我正在尝试训练具有2个输出的张量流模型，每个输出都有损失函数。一个叫做“ contour_segmentation”-可以很好地处理categorical_crossentropy损失，另一个叫做“边界”，为此我定义了自己的自定义损失函数。
我的自定义丢失看起来像这样：
def borders_loss_calc(y_true, y_pred):
multi = tf.multiply(y_true, y_pred)
sum_multi = tf.reduce_sum(multi)
return sum_multi
y_pred和y_true均为[batch_size, 384*384*4]的形式。
（通常我使用batch_size=2，因为我认为这是很多数字）
很简单，所以我想-但是我遇到了真正的麻烦，无法在任何地方找到问题的答案。
我的相关实验：
当我在损失函数之外的数据上应用此简单代码时- 它在tensorflow中效果很好（显然在numpy中）：
当我将损失定义为简单时：
def borders_loss_calc(y_true, y_pred):
sum_pred = tf.reduce_sum(y_pred)
return sum_pred
有效！
因此，可以定义损耗的方式和其中的功能都可以，但是它不能一起工作，并且很难在“ fit_generator”功能的执行中进行调试！
非常感谢尝试提供帮助的人！
完整的输出调试消息是：
2019-02-03 18:26:21.875161: W tensorflow/core/framework/op_kernel.cc:1273] OP_REQUIRES failed at reduction_ops_common.h:155 : Invalid argument: Invalid reduction dimension (2 for input with 2 dimension(s)
Traceback (most recent call last):
File "C:\Program Files\JetBrains\PyCharm Community Edition 2018.3.1\helpers\pydev\pydevd.py", line 1741, in <module>
main()
File "C:\Program Files\JetBrains\PyCharm Community Edition 2018.3.1\helpers\pydev\pydevd.py", line 1735, in main
globals = debugger.run(setup['file'], None, None, is_module)
File "C:\Program Files\JetBrains\PyCharm Community Edition 2018.3.1\helpers\pydev\pydevd.py", line 1135, in run
pydev_imports.execfile(file, globals, locals) # execute the script
File "C:\Program Files\JetBrains\PyCharm Community Edition 2018.3.1\helpers\pydev\_pydev_imps\_pydev_execfile.py", line 18, in execfile
exec(compile(contents+"\n", file, 'exec'), glob, loc)
File "C:/work/code/segnet-contour/src/kobis_testing/new_testing/train_borders.py", line 179, in <module>
tmh.train()
File "C:/work/code/segnet-contour/src/kobis_testing/new_testing/train_borders.py", line 137, in train
verbose=1, use_multiprocessing=False, callbacks=[tensorboard])
File "C:\Users\kobih\Anaconda3\envs\python3\lib\site-packages\keras\legacy\interfaces.py", line 91, in wrapper
return func(*args, **kwargs)
File "C:\Users\kobih\Anaconda3\envs\python3\lib\site-packages\keras\engine\training.py", line 1418, in fit_generator
initial_epoch=initial_epoch)
File "C:\Users\kobih\Anaconda3\envs\python3\lib\site-packages\keras\engine\training_generator.py", line 217, in fit_generator
class_weight=class_weight)
File "C:\Users\kobih\Anaconda3\envs\python3\lib\site-packages\keras\engine\training.py", line 1217, in train_on_batch
outputs = self.train_function(ins)
File "C:\Users\kobih\Anaconda3\envs\python3\lib\site-packages\keras\backend\tensorflow_backend.py", line 2715, in __call__
return self._call(inputs)
File "C:\Users\kobih\Anaconda3\envs\python3\lib\site-packages\keras\backend\tensorflow_backend.py", line 2675, in _call
fetched = self._callable_fn(*array_vals)
File "C:\Users\kobih\Anaconda3\envs\python3\lib\site-packages\tensorflow\python\client\session.py", line 1439, in __call__
run_metadata_ptr)
File "C:\Users\kobih\Anaconda3\envs\python3\lib\site-packages\tensorflow\python\framework\errors_impl.py", line 528, in __exit__
c_api.TF_GetCode(self.status.status))
tensorflow.python.framework.errors_impl.InvalidArgumentError: Invalid reduction dimension (2 for input with 2 dimension(s)
[[{{node loss/borders_loss/Sum}} = Sum[T=DT_FLOAT, Tidx=DT_INT32, _class=["loc:@training/Adam/gradients/loss/borders_loss/Sum_grad/Tile"], keep_dims=false, _device="/job:localhost/replica:0/task:0/device:GPU:0"](loss/borders_loss/Mul, loss/borders_loss/Const)]]
[[{{node loss/contour_segmentation_loss/Mean_2/_1647}} = _Recv[client_terminated=false, recv_device="/job:localhost/replica:0/task:0/device:CPU:0", send_device="/job:localhost/replica:0/task:0/device:GPU:0", send_device_incarnation=1, tensor_name="edge_12857_loss/contour_segmentation_loss/Mean_2", tensor_type=DT_FLOAT, _device="/job:localhost/replica:0/task:0/device:CPU:0"]()]]