Keras学习

• 参加比赛用到了keras,虽然之前用tensorflow,但是感觉tensorflow的确不太友好，api比较难读，然后就学习keras使用
• 随着深入，发现keras的api确实比较友好
• 跑了一些example和models: https://github.com/fchollet/keras
• 官网blog：Building powerful image classification models using very little data :从网络中提取特征和fine-tune网络，也有中文的blog讲

We will go over the following options:

    training a small network from scratch (as a baseline)
    using the bottleneck features of a pre-trained network
    fine-tuning the top layers of a pre-trained network

• 还有一个东西就是：可视化卷积层 How convolutional neural networks see the world

• 自己也找了一些基于keras的project: Fine-tune Convolutional Neural Network in Keras with ImageNet Pretrained Models：包含很多基本网络，但有些模型参数没有

• example里面的demo:

'''Train a simple deep CNN on the CIFAR10 small images dataset.
GPU run command with Theano backend (with TensorFlow, the GPU is automatically used):
    THEANO_FLAGS=mode=FAST_RUN,device=gpu,floatx=float32 python cifar10_cnn.py
It gets down to 0.65 test logloss in 25 epochs, and down to 0.55 after 50 epochs.
(it's still underfitting at that point, though).
'''

from __future__ import print_function
import keras
from keras.datasets import cifar10
from keras.preprocessing.image import ImageDataGenerator
from keras.models import Sequential
from keras.layers import Dense, Dropout, Activation, Flatten
from keras.layers import Conv2D, MaxPooling2D

import os

batch_size = 32
num_classes = 10
epochs = 1
data_augmentation = False
num_predictions = 20
save_dir = os.path.join(os.getcwd(), 'saved_models')
model_name = 'keras_cifar10_trained_model.h5'

# The data, shuffled and split between train and test sets:
(x_train, y_train), (x_test, y_test) = cifar10.load_data()
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.
y_train = keras.utils.to_categorical(y_train, num_classes)
y_test = keras.utils.to_categorical(y_test, num_classes)

model = Sequential()
model.add(Conv2D(32, (3, 3), padding='same',
                 input_shape=x_train.shape[1:]))
model.add(Activation('relu'))
model.add(Conv2D(32, (3, 3)))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.25))

model.add(Conv2D(64, (3, 3), padding='same'))
model.add(Activation('relu'))
model.add(Conv2D(64, (3, 3)))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.25))

model.add(Flatten())
model.add(Dense(512))
model.add(Activation('relu'))
model.add(Dropout(0.5))
model.add(Dense(num_classes))
model.add(Activation('softmax'))

# initiate RMSprop optimizer
opt = keras.optimizers.rmsprop(lr=0.0001, decay=1e-6)

# Let's train the model using RMSprop
model.compile(loss='categorical_crossentropy',
              optimizer=opt,
              metrics=['accuracy'])

x_train = x_train.astype('float32')
x_test = x_test.astype('float32')
x_train /= 255
x_test /= 255

if not data_augmentation:
    print('Not using data augmentation.')
    model.fit(x_train, y_train,
              batch_size=batch_size,
              epochs=epochs,
              validation_data=(x_test, y_test),
              shuffle=True)
else:
    print('Using real-time data augmentation.')
    # This will do preprocessing and realtime data augmentation:
    datagen = ImageDataGenerator(
        featurewise_center=False,  # set input mean to 0 over the dataset
        samplewise_center=False,  # set each sample mean to 0
        featurewise_std_normalization=False,  # divide inputs by std of the dataset
        samplewise_std_normalization=False,  # divide each input by its std
        zca_whitening=False,  # apply ZCA whitening
        rotation_range=0,  # randomly rotate images in the range (degrees, 0 to 180)
        width_shift_range=0.1,  # randomly shift images horizontally (fraction of total width)
        height_shift_range=0.1,  # randomly shift images vertically (fraction of total height)
        horizontal_flip=True,  # randomly flip images
        vertical_flip=False)  # randomly flip images

    # Compute quantities required for feature-wise normalization
    # (std, mean, and principal components if ZCA whitening is applied).
    datagen.fit(x_train)

    # Fit the model on the batches generated by datagen.flow().
    print(x_train.shape[0] // batch_size)
    model.fit_generator(datagen.flow(x_train, y_train,
                                     batch_size=batch_size),
                        steps_per_epoch=x_train.shape[0] // batch_size,
                        epochs=epochs,
                        validation_data=(x_test, y_test),
                        workers=4)

# Save model and weights
if not os.path.isdir(save_dir):
    os.makedirs(save_dir)
model_path = os.path.join(save_dir, model_name)
model.save(model_path)
print('Saved trained model at %s ' % model_path)

# Score trained model.
scores = model.evaluate(x_test, y_test, verbose=1)
print('Test loss:', scores[0])
print('Test accuracy:', scores[1])

• model里面的demo:加载pre-trained模型
• 修改了一个bug: #include_top=include_top
  
  require_flatten=include_top

# -*- 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
                                      require_flatten=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')
        weights_path='vgg16_weights_tf_dim_ordering_tf_kernels.h5'
        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 = 'C:\\Users\\Administrator\\Desktop\\pic2.png'
    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))