如何正确训练VGG16 Keras

Question

我正在尝试重新训练VGG16来对乐高图像进行分类。然而，我的模型的准确率很低(在20%之间)。我做错了什么？可能是FC号错了，或者是我的ImageDataGenerator。我有大约。每个类2k个图像，总共6个类。

如何创建模型：

def vgg16Model(self,image_shape,num_classes):
    model_VGG16 = VGG16(include_top = False, weights = None)
    model_input = Input(shape = image_shape, name = 'input_layer')
    output_VGG16_conv = model_VGG16(model_input)
    #Init of FC layers
    x = Flatten(name='flatten')(output_VGG16_conv)
    x = Dense(256, activation = 'relu', name = 'fc1')(x)
    output_layer = Dense(num_classes,activation='softmax',name='output_layer')(x)
    vgg16 = Model(inputs = model_input, outputs = output_layer)
    vgg16.compile(loss = 'categorical_crossentropy', optimizer = 'adam', metrics = ['accuracy'])
    vgg16.summary()
    return vgg16

我正在创建ImageDataGenerator并进行培训：

path = "real_Legos_images/trainable_classes"
evaluate_path = "real_Legos_images/evaluation"
NN = NeuralNetwork()
gen = ImageDataGenerator(rotation_range=40, width_shift_range=0.02, shear_range=0.02,height_shift_range=0.02, horizontal_flip=True, fill_mode='nearest')

train_generator = gen.flow_from_directory(os.path.abspath(os.path.join(path)), 
                target_size = (224,224), color_mode = "rgb", batch_size = 16, class_mode='categorical')

validation_generator = gen.flow_from_directory(os.path.abspath(os.path.join(evaluate_path)),
                target_size = (224,224), color_mode = "rgb", batch_size = 16, class_mode='categorical')

STEP_SIZE_TRAIN = train_generator.n//train_generator.batch_size
num_classes = len(os.listdir(os.path.abspath(os.path.join(path))))
VGG16 = NN.vgg16Model((224, 224, 3), num_classes)

VGG16.save_weights('weights.h5')
VGG16.fit_generator(train_generator, validation_data = validation_generator, validation_steps = validation_generator.n//validation_generator.batch_size,
                steps_per_epoch = STEP_SIZE_TRAIN, epochs = 50)

Answer 1

带有参数include_top = False的VGG16模型将返回512维特征映射。通常，我们应该首先在它后面添加一个GlobalAveragePooling2D或GlobalMaxPooling2D层，然后将它展平为一个一维数组。否则，您将得到一个太长而无法容纳的数组。

Answer 2

您已经将VGG的weight属性设置为'None‘，这意味着您的网络是用随机权重初始化的。这意味着您没有使用预先训练好的权重。因此，我建议尝试将权重设置为' imagenet‘，这样您就可以使用VGG网络，其权重是在imagenet数据集上预先训练的：

model_VGG16 = VGG16(include_top=False, weights='imagenet')