深度学习笔记4：在卷积基上添加数据增强代码块和分类器

　　特征提取的另一种方式是将原有模型与一个新的密集分类器相连接，以构建一个新的模型，然后对整个模型进行端到端的训练。这种方法在输入数据上进行整体训练，使模型能够更好地适应数据特性并提取更有效的特征。通过这种方式，模型的性能可以得到进一步提高，同时也能更好地捕捉到数据中的复杂模式。

冻结卷积基

from tensorflow import keras
conv_base = keras.applications.vgg16.VGG16(
   weights="imagenet",    
   include_top=False,    
   #input_shape=(180, 180, 3)
)
conv_base.trainable = False

在卷积基上添加数据增强代码块和分类器

data_augmentation = keras.Sequential([
  layers.RandomFlip("horizontal"),
  layers.RandomRotation(0.1),        
  layers.RandomZoom(0.2),    
])  

inputs = keras.Input(shape=(180, 180, 3))
x = data_augmentation(inputs)
x = keras.applications.vgg16.preprocess_input(x) 
x = conv_base(x)
x = layers.Flatten()(x)   
x = layers.Dense(256)(x)
x = layers.Dropout(0.5)(x)
outputs = layers.Dense(1, activation="sigmoid")(x)
model = keras.Model(inputs, outputs)
model.compile(loss="binary_crossentropy",optimizer="rmsprop",metrics=["accuracy"])

加载训练数据

import  pathlib

batch_size = 32
img_height = 180
img_width = 180

new_base_dir = pathlib.Path('C:/Users/wuchh/.keras/datasets/dogs-vs-cats-small')

train_dataset = keras.preprocessing.image_dataset_from_directory(
    new_base_dir / 'train' ,
    validation_split=0.2,
    subset="training",
    seed=123,
    image_size=(img_height, img_width),
    batch_size=batch_size
)


validation_dataset = keras.preprocessing.image_dataset_from_directory(
    new_base_dir / 'train' ,
    validation_split=0.2,
    subset="validation",
    seed=123,
    image_size=(img_height, img_width),
    batch_size=batch_size
)


test_dataset = keras.preprocessing.image_dataset_from_directory(
    new_base_dir / 'test' ,
    seed=123,
    image_size=(img_height, img_width),
    batch_size=batch_size
)

训练模型

callbacks = [keras.callbacks.ModelCheckpoint( 
  filepath="feature_extraction_with_data_augmentation.model",
  save_best_only=True,
  monitor="val_loss")]

history = model.fit(    train_dataset,    epochs=50,    validation_data=validation_dataset,    callbacks=callbacks)  

绘制训练结果 

import matplotlib.pyplot as plt
acc = history.history["accuracy"]
val_acc = history.history["val_accuracy"]
loss = history.history["loss"]
val_loss = history.history["val_loss"]
epochs = range(1, len(acc) + 1)
plt.plot(epochs, acc, "bo", label="Training accuracy")
plt.plot(epochs, val_acc, "b", label="Validation accuracy")
plt.title("Training and validation accuracy")
plt.legend()
plt.figure()
plt.plot(epochs, loss, "bo", label="Training loss")
plt.plot(epochs, val_loss, "b", label="Validation loss")
plt.title("Training and validation loss")
plt.legend()
plt.show()

 在测试集上评估模型

test_model = keras.models.load_model("feature_extraction_with_data_augmentation.model")
test_loss, test_acc = test_model.evaluate(test_dataset)
print(f"Test accuracy: {test_acc:.3f}")

32/32 [==============================] - 15s 452ms/step - loss: 2.0066 - accuracy: 0.9790
Test accuracy: 0.979

总之，鉴于模型在验证数据上取得的好结果，这有点令人失望。模型的精度始终取决于评估模型的样本集。有些样本集可能比其他样本集更难以预测，在一个样本集上得到的好结果，并不一定能够在其他样本集上完全复现。