tf.cond报错Initializer for variable is from inside control-flow construct such as a loop or condition

完整报错信息：ValueError: Initializer for variable lambda_5/cond/mrcnn_mask_conv1/kernel/ is from inside a control-flow construct, such as a loop or conditional. When creating a variable inside a loop or conditional, use a lambda as the initializer.

解决思路：这个报错的原因是在tf.cond中有变量的初始化，所以只要把初始化的部分单独提出来先用变量来接收，然后把变量放入tf.cond的选择部分即可。

参考网站：

https://*.com/questions/48515034/keras-tensorflow-initializer-for-variable-is-from-inside-a-control-flow-con

举例子：

def ff_true():
    mrcnn_mask = build_fpn_mask_graph(rois, mrcnn_feature_maps,
       config.IMAGE_SHAPE,
       config.MASK_POOL_SIZE,
       config.NUM_CLASSES)

def ff_false():
    return tf.zeros_like(target_mask)

mrcnn_mask = KL.Lambda(lambda x: tf.cond(tf.equal(tf.reduce_mean(x), 0), 
    ff_true, ff_true)) (rois)

上面会有报错，修改成如下形式无报错：

a = build_fpn_mask_graph(rois, mrcnn_feature_maps,
    config.IMAGE_SHAPE,
    config.MASK_POOL_SIZE,
    config.NUM_CLASSES)   
def ff_true():
    return a
def ff_false():
    return tf.zeros_like(target_mask)

mrcnn_mask = KL.Lambda(lambda x: tf.cond(tf.equal(tf.reduce_mean(x), 0), 
    ff_true, ff_true)) (rois)

可以看到先用a来赋值，完成计算后，再将其放入tf.cond中作为选择项。