Database collection error

cespedesk · December 25, 2020, 3:45am

I have followed the steps in Hello AI World to collect my own dataset. Now I am trying to train it but it crashes with this error.
IndexError: too many indices for array: array is 1-dimensional, but 2 were indexed
Does anybody know why??

AastaLLL · December 28, 2020, 7:24am

Hi,

The error occurs when the PyTorch parses the database file.
Please check if you follow the data format listed in our tutorial.

For example, here is the format for the classification label:

github.com

dusty-nv/jetson-inference/blob/master/docs/pytorch-collect.md#creating-the-label-file

<img src="https://github.com/dusty-nv/jetson-inference/raw/master/docs/images/deep-vision-header.jpg" width="100%">
<p align="right"><sup><a href="pytorch-plants.md">Back</a> | <a href="pytorch-ssd.md">Next</a> | </sup><a href="../README.md#hello-ai-world"><sup>Contents</sup></a>
<br/>
<sup>Transfer Learning - Classification</sup></s></p>

# Collecting your own Classification Datasets

In order to collect your own datasets for training customized models to classify objects or scenes of your choosing, we've created an easy-to-use tool called `camera-capture` for capturing and labeling images on your Jetson from live video:

<img src="https://github.com/dusty-nv/jetson-inference/raw/python/docs/images/pytorch-collection.jpg" >

The tool will create datasets with the following directory structure on disk:

```
‣ train/
	• class-A/
	• class-B/
	• ...
‣ val/
	• class-A/

This file has been truncated. show original

Thanks.

dusty_nv · December 28, 2020, 6:53pm

Hi @cespedesk, I take it that you are training a detection model. Are there any warnings printed out before it crashes? Like ‘warning - failed to find any bounding boxes for image xyz’ or similar.

You can better determine which image is causing the error by uncommenting this line of code:

pytorch-ssd/voc_dataset.py at e7b5af50a157c50d3bab8f55089ce57c2c812f37 · dusty-nv/pytorch-ssd · GitHub

If you can’t find the source of the error, you can upload your dataset to Google Drive (or similar) and I can give it a try here to find the issue.

cespedesk · December 29, 2020, 11:32pm

My bad wrote label instead of labels. It took me 4 days to realized it.