python - keras 预训练模型提供新的输入占位符

Question

我有一个经过训练的模型。像这样

model_inceptionv3_conv = InceptionV3(weights='imagenet', include_top=False)
for layer in model_inceptionv3_conv.layers:
    layer.trainable = False
x = model_inceptionv3_conv.output
x = GlobalAveragePooling2D()(x)
predictions = Dense(NB_CLASSES, activation='sigmoid', name='predictions')(x)
my_model = Model(inputs=model_inceptionv3_conv.input, outputs=predictions)
my_model.fit(...)

现在我不想为该模型提供占位符，但发生了某些值未初始化的情况。这段代码 preds = model(x) 会生成一个新图吗？

x = tf.placeholder(tf.float32, shape=(None, 299, 299,
                                          3))
preds = model(x)
sess.run(preds, feed_dict={x: x_val})

错误FailedPreconditionError:尝试使用未初始化的值batch_normalization_86/moving_mean......

Answer 1

您的错误在这里:

preds = my_model(x)

应该是:

preds = my_model.predict(x)

这是一个工作示例:

NB_CLASSES = 2
model_inceptionv3_conv = InceptionV3(weights='imagenet', include_top=False)
for layer in model_inceptionv3_conv.layers:
    layer.trainable = False
x = model_inceptionv3_conv.output
x = GlobalAveragePooling2D()(x)
predictions = Dense(NB_CLASSES, activation='softmax', name='predictions')(x)
my_model = Model(inputs=model_inceptionv3_conv.input, outputs=predictions)
test_img = np.random.rand(1,299,299,3)
preds = my_model.predict(test_img)

玩得开心!