search

VisionLearningGroup / R-C3D

code for R-C3D
MIT License
254 stars 94 forks source link

How to get the result for a new input video, once the model is trained and tested. #47

Closed viswalal closed 5 years ago

viswalal commented 5 years ago

Once I train and test the model, How to use the model for getting the detection result for new input video? Lets say, I have trained it for my custom dataset and evaluated the performance. How to deploy it for detection.

viswalal commented 5 years ago

Got the solution. We can Convert the videos to frames first, as we do for training. ( Change the script to remove those portions, which are looking for annotation). Then generate roidb data by running generate_roidb_512_full.py . Here also, remove the portion which reads annotation. Then run script_test.sh. It will give the result of detection in log file.