如何获得急切模式的中间输出

时间:2018-11-20 04:12:40

标签: python tensorflow eager

我建立了转移学习模型,并试图获得中间输出。我遵循建议here之一,以获取模型的中间输出,如下所示:

20G

但是我得到一个错误:

import tensorflow as tf
from tensorflow.keras import backend as K

tf.enable_eager_execution()

base_conv = tf.keras.applications.MobileNetV2(input_shape= None, 
            alpha=1.0, depth_multiplier=1, \
            include_top=True, weights='imagenet', input_tensor=None, \
            pooling=None, classes=1000)

model = tf.keras.models.Sequential()

model.add(base_conv)

model.add(tf.keras.layers.Dense(512, activation='relu'))

model.add(tf.keras.layers.Dense(5, activation='softmax'))

# with a Sequential model
get_layer_output = K.function([model.layers[0].input],                                 
                          [model.layers[0].get_layer('Conv_1').output])

#x is the input image
layer_output = get_layer_output([x])

0 个答案:

没有答案