6.7 使用预训练网络 2.0 实现猫狗分类

keras内置经典网络实现

covn_base = keras.applications.VGG16(weights='imagenet', 
                                     include_top=False, 
                                     input_shape=(200, 200, 3))

covn_base.summary()

batch_size=20

def extract_features(data_generator, sample_count):
    i = 0
    features = np.zeros(shape=(sample_count, 6, 6, 512))
    labels = np.zeros(shape=(sample_count))
    for inputs_batch, labels_batch in data_generator:
        features_batch = covn_base.predict(inputs_batch)
        features[i * batch_size : (i + 1) * batch_size] = features_batch
        labels[i * batch_size : (i + 1) * batch_size] = labels_batch
        i += 1
        if i * batch_size >= sample_count:
            break
    return features, labels

train_features, train_labels = extract_features(train_generator, 2000)
test_features, test_labels = extract_features(test_generator, 1000)

model = keras.Sequential()
model.add(layers.GlobalAveragePooling2D(input_shape=(6, 6, 512)))
model.add(layers.Dense(512, activation='relu'))
model.add(layers.Dropout(0.5))
model.add(layers.Dense(1, activation='sigmoid'))

model.summary()

model.compile(optimizer=keras.optimizers.Adam(lr=0.001),
              loss='binary_crossentropy',
              metrics=['acc'])

history = model.fit(train_features, train_labels,
                    epochs=30,
                    batch_size=50,
                    validation_data=(test_features, test_labels))


import matplotlib.pyplot as plt
%matplotlib inline

plt.plot(history.epoch, history.history['loss'], 'r', label='loss')
plt.plot(history.epoch, history.history['val_loss'], 'b--', label='val_loss')
plt.legend()

plt.plot(history.epoch, history.history['acc'], 'r')
plt.plot(history.epoch, history.history['val_acc'], 'b--')

二、特征提取使得训练速度加快

def extract_features(data_generator, sample_count):
    i = 0
    features = np.zeros(shape=(sample_count, 6, 6, 512))
    labels = np.zeros(shape=(sample_count))
    for inputs_batch, labels_batch in data_generator:
        features_batch = covn_base.predict(inputs_batch)
        features[i * batch_size : (i + 1) * batch_size] = features_batch
        labels[i * batch_size : (i + 1) * batch_size] = labels_batch
        i += 1
        if i * batch_size >= sample_count:
            break
    return features, labels