菜尼奥排错之merge6 = merge([drop4,up6], mode = ‘concat‘...)TypeError: ‘module‘ object is not callable

 环境版本：

Ubuntu 18.04.2 LTS

Nvidia GeForce RTX2080super CUDA Version 10.0

tensorflow-gpu 1.13.1

keras 2.2.4-tf

project https://github.com/decouples/Unet unet.py脚本文件

---

报错信息：

诸如此类：

merge6 = merge([drop4,up6], mode = 'concat'...)
TypeError: 'module' object is not callable

本人是在运行Unet时出现的此问题：

Instructions for updating:
Please use `rate` instead of `keep_prob`. Rate should be set to `rate = 1 - keep_prob`.
Traceback (most recent call last):
  File "unet.py", line 186, in <module>
    myunet.train()
  File "unet.py", line 165, in train
    model = self.get_unet()
  File "unet.py", line 129, in get_unet
    merge6 = merge([drop4,up6], mode = 'concat', concat_axis = 3)
TypeError: 'module' object is not callable

---

原因分析：

tensorflow里keras版本不同造成的，调用方法改变了，需要修改下代码即可。

---

解决方案：

1.脚本前keras.layers中由插入merge改为concatenate;

2.脚本中merge函数替换为concatenate函数，具体如下。 

#修改之前
from keras.layers import merge

merge6 = merge([drop4,up6], mode = 'concat', concat_axis = 3)
merge7 = merge([conv3,up7], mode = 'concat', concat_axis = 3)
merge8 = merge([conv2,up8], mode = 'concat', concat_axis = 3)
merge9 = merge([conv1,up9], mode = 'concat', concat_axis = 3)

#修改之后
from tensorflow.python.keras.layers import concatenate

merge6 = concatenate([drop4,up6],axis=3)
merge7 = concatenate([conv3,up7],axis=3) 
merge8 = concatenate([conv2,up8],axis=3)
merge9 = concatenate([conv1,up9],axis=3)