NVIDIA-AI-IOT / face-mask-detection

Face Mask Detection using NVIDIA Transfer Learning Toolkit (TLT) and DeepStream for COVID-19
MIT License
241 stars 94 forks source link

How to more counts for no_mask and less count for mask while generating dataset #26

Open Samjith888 opened 3 years ago

Samjith888 commented 3 years ago

Thank you for your great work.

How to generate dataset with following counts by using "python3 data2kitti.py"?

mask : 6000 no_mask : 9000

I just noticed that "--category-limit" is for setting the limit for both classes together, but i need to assign a different count for each classes like i mentioned above