I am training pre-trained SSD-InceptionV2-Coco to detect the "car",

which is one of the classes in mscoco label.

I train the model with ~50k sample from KITTI, 500k iteration with batch size 2.

I followed this script to generate tfrecord file.

Then I test both original pre-trained model and my trained model with one video.

The performance of my trained model is worse. More missing detected results.

One thing I found recently is the classification_loss/localization_loss increases when AvgNumGroundtruthBoxesPerImage increases.

enter image description here

enter image description here


enter image description here

Another thing I found is the more ground truth boxes per image I have,

the less average num positive anchors per image I have.

This bothers me because if the number of anchors generated per image is fixed,

more ground truth boxes should provide more positive anchors per image.

So I wonder where to find the root cause.

Any suggestion is welcome.

Thank you for precious time on my question.


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.