我正在尝试使用Keras框架的VGG Face实现来训练我自己的数据集，该数据集包含12类人脸图像。我对训练集中数据量较少的某些类别进行了数据增强处理。
在使用resnet50进行微调后，当我尝试训练模型时，模型卡在了epoch阶段，即它无法开始训练，而是持续显示Epoch 1/50。看起来是这样的：
Layer (type) Output Shape Param # =================================================================model_1 (Model) (None, 12) 23585740 =================================================================Total params: 23,585,740Trainable params: 23,532,620Non-trainable params: 53,120_________________________________________________________________Found 1774 images belonging to 12 classes.Found 313 images belonging to 12 classes.Epoch 1/50这是我的代码：
train_data_path = 'dataset_cfps/train'validation_data_path = 'dataset_cfps/validation'#Parametresimg_width, img_height = 224, 224vggface = VGGFace(model='resnet50', include_top=False, input_shape=(img_width, img_height, 3))#vgg_model = VGGFace(include_top=False, input_shape=(224, 224, 3))last_layer = vggface.get_layer('avg_pool').outputx = Flatten(name='flatten')(last_layer)out = Dense(12, activation='sigmoid', name='classifier')(x)custom_vgg_model = Model(vggface.input, out)# Create the modelmodel = models.Sequential()# Add the convolutional base modelmodel.add(custom_vgg_model)# Add new layers# model.add(layers.Flatten())# model.add(layers.Dense(1024, activation='relu'))# model.add(BatchNormalization())# model.add(layers.Dropout(0.5))# model.add(layers.Dense(12, activation='sigmoid'))# Show a summary of the model. Check the number of trainable parametersmodel.summary()train_datagen = ImageDataGenerator( rescale=1./255, rotation_range=20, width_shift_range=0.2, height_shift_range=0.2, horizontal_flip=True, fill_mode='nearest')validation_datagen = ImageDataGenerator(rescale=1./255)train_batchsize = 16val_batchsize = 16train_generator = train_datagen.flow_from_directory( train_data_path, target_size=(img_width, img_height), batch_size=train_batchsize, class_mode='categorical')validation_generator = validation_datagen.flow_from_directory( validation_data_path, target_size=(img_width, img_height), batch_size=val_batchsize, class_mode='categorical', shuffle=True)# Compile the modelmodel.compile(loss='categorical_crossentropy', optimizer=optimizers.SGD(lr=1e-3), metrics=['acc'])# Train the modelhistory = model.fit_generator( train_generator, steps_per_epoch=train_generator.samples/train_generator.batch_size , epochs=50, validation_data=validation_generator, validation_steps=validation_generator.samples/validation_generator.batch_size, verbose=1)# Save the modelmodel.save('facenet_resnet.h5')有人知道可能的问题是什么吗？还有，我怎样才能使我的模型更好（如果有我可以做的事情的话）？欢迎提出改进建议。
回答：
等待并没有解决问题，我通过重新启动整个程序解决了这个问题。
