python - Theano 'Expected an array-like object, but found a Variable': Using scan & categorical_crossentropy -

i'm trying sum multiple loss in theano can't make work. i'm using categorical crossentroy.

here code:

import numpy np  import theano import theano.tensor t   answers = t.ivector() temp = t.scalar() predictions = t.matrix()  def loss_acc(curr_ans,curr_pred, loss):     temp= t.nnet.categorical_crossentropy(curr_pred.dimshuffle('x',0), t.stack([curr_ans]))[0]     return temp + loss    outputs, updates = theano.scan(fn = loss_acc,                                 sequences = [answers, predictions],                                 outputs_info = [np.float64(0.0)],                                                 n_steps = 5)  loss = outputs[-1]  loss_cal = theano.function(inputs = [answers, predictions], outputs = [loss])  #here i'm generating random data see if can make code work max_nbr = 5 pred = [] in range(0, max_nbr):     temp = np.ones(8)     temp[i] = temp[i] + 5     temp = temp/sum(temp)     pred.append(temp)   answers = [] in range(0, max_nbr):     answers.append(pred[i].argmax())  loss = loss_cal(answers, predictions) print(loss) 

the error i'm getting

expected array-like object, found variable: typeerror: ('bad input argument theano function name "main.py:89" @ index1(0-based)', expected array-like object found variable: maybe trying call function on (possibly shared) variable instead of numeric array? 

i don't why code doesn't work, can explain me? lot!

i found problem, it's stupid one.

loss = loss_cal(answers, predictions) 

this wrong, predictions theano matrix, should have been using pred.

pred = [] in range(0, max_nbr):     temp = np.ones(8)     temp[i] = temp[i] + 5     temp = temp/sum(temp)     pred.append(temp) 

it works loss = loss_cal(answers, pred) thanks anyway