using tensorflow:feed_dict,ValueError: setting an array element with a sequence

Asked May 07 '18 at 06:43

Active May 07 '18 at 07:08

Viewed 27 times

for i in range(iter_time):  
    for step in range(len(batch_index)-1):
        _,loss_=sess.run([train_op,loss], feed_dict={X:train_x[batch_index[step]:batch_index[step+1]], Y:train_y[batch_index[step]:batch_index[step+1]]})  
    if i % 100 == 0:
        print('iter:',i,'loss:',loss_)

where train_x[batch_index[step]:batch_index[step+1]] is a list with shape (80, 15, 44). I have tried to convert train_x to np.array but it still not work.

edited May 07 '18 at 07:08

Francesco Montesano

8,485
2
40
64

asked May 07 '18 at 06:43

YIHAN DONG

Please format your code so that it is readable. – Dragonthoughts May 07 '18 at 06:50
I have format my code just now. – YIHAN DONG May 07 '18 at 06:54
This is a numpy error. See https://stackoverflow.com/questions/4674473/valueerror-setting-an-array-element-with-a-sequence and https://stackoverflow.com/questions/13310347/numpy-valueerror-setting-an-array-element-with-a-sequence-this-message-may-app/39114489 – walkerlala May 07 '18 at 12:40

using tensorflow:feed_dict,ValueError: setting an array element with a sequence

0 Answers0