When I was training data, I changed the value of evaluate_every to 100, and the original value was 500. However, there are the following errors. Can you help me solve this problem again? Thank you very much for your help.

[H0203]

When I was training data, I changed the value of evaluate_every to 100, and the original value was 500. However, there are the following errors. Can you help me solve this problem again? Thank you very much for your help.

errors： iteration 50, training loss: 6.15, Evaluating model on 250 unique 20 way one-shot learning tasks ...

UnboundLocalError Traceback (most recent call last)

in () 11 12 if i % evaluate_every == 0: ---> 13 val_acc = loader.test_oneshot(siamese_net,N_way,n_val,verbose=True) 14 print('val_acc的值为：' + val_acc) 15 if val_acc >= best: in test_oneshot(self, model, N, k, s, verbose) 67 print("Evaluating model on {} unique {} way one-shot learning tasks ...".format(k,N)) 68 for i in range(k): ---> 69 inputs, targets = self.make_oneshot_task(N,s) 70 probs = model.predict(inputs) 71 if np.argmax(probs) == np.argmax(targets): in make_oneshot_task(self, N, s, language) 51 ex1, ex2 = rng.choice(n_examples,replace=False,size=(2,)) 52 test_image = np.asarray([X[true_category,ex1,:,:]]*N).reshape(N,self.w,self.h,1) ---> 53 support_set = X[categories,indices,:,:] 54 support_set[0,:,:] = X[true_category,ex2] 55 support_set = support_set.reshape(N,self.w,self.h,1) UnboundLocalError: local variable 'indices' referenced before assignment

[H0203]

This problem can be solved by adding a new code “ global indices” in front of the code of the “indices = rng.randint(0,self.n_examples,size=(N,))” sentence.