Im pretty new to Siamese Neural Networks and recently found this example and Colab notebook.
When running the code i get the following error:
IndexError: invalid index of a 0-dim tensor. Use tensor.item() to convert a 0-dim tensor to a Python number
on the line:
result=torch.max(res,1)[1][0][0][0].data[0].tolist()
I found something about the tensor.item() but i really just don't know how to use it here.
EDIT:
test_dataloader = DataLoader(test_dataset,num_workers=6,batch_size=1,shuffle=True)
accuracy=0
counter=0
correct=0
for i, data in enumerate(test_dataloader,0):
x0, x1 , label = data
# onehsot applies in the output of 128 dense vectors which is then converted to 2 dense vectors
output1,output2 = model(x0.to(device),x1.to(device))
res=torch.abs(output1.cuda() - output2.cuda())
label=label[0].tolist()
label=int(label[0])
result=torch.max(res,1)[1][0][0][0].data.item().tolist()
if label == result:
correct=correct+1
counter=counter+1
# if counter ==20:
# break
accuracy=(correct/len(test_dataloader))*100
print("Accuracy:{}%".format(accuracy))
Thats the code i get the error on.
What this error message says is that you're trying to index into an array which has just one item in it. For example,
In [10]: aten = torch.tensor(2)
In [11]: aten
Out[11]: tensor(2)
In [12]: aten[0]
---------------------------------------------------------------------------
IndexError Traceback (most recent call last)
<ipython-input-12-5c40f6ab046a> in <module>
----> 1 aten[0]
IndexError: invalid index of a 0-dim tensor. Use tensor.item() to convert a 0-dim
tensor to a Python number
In the above case, aten is a tensor with just a single number in it. So, using an index (or more) to retrieve that number throws the IndexError.
The correct way to extract the number(item) out of the tensor is to use tensor.item(), here aten.item() as in:
In [14]: aten.item()
Out[14]: 2