溫馨提示×

tensorflow中vgg搭建的步驟是什么

小億
92
2024-04-02 15:22:03
欄目: 深度學習

在TensorFlow中搭建VGG模型的步驟如下：

  1. 導入必要的庫和模塊：
import tensorflow as tf
from tensorflow.keras.layers import Input, Conv2D, MaxPooling2D, Flatten, Dense
  1. 定義VGG網(wǎng)絡的結構：
def build_vgg(input_shape):
    model = tf.keras.Sequential()
    
    # Block 1
    model.add(Conv2D(64, (3, 3), activation='relu', padding='same', input_shape=input_shape))
    model.add(Conv2D(64, (3, 3), activation='relu', padding='same'))
    model.add(MaxPooling2D((2, 2), strides=(2, 2)))
    
    # Block 2
    model.add(Conv2D(128, (3, 3), activation='relu', padding='same'))
    model.add(Conv2D(128, (3, 3), activation='relu', padding='same'))
    model.add(MaxPooling2D((2, 2), strides=(2, 2)))
    
    # Block 3
    model.add(Conv2D(256, (3, 3), activation='relu', padding='same'))
    model.add(Conv2D(256, (3, 3), activation='relu', padding='same'))
    model.add(Conv2D(256, (3, 3), activation='relu', padding='same'))
    model.add(MaxPooling2D((2, 2), strides=(2, 2)))
    
    # Block 4
    model.add(Conv2D(512, (3, 3), activation='relu', padding='same'))
    model.add(Conv2D(512, (3, 3), activation='relu', padding='same'))
    model.add(Conv2D(512, (3, 3), activation='relu', padding='same'))
    model.add(MaxPooling2D((2, 2), strides=(2, 2))
    
    # Block 5
    model.add(Conv2D(512, (3, 3), activation='relu', padding='same'))
    model.add(Conv2D(512, (3, 3), activation='relu', padding='same'))
    model.add(Conv2D(512, (3, 3), activation='relu', padding='same'))
    model.add(MaxPooling2D((2, 2), strides=(2, 2))
    
    model.add(Flatten())
    
    # Fully connected layers
    model.add(Dense(4096, activation='relu'))
    model.add(Dense(4096, activation='relu'))
    model.add(Dense(1000, activation='softmax'))
    
    return model
  1. 編譯模型并進行訓練：
input_shape = (224, 224, 3)
vgg_model = build_vgg(input_shape)
vgg_model.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])
vgg_model.fit(train_images, train_labels, epochs=10, batch_size=32, validation_data=(validation_images, validation_labels))

這樣就可以在TensorFlow中搭建VGG模型并進行訓練了。

0 踩