低准确度-转移学习+瓶颈keras tensorflow(resnet50)

我正在尝试转移学习/瓶颈 keras /谷歌实验室笔记本上的tensorflow。我的问题是准确率没有超过6%(Kaggle的狗品种挑战赛,120个等级,数据由 datagen.flow_from_directory )

下面是我的代码,有什么我遗漏的吗?

tr_model=ResNet50(include_top=False,
                  weights='imagenet',
                 input_shape = (224, 224, 3),)

datagen = ImageDataGenerator(rescale=1. / 255)

#### Training ####
train_generator = datagen.flow_from_directory(train_data_dir,
                                                    target_size=(image_size,image_size),
                                                    class_mode=None,
                                                    batch_size=batch_size,
                                                    shuffle=False)
bottleneck_features_train = tr_model.predict_generator(train_generator)
train_labels = to_categorical(train_generator.classes , num_classes=num_classes)

#### Validation ####
validation_generator = datagen.flow_from_directory(validation_data_dir, 
                                                    target_size=(image_size,image_size),
                                                    class_mode=None,
                                                    batch_size=batch_size,
                                                    shuffle=False)
bottleneck_features_validation = tr_model.predict_generator(validation_generator)
validation_labels = to_categorical(validation_generator.classes, num_classes=num_classes)

#### Model creation ####
model = Sequential()
model.add(Flatten(input_shape=bottleneck_features_train.shape[1:]))
model.add(Dense(num_class, activation='softmax'))

model.compile(optimizer='rmsprop',
              loss='categorical_crossentropy',
              metrics=['accuracy'])

history = model.fit(bottleneck_features_train, train_labels,
                    epochs=30,
                    batch_size=batch_size,
                    validation_data=(bottleneck_features_validation, validation_labels))

我得到val\u acc=0.0592

当我在最后一层使用ResNet50时,我得到了82%的分数。

有人能发现我的代码有什么问题吗。