, :, :, :]
plt.figure(figsize=(10,10))
for i in range(images.shape[0]):
plt.subplot(4, 4, i+1)
image = images[i, :, :, :]
image = np.reshape(image, [self.img_rows, self.img_cols])
plt.imshow(image, cmap='gray')
plt.axis('off')
plt.tight_layout()
if save2file:
plt.savefig(filename)
plt.close('all')
else:
plt.show()
if __name__ == '__main__':
mnist_dcgan = MNIST_DCGAN()
timer = ElapsedTimer()
mnist_dcgan.train(train_steps=10000, batch_size=256, save_interval=500)
timer.elapsed_time()
mnist_dcgan.plot_images(fake=True)
mnist_dcgan.plot_images(fake=False, save2file=True)
Note: https://keras-cn.readthedocs.io/en/latest/other/callbacks/
