Open cuienjiecv opened 6 years ago
I ran the python script "test_predicate_recognition.py" , where the obj_dets_file ?
# obj_dets: numpy.array of size: num_instance x 5 # instance: [x1, y1, x2, y2, prob, label] parser.add_argument('--obj_dets_file', dest='obj_dets_file', help='file containing object detections', default=None, type=str)
This repo does not include code for object detection since no modification is made to existing code. You may refer to repo of Faster-RCNN, and rearrange the detection results into the described format.
I ran the python script "test_predicate_recognition.py" , where the obj_dets_file ?
obj_dets_file format: [ obj_dets of image_i for image_i in images ]