Element missing from middle of dataset

[liocoa]

Describe the bug I am training a custom model with a set of 162 training images. When I run model.fit, it works until I reach image 95, when it throws a "single positional indexer is out-of-bounds" exception. Upon closer inspection, attempting to index that item manually yields the same exception. Every other index from 0 to 161 works, with the exception of 95. What is happening?

Code and Data

for n in range(len(dataset)): try: dataset[n] print(f'{n}/{len(dataset)}') except: print("Missing!")

This yields:

0/162 1/162 2/162 ... 93/162 94/162 Missing! 96/162 97/162 ... 159/162 160/162 161/162

Environment:

• OS: Google Colab
• Python version: 3.6.9
• Detecto version: 1.2.0
• torch version: 1.7.0+cu101
• torchvision version: 0.8.1+cu101

[alankbi]

I would guess most likely there's an issue with the XML file or image file for that specific index. Could you double-check that everything matches correctly for that index?