迁移学习实例
代码注释
- '''''Transfer learning toy example.
- 迁移学习实例
- 1 - Train a simple convnet on the MNIST dataset the first 5 digits [0..4].
- 1 - 基于MINIST数据集,训练简单卷积网络,前5个数字[0..4].
- 2 - Freeze convolutional layers and fine-tune dense layers
- for the classification of digits [5..9].
- 2 - 为[5..9]数字分类,冻结卷积层并微调全连接层
- Get to 99.8% test accuracy after 5 epochs
- for the first five digits classifier
- and 99.2% for the last five digits after transfer + fine-tuning.
- 5个周期后,前5个数字分类测试准确率99.8% ,同时通过迁移+微调,后5个数字测试准确率99.2%
- '''
- from __future__ import print_function
- import datetime
- import keras
- from keras.datasets import mnist
- from keras.models import Sequential
- from keras.layers import Dense, Dropout, Activation, Flatten
- from keras.layers import Conv2D, MaxPooling2D
- from keras import backend as K
- now = datetime.datetime.now
- batch_size = 128
- num_classes = 5
- epochs = 5
- # input image dimensions
- # 输入图像维度
- img_rows, img_cols = 28, 28
- # number of convolutional filters to use
- # 使用的卷积过滤器数量
- filters = 32
- # size of pooling area for max pooling
- # 最大值池化的池化区域大小
- pool_size = 2
- # convolution kernel size
- # 卷积核大小
- kernel_size = 3
- if K.image_data_format() == 'channels_first':
- input_shape = (1, img_rows, img_cols)
- else:
- input_shape = (img_rows, img_cols, 1)
- def train_model(model, train, test, num_classes):
- x_train = train[0].reshape((train[0].shape[0],) + input_shape)
- x_test = test[0].reshape((test[0].shape[0],) + input_shape)
- 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
- # 类别向量转为多分类矩阵
- y_train = keras.utils.to_categorical(train[1], num_classes)
- y_test = keras.utils.to_categorical(test[1], num_classes)
- model.compile(loss='categorical_crossentropy',
- optimizer='adadelta',
- metrics=['accuracy'])
- t = now()
- model.fit(x_train, y_train,
- batch_size=batch_size,
- epochs=epochs,
- verbose=1,
- validation_data=(x_test, y_test))
- print('Training time: %s' % (now() - t))
- score = model.evaluate(x_test, y_test, verbose=0)
- print('Test score:', score[0])
- print('Test accuracy:', score[1])
- # the data, shuffled and split between train and test sets
- # 筛选(数据顺序打乱)、划分训练集和测试集
- (x_train, y_train), (x_test, y_test) = mnist.load_data()
- # create two datasets one with digits below 5 and one with 5 and above
- # 创建2个数据集,一个数字小于5,另一个数学大于等与5
- x_train_lt5 = x_train[y_train < 5]
- y_train_lt5 = y_train[y_train < 5]
- x_test_lt5 = x_test[y_test < 5]
- y_test_lt5 = y_test[y_test < 5]
- x_train_gte5 = x_train[y_train >= 5]
- y_train_gte5 = y_train[y_train >= 5] - 5
- x_test_gte5 = x_test[y_test >= 5]
- y_test_gte5 = y_test[y_test >= 5] - 5
- # define two groups of layers: feature (convolutions) and classification (dense)
- # 定义2组层:特征(卷积)和分类(全连接)
- feature_layers = [
- Conv2D(filters, kernel_size,
- padding='valid',
- input_shape=input_shape),
- Activation('relu'),
- Conv2D(filters, kernel_size),
- Activation('relu'),
- MaxPooling2D(pool_size=pool_size),
- Dropout(0.25),
- Flatten(),
- ]
- classification_layers = [
- Dense(128),
- Activation('relu'),
- Dropout(0.5),
- Dense(num_classes),
- Activation('softmax')
- ]
- # create complete model
- # 创建完整模型
- model = Sequential(feature_layers + classification_layers)
- # train model for 5-digit classification [0..4]
- # 为5数字分类[0..4]训练模型
- train_model(model,
- (x_train_lt5, y_train_lt5),
- (x_test_lt5, y_test_lt5), num_classes)
- # freeze feature layers and rebuild model
- # 冻结特征层并重建模型
- for l in feature_layers:
- l.trainable = False
- # transfer: train dense layers for new classification task [5..9]
- # 迁移:训练全连接层为[5..9]分类任务
- train_model(model,
- (x_train_gte5, y_train_gte5),
- (x_test_gte5, y_test_gte5), num_classes)