Inference on KITTI
jtang10 opened this issue · comments
Jingning Tang commented
Hello there, I'm a student working on system level characterization of deep learning tasks and want to use GOTURN as an example for object tracking. I found your codebase is very concise and easy to understand. However, I'm not very familiar with object tracking task, so I want to know
- Can your pretrained model directly on KITTI tracking data without fine-tuning? I don't really need the inference accuracy to be optimal as long as it works well.
- If answer to the question 1 is yes, I guess all I need to do it to modify the test.py to make it work on non-OTB dataset, right?
- If not, how hard do you think is to retrain or fine-tune your pre-trained model on KITTI monocular tracking? Rough estimation is perfectly fine, I just want to get an idea of the difficulty.
Thank you for the code and any help you can provide!
Abhinav Moudgil commented
Hi, thanks for your comments! Following are my suggestions:
- Ideally, it should work fine since the object tracking task by definition is class agnostic. Training data also includes vehicle class (cars, bikes etc.).
- Yes, you just need to write a new class similar in
test.py
. - I think finetuning could yield some improvement but not sure, didn't try this.