對於牛逼的程序員，人家都喜歡叫他大神；因為大神很牛逼，人家需要一個小時完成的技術問題，他就20分鍾就搞定。Keras框架是一個高度集成的框架，學好它，就猶如掌握一個法寶，可以呼風喚雨。所以學keras 猶如在修仙，呵呵。請原諒我無厘頭的邏輯。
ResNet
關於ResNet算法，在歸納卷積算法中有提到了，可以去看看。
1， ResNet 要解決的問題
ResNet要解決的問題是在求損失函數最小值時,梯度下降太快了，無法捕捉到最優解。
解決的方法是在求激活函數值 A值的時候
a^[l+1] =g(z^[l+1] +?)
〖?可以是a〗^([l-1]) 也可以是a^([l])等等
這樣就能避免梯度下降過快
以上圖是不同層數的模型的下降曲線
2， 構建自己的ResNet模型
在resnet網絡中，identity block的跳躍可能有1個或者2（conv2D+batchnorm+Relu）個，下面是兩個可選圖：
或者：
import numpy as np import tensorflow as tf from keras import layers from keras.layers import Input, Add, Dense, Activation, ZeroPadding2D, BatchNormalization, Flatten, Conv2D, AveragePooling2D, MaxPooling2D, GlobalMaxPooling2D from keras.models import Model, load_model from keras.preprocessing import image from keras.utils import layer_utils from keras.utils.data_utils import get_file from keras.applications.imagenet_utils import preprocess_input import pydot from IPython.display import SVG from keras.utils.vis_utils import model_to_dot from keras.utils import plot_model from resnets_utils import * from keras.initializers import glorot_uniform import scipy.misc from matplotlib.pyplot import imshow %matplotlib inline import keras.backend as K K.set_image_data_format('channels_last') K.set_learning_phase(1)
from keras.layers import Input, Add, Dense, Activation, ZeroPadding2D, BatchNormalization, Flatten, Conv2D, AveragePooling2D, MaxPooling2D, GlobalMaxPooling2D from keras.models import Model, load_model
紅色字體是重點關注的函數，很多在上節就已經說明，這里是BatchNormalization函數是為了規范化通道參數的，都必須給予命名：bn_name_base+’2?’
Activation 函數就不用命名了
2.1 創建標識塊 identify block
def identity_block(X, f, filters, stage, block): """ ##參數說明 ## X：輸入的維度 (m, n_H_prev, n_W_prev, n_C_prev) ## f：整數，中間conv2D的維度 ##filters 過濾核的維度 ## block 用於命名網絡中的層 ###返回值： 維度為(n_H, n_W, n_C) ###返回值： 維度為(n_H, n_W, n_C) """ ##定義偏差 conv_name_base = 'res' + str(stage) + block + '_branch' bn_name_base = 'bn' + str(stage) + block + '_branch' ##過濾核 F1, F2, F3 = filters ##保存輸入的值 X_shortcut = X # #第一層卷積 X = Conv2D(filters = F1, kernel_size = (1, 1), strides = (1,1), padding = 'valid', name = conv_name_base + '2a', kernel_initializer = glorot_uniform(seed=0))(X) X = BatchNormalization(axis = 3, name = bn_name_base + '2a')(X) X = Activation('relu')(X) ### START CODE HERE ### # Second component of main path (≈3 lines) X = Conv2D(filters = F2, kernel_size = (f, f), strides = (1,1), padding = 'same', name = conv_name_base + '2b', kernel_initializer = glorot_uniform(seed=0))(X) X = BatchNormalization(axis=3, name = bn_name_base + '2b')(X) X = Activation('relu')(X) # Third component of main path (≈2 lines) X = Conv2D(filters = F3, kernel_size = (1, 1), strides = (1,1), padding = 'valid', name = conv_name_base + '2c', kernel_initializer = glorot_uniform(seed=0))(X) X = BatchNormalization(axis=3, name = bn_name_base + '2c')(X) ###添加shortcut操作的激化 X = layers.add([X, X_shortcut]) X = Activation('relu')(X) ### END CODE HERE ### return X
小測：
tf.reset_default_graph() with tf.Session() as test: np.random.seed(1) A_prev = tf.placeholder("float", [3, 4, 4, 6]) X = np.random.randn(3, 4, 4, 6) A = identity_block(A_prev, f = 2, filters = [2, 4, 6], stage = 1, block = 'a') test.run(tf.global_variables_initializer()) out = test.run([A], feed_dict={A_prev: X, K.learning_phase(): 0}) print("out = " + str(out[0][1][1][0]))
結果：
out[ 0.94822985 0. 1.16101444 2.747859 0. 1.36677003]
2.2 卷積塊 convolutional_block
卷積塊主要是為了適配=g(+?)例子中？的維度跟的維度不匹配的現象，具體是在shortcut增加一個卷積，使其維度能都適配，而且是沒有經過activation激活過的，如圖：
這樣就可以通過卷積核的維度達到我們想到的維度減少非線性的函數操作。
def convolutional_block(X, f, filters, stage, block, s = 2): """ 參數跟identity_block是一樣的，就多了一個 s=2 表示卷積的步長 """ # defining name basis conv_name_base = 'res' + str(stage) + block + '_branch' bn_name_base = 'bn' + str(stage) + block + '_branch' # Retrieve Filters F1, F2, F3 = filters # Save the input value X_shortcut = X ##### MAIN PATH ##### # First component of main path X = Conv2D(F1, (1, 1), strides = (s,s), name = conv_name_base + '2a', padding='valid', kernel_initializer = glorot_uniform(seed=0))(X) X = BatchNormalization(axis = 3, name = bn_name_base + '2a')(X) X = Activation('relu')(X) ### START CODE HERE ### # Second component of main path (≈3 lines) X = Conv2D(F2, (f, f), strides = (1, 1), name = conv_name_base + '2b',padding='same', kernel_initializer = glorot_uniform(seed=0))(X) X = BatchNormalization(axis = 3, name = bn_name_base + '2b')(X) X = Activation('relu')(X) # Third component of main path (≈2 lines) X = Conv2D(F3, (1, 1), strides = (1, 1), name = conv_name_base + '2c',padding='valid', kernel_initializer = glorot_uniform(seed=0))(X) X = BatchNormalization(axis = 3, name = bn_name_base + '2c')(X) ##### SHORTCUT PATH #### (≈2 lines) X_shortcut = Conv2D(F3, (1, 1), strides = (s, s), name = conv_name_base + '1',padding='valid', kernel_initializer = glorot_uniform(seed=0))(X_shortcut) X_shortcut = BatchNormalization(axis = 3, name = bn_name_base + '1')(X_shortcut) # Final step: Add shortcut value to main path, and pass it through a RELU activation (≈2 lines) X = layers.add([X, X_shortcut]) X = Activation('relu')(X) ### END CODE HERE ### return X
小測：
tf.reset_defalut_graph() with tf.Session() as test: np.random.seed(1) A_prev=tf.placeholder(“float”,[3,4,4,6]) X=np.random.randn(3,4,4,6) A=convolutional_block(A_prev,f=2,filters=[2,4,6],stage=1,block=’a’) test.run(tf.global_variable_initializer()) out.test.run([A],feed_dict={A_prev:X,K.learning_phase():0}) print(“out=”+str(out[0][1][1][0]))
結果：
結果: out = [ 0.09018463 1.23489773 0.46822017 0.0367176 0. 0.65516603]
2.3 構建完整的例子
接下來我們根據
CONV2D -> BATCHNORM -> RELU -> MAXPOOL -> CONVBLOCK -> IDBLOCK*2 -> CONVBLOCK -> IDBLOCK*3
-> CONVBLOCK -> IDBLOCK*5 -> CONVBLOCK -> IDBLOCK*2 -> AVGPOOL -> TOPLAYER構建一個完整的resnet網絡
def ResNet50(input_shape = (64, 64, 3), classes = 6): """ Implementation of the popular ResNet50 the following architecture: CONV2D -> BATCHNORM -> RELU -> MAXPOOL -> CONVBLOCK -> IDBLOCK*2 -> CONVBLOCK -> IDBLOCK*3 -> CONVBLOCK -> IDBLOCK*5 -> CONVBLOCK -> IDBLOCK*2 -> AVGPOOL -> TOPLAYER Arguments: input_shape -- shape of the images of the dataset classes -- integer, number of classes Returns: model -- a Model() instance in Keras """ # Define the input as a tensor with shape input_shape X_input = Input(input_shape) # Zero-Padding X = ZeroPadding2D((3, 3))(X_input) # Stage 1 X = Conv2D(64, (7, 7), strides = (2, 2), name = 'conv1', kernel_initializer = glorot_uniform(seed=0))(X) X = BatchNormalization(axis = 3, name = 'bn_conv1')(X) X = Activation('relu')(X) X = MaxPooling2D((3, 3), strides=(2, 2))(X) # Stage 2 X = convolutional_block(X, f = 3, filters = [64, 64, 256], stage = 2, block='a', s = 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') ### START CODE HERE ### # Stage 3 (≈4 lines) # The convolutional block uses three set of filters of size [128,128,512], "f" is 3, "s" is 2 and the block is "a". # The 3 identity blocks use three set of filters of size [128,128,512], "f" is 3 and the blocks are "b", "c" and "d". X = convolutional_block(X, f = 3, filters=[128,128,512], stage = 3, block='a', s = 2) X = identity_block(X, f = 3, filters=[128,128,512], stage= 3, block='b') X = identity_block(X, f = 3, filters=[128,128,512], stage= 3, block='c') X = identity_block(X, f = 3, filters=[128,128,512], stage= 3, block='d') # Stage 4 (≈6 lines) # The convolutional block uses three set of filters of size [256, 256, 1024], "f" is 3, "s" is 2 and the block is "a". # The 5 identity blocks use three set of filters of size [256, 256, 1024], "f" is 3 and the blocks are "b", "c", "d", "e" and "f". X = convolutional_block(X, f = 3, filters=[256, 256, 1024], block='a', stage=4, s = 2) X = identity_block(X, f = 3, filters=[256, 256, 1024], block='b', stage=4) X = identity_block(X, f = 3, filters=[256, 256, 1024], block='c', stage=4) X = identity_block(X, f = 3, filters=[256, 256, 1024], block='d', stage=4) X = identity_block(X, f = 3, filters=[256, 256, 1024], block='e', stage=4) X = identity_block(X, f = 3, filters=[256, 256, 1024], block='f', stage=4) # Stage 5 (≈3 lines) # The convolutional block uses three set of filters of size [512, 512, 2048], "f" is 3, "s" is 2 and the block is "a". # The 2 identity blocks use three set of filters of size [256, 256, 2048], "f" is 3 and the blocks are "b" and "c". X = convolutional_block(X, f = 3, filters=[512, 512, 2048], stage=5, block='a', s = 2) # filters should be [256, 256, 2048], but it fail to be graded. Use [512, 512, 2048] to pass the grading X = identity_block(X, f = 3, filters=[256, 256, 2048], stage=5, block='b') X = identity_block(X, f = 3, filters=[256, 256, 2048], stage=5, block='c') # AVGPOOL (≈1 line). Use "X = AveragePooling2D(...)(X)" # The 2D Average Pooling uses a window of shape (2,2) and its name is "avg_pool".平均值池化 X = AveragePooling2D(pool_size=(2,2))(X) ### END CODE HERE ### # output layer X = Flatten()(X) X = Dense(classes, activation='softmax', name='fc' + str(classes), kernel_initializer = glorot_uniform(seed=0))(X) # Create model model = Model(inputs = X_input, outputs = X, name='ResNet50') return model
2.4 執行模型
1）加載模型
model = ResNet50(input_shape = (64, 64, 3), classes = 6)
2）編譯模型
model.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])
3）加載數據，訓練模型
X_train_orig, Y_train_orig, X_test_orig, Y_test_orig, classes = load_dataset() # Normalize image vectors X_train = X_train_orig/255. X_test = X_test_orig/255. # Convert training and test labels to one hot matrices Y_train = convert_to_one_hot(Y_train_orig, 6).T Y_test = convert_to_one_hot(Y_test_orig, 6).T print ("number of training examples = " + str(X_train.shape[0])) print ("number of test examples = " + str(X_test.shape[0])) print ("X_train shape: " + str(X_train.shape)) print ("Y_train shape: " + str(Y_train.shape)) print ("X_test shape: " + str(X_test.shape)) print ("Y_test shape: " + str(Y_test.shape))
model.fit(X_train, Y_train, epochs = 20, batch_size = 32)
4）測試模型
preds = model.evaluate(X_test, Y_test) print ("Loss = " + str(preds[0])) print ("Test Accuracy = " + str(preds[1]))
輸出結果：
120/120 [==============================] - 9s 72ms/step
Loss = 0.729047638178
Test Accuracy = 0.891666666667
=========================================================
總結：這個例子到底位置，訓練結果可能不是很滿意，可以進一步加大測試集或者加大網絡來達到優化的。
參考
中文keras手冊：http://keras-cn.readthedocs.io/en/latest/layers/core_layer/
吳恩達網易課堂教程