如何在迁移学习中使用初始层

【问题标题】：How to use inception layer in transfer learning如何在迁移学习中使用初始层
【发布时间】：2019-12-17 19:12:03
【问题描述】：

我想做迁移学习，我正在加载这些权重文件，但现在我不知道如何使用它的层来训练我的自定义模型。任何帮助将不胜感激下面是我试过的示例代码：

local_weights_file= '/tmp/inception_v3_weights_tf_dim_ordering_tf_kernels_notop.h5'

pre_trained_model = InceptionV3(input_shape = (150, 150, 3),
include_top = False,
weights = None)

pre_trained_model.load_weights(local_weights_file)

for layer in pre_trained_model.layers:
layer.trainable = False

【问题讨论】：

标签： python machine-learning deep-learning

【解决方案1】：

您需要将最后一层的输出输入到最终模型中。像这样的东西应该可以工作

last_layer = pre_trained_model.get_layer('mixed7')
last_output = last_layer.output



# Flatten the output layer to 1 dimension
x = layers.Flatten()(last_output)
# Add a fully connected layer with 1,024 hidden units and ReLU activation
x = layers.Dense(1024, activation='relu')(x)
# Add a dropout rate of 0.2
x = layers.Dropout(0.2)(x)                  
# Add a final sigmoid layer for classification
x = layers.Dense  (1, activation='sigmoid')(x)           

model = Model( pre_trained_model.input, x)

【讨论】：