Retraining DashcamNet with TLT

Accelerated Computing Intelligent Video Analytics TAO Toolkit
1

DashcamNet has four objects detection. Now I am going to use it for vehicle detection.
The model is good for side view detection, but not good for topdown view.
I am going to retrain with images for topdown view.
I am going to retrain for topdown view vehicles only.
Is there any concern for model accuracy? Since model is trained with four classes and I am going to retrain for only one class.
Is this ok to retrain?
What are the things I need to caution in retraining?

3

It is ok to retrain with only one class.
For topdown view objects, they may be small.
Refer to https://docs.nvidia.com/tlt/tlt-user-guide/text/faqs.html#training

In DetectNet_V2, are there any parameters that can help improve AP (average precision) on training small objects?

Following parameters can help you improve AP on smaller objects:

  • Increase num_layers of resnet
  • class_weight for small objects
  • Increase the coverage_radius_x and coverage_radius_y parameters of the bbox_rasterizer_config section for the small objects class
  • Decrease minimum_detection_ground_truth_overlap
  • Lower minimum_height to cover more small objects for evaluation
4

Yes the size is small, any issue for that?

5

For small objects, you can refer to above guide mentioned in NVIDIA TAO Documentation

6

Previously I used TLT to train detectnet_v2 with Resnet18 for one object detection.
But now I am going to retrain DashcamNet.
How about image size to retrain DashcamNet.
What is the image size I need to use for retraining?

7

Please set
output_image_width: 960
output_image_height: 544

and setting the enable_auto_resize parameter to true

Reference: NVIDIA TAO Documentation

8

Thanks a lot

10

This topic was automatically closed 60 days after the last reply. New replies are no longer allowed.