What is the minimum no. of images that I need to train LPR on my custom dataset:
Since, its hard to get annotated USA license plate images, like the CCPD(chinese) dataset, a minimum no. will be helpful.
Thanks for reaching out.
There is no minimum number of the exact datasets that we can provide. However, too small number of trained images will not enough for the model to give better performance. We would recommend you use the recommended number of datasets used for the project, which are 300320 images.
This thread will no longer be monitored since we have provided a solution. If you need any additional information from Intel, please submit a new question.