Dataset for ReidentificanNet

Accelerated Computing Intelligent Video Analytics TAO Toolkit
1

Please provide complete information as applicable to your setup.

• Hardware Platform (Jetson / GPU) RTX A2000
• DeepStream Version 6.3
• JetPack Version (valid for Jetson only)
• TensorRT Version 8.6.1
• NVIDIA GPU Driver Version (valid for GPU only)
• Issue Type( questions, new requirements, bugs) questions

I want to create a dataset to train ReidentificationNet for vehicle reidentification from a single camera. How should I name the images? 0001_c1s1_01_00.jpg. What I can understand from the docs is that 0001 in the object_id, c1 camera id should be the same for me, what should be the s1 value?

3

Please refer to https://docs.nvidia.com/tao/tao-toolkit/text/data_annotation_format.html#reidentification-market1501-format.

For example, the image 0001_c1s1_01_00.jpg is from the first sequence s1 of camera c1. 01 indicates the first frame in the sequence c1s1 . 0001 is the unique ID assigned to the object. The contents after the third _ are ignored.

You can also find some info from tao_pytorch_backend/nvidia_tao_pytorch/cv/re_identification/dataloader/datasets/market1501.py at dc07b02eb78c2eb868315107892b466496e55a0f · NVIDIA/tao_pytorch_backend · GitHub.
and
Missing Value Error in Training Re-Identification Net with TAO Toolkit - #19 by Morganh.

4

There is no update from you for a period, assuming this is not an issue anymore. Hence we are closing this topic. If need further support, please open a new one. Thanks