Getting error on Google Colab : invalid index of a 0-dim tensor. Use tensor.item() to convert a 0-dim tensor to a Python number

Gautham_SV · November 17, 2020, 7:45pm

Hi All,
Can someone please help with the below error.
I have no idea what went wrong and here is my error and code link from my Github please help in fixing the error.

github.com

Batmancity/Detection/blob/main/Code.py

from .imports import *
from .torch_imports import *
from .core import *
from .layer_optimizer import *

def cut_model(m, cut):
    return list(m.children())[:cut] if cut else [m]

def predict_to_bcolz(m, gen, arr, workers=4):
    arr.trim(len(arr))
    lock=threading.Lock()
    m.eval()
    for x,*_ in tqdm(gen):
        y = to_np(m(VV(x)).data)
        with lock:
            arr.append(y)
            arr.flush()

def num_features(m):
    c=children(m)

This file has been truncated. show original

ptrblck · November 21, 2020, 1:44am

As the error message suggests, you should use tensor.item() instead of tensor[0].
Also, don’t use the .data attribute, as it might yield unwanted side effects.