Syntax Error: invalid syntax

[sungminha]

I am using the following:

CentOS 6.10
Cuda 9.0
Tensorflow 1.10.0
Keras 2.2.0
Python 3.6

I am getting the following error:

Using TensorFlow backend.
/scratch/hasm/conda/envs/py3_6_dunet/lib/python3.6/site-packages/tensorflow/python/framework/dtypes.py:523: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
_np_qint8 = np.dtype([("qint8", np.int8, 1)])
/scratch/hasm/conda/envs/py3_6_dunet/lib/python3.6/site-packages/tensorflow/python/framework/dtypes.py:524: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
_np_quint8 = np.dtype([("quint8", np.uint8, 1)])
/scratch/hasm/conda/envs/py3_6_dunet/lib/python3.6/site-packages/tensorflow/python/framework/dtypes.py:525: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
_np_qint16 = np.dtype([("qint16", np.int16, 1)])
/scratch/hasm/conda/envs/py3_6_dunet/lib/python3.6/site-packages/tensorflow/python/framework/dtypes.py:526: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
_np_quint16 = np.dtype([("quint16", np.uint16, 1)])
/scratch/hasm/conda/envs/py3_6_dunet/lib/python3.6/site-packages/tensorflow/python/framework/dtypes.py:527: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
_np_qint32 = np.dtype([("qint32", np.int32, 1)])
/scratch/hasm/conda/envs/py3_6_dunet/lib/python3.6/site-packages/tensorflow/python/framework/dtypes.py:532: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
np_resource = np.dtype([("resource", np.ubyte, 1)])
Traceback (most recent call last):
File "Stroke_segment.py", line 4, in
from Statistics import *
File "/scratch/hasm/Data/Lesion/Unet_Test/D-UNet/Statistics.py", line 106
-K.mean(1-alpha)*K.pow(pt_0,gamma)*K.log(1. -pt_0),axis=-1)
^
SyntaxError: invalid syntax

Do you have any suggestion how to debug this?

[jcfszxc]

line 106
true is : -K.mean((1-alpha)*K.pow(pt_0,gamma)*K.log(1. -pt_0),axis=-1)
wrong is : -K.mean(1-alpha)*K.pow(pt_0,gamma)*K.log(1. -pt_0),axis=-1)

code lost a '('

you need to add it.

but I still have some problem at line 102 "y_pred = K.clip(y_pred, K.epsilon())"

I guess this line may not be necessary, so I commented it out