Open chengjianhong opened 5 years ago
I have the same error
hello I have also the same error !!!
Anyone solved it?
I solved this by using
y_core=K.sum(tf.gather(y_true_f, [1,3],axis =1),axis=1)
p_core=K.sum(tf.gather(y_pred_f, [1,3],axis =1),axis=1)
instead of
y_core=K.sum(y_true_f[:,[1,3]],axis=1)
p_core=K.sum(y_pred_f[:,[1,3]],axis=1)
in losses.py
I solved this by using
y_core=K.sum(tf.gather(y_true_f, [1,3],axis =1),axis=1) p_core=K.sum(tf.gather(y_pred_f, [1,3],axis =1),axis=1)
instead of
y_core=K.sum(y_true_f[:,[1,3]],axis=1) p_core=K.sum(y_pred_f[:,[1,3]],axis=1)
in losses.py
I'm still get the error, with Keras 2.1.5 what version you are using?
Hi, I found the TypeError while run train.py. the detail is as follows: