Issue when running code

[rakesh903]

Hi,
I am getting error when I am trying to train the model.

Below is the error.

Traceback (most recent call last):
File "D:/Projects/ML/DeepL/NLPLSTM/lstm/lst.py", line 234, in
nextBatch, nextBatchLabels = getTrainBatch()
File "D:/Projects/ML/DeepL/NLPLSTM/lstm/lst.py", line 170, in getTrainBatch
arr[i] = ids[num-1:num]
ValueError: could not broadcast input array from shape (0,250) into shape (250)

Code:

def getTrainBatch():
labels = []
arr = np.zeros([batchSize, maxSeqLength])
for i in range(batchSize):
if i % 2 == 0:
num = randint(1,11499)
labels.append([1,0])
else:
num = randint(13499,24999)
labels.append([0,1])
arr[i] = ids[num-1:num]
return arr, labels

[adelabdelli]

i got the same error, i don't know why !! are you using your own dataset ? if yes you have to change the randint value, i'd change and it works but after that i tried to re-run it but it give the same error

[adelabdelli]

@adeshpande3 please Help us

[rakesh903]

I did resolve it my self.
The shape of the input needs to be changed. Use numpy to change the shape.

Thanks

[adelabdelli]

How to reshape it , i mean from what to what ?

[roaminggypsy]

I don't know how to solve this.
Could you please explain your solution?

[adeshpande3]

If you're getting an error like "ValueError: could not broadcast input array from shape (0,250) into shape (250)", then that means your ids matrix may not be filled properly. Check to see that there are indeed values inside that matrix.

[roaminggypsy]

Thanks for your reply.

I solved this problem.
There are some typos in the negativeFiles initialization (so negativeFiles was empty) I fixed them.

Also,
In getTrainBatch():
arr[i] = ids[num-1:num]
I change to
arr[i] = ids[num-1]

[adeshpande3]

What were the typos?