Allocate the amount of photos

andy8902 · September 27, 2020, 5:53am

I use this web(jetson-inference/pytorch-collect.md at master · dusty-nv/jetson-inference · GitHub)for training. How do I allocate the amount of photos of train, test and val?

AastaLLL · September 28, 2020, 5:48am

Hi,

Based on the follow document, it’s recommended to collect at least 100 images for training.

github.com

dusty-nv/jetson-inference/blob/master/docs/pytorch-collect.md#collecting-data

<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

In general, we reserve 1/5 for testing and validation.
Thanks.

andy8902 · October 2, 2020, 3:21pm

Is the method(jetson-inference/pytorch-collect.md at master · dusty-nv/jetson-inference · GitHub) training googlenet same?

AastaLLL · October 19, 2020, 4:02am

Hi,

Suppose yes.

This is a general frameworks for collecting training dataset.
It can be used for both the default resnet18 and googlenet.

Thanks.