Question

我正在尝试微调Inception-v3，但无论我选择冻结哪一层，我都会得到随机预测。我发现其他人遇到了同样的问题：https://github.com/keras-team/keras/issues/9214。似乎问题来自于将BN层设置为不可训练的。现在我试图获取我要冻结的最后一层的输出，并将其用作以下图层的输入，然后我将训练：

train_generator = train_datagen.flow_from_directory(
                os.path.join(directory, "train_data"),
                target_size=size,
                interpolation="bilinear",
                classes=["a", "b", "c","d"],
                batch_size=1,
                shuffle=False) base_model = InceptionV3(weights='imagenet', include_top=True, input_shape=(299, 299, 3))

model_features = Model(inputs=base_model.input, outputs=base_model.get_layer(
                self.Inception_Fine_Tune_Layers[layer_freeze]).output)

#I want to use this as input 
values_train = model_features.predict_generator(train_generator, verbose=1)

然而，我得到像这样的内存错误，虽然我有12Gb，这比我需要的更多：

....
 I tensorflow/core/common_runtime/bfc_allocator.cc:696] 1 Chunks of size 3268864 totalling 3.12MiB
 I tensorflow/core/common_runtime/bfc_allocator.cc:696] 1 Chunks of size 3489024 totalling 3.33MiB
 I tensorflow/core/common_runtime/bfc_allocator.cc:696] 1 Chunks of size 4211968 totalling 4.02MiB
 I tensorflow/core/common_runtime/bfc_allocator.cc:696] 1 Chunks of size 5129472 totalling 4.89MiB
 I tensorflow/core/common_runtime/bfc_allocator.cc:700] Sum Total of in-use chunks: 3.62GiB
 I tensorflow/core/common_runtime/bfc_allocator.cc:702] Stats: 
Limit:                 68719476736
InUse:                  3886957312
MaxInUse:               3889054464
NumAllocs:                    3709
MaxAllocSize:              8388608

任何建议如何解决该问题或其他解决方法以微调Inception将是非常有帮助的。

Answer 1

我无法判断您是否已根据自己提供的内容正确预处理输入。但是，Keras提供特定于预训练网络的预处理功能，在本例中为Inception V3。

from keras.applications.inception_v3 import preprocess_input

尝试将此添加到数据生成器中作为预处理函数，如此...

train_generator = train_datagen.flow_from_directory(
            os.path.join(directory, "train_data"),
            preprocessing_function=preprocess_input,  # <---
            target_size=size,
            interpolation="bilinear",
            classes=["a", "b", "c","d"],
            batch_size=1,
            shuffle=False)

然后，您应该能够解冻所有图层，或者您想要训练的少数图层。

希望有所帮助！

Keras Inception-v3微调工作流程

1 个答案: