文件列表:

000001.jpg (7506, 2019-09-20)
CenterNet (0, 2019-09-20)
CenterNet\.travis.yml (657, 2019-09-20)
CenterNet\LICENSE (1090, 2019-09-20)
CenterNet\NOTICE (6181, 2019-09-20)
CenterNet\change.sh (357, 2019-09-20)
CenterNet\data (0, 2019-09-20)
CenterNet\exp (0, 2019-09-20)
CenterNet\experiments (0, 2019-09-20)
CenterNet\experiments\ctdet_coco_dla_1x.sh (430, 2019-09-20)
CenterNet\experiments\ctdet_coco_dla_2x.sh (717, 2019-09-20)
CenterNet\experiments\ctdet_coco_hg.sh (504, 2019-09-20)
CenterNet\experiments\ctdet_coco_resdcn101.sh (462, 2019-09-20)
CenterNet\experiments\ctdet_coco_resdcn18.sh (499, 2019-09-20)
CenterNet\experiments\ctdet_pascal_dla_384.sh (288, 2019-09-20)
CenterNet\experiments\ctdet_pascal_dla_512.sh (347, 2019-09-20)
CenterNet\experiments\ctdet_pascal_resdcn101_384.sh (371, 2019-09-20)
CenterNet\experiments\ctdet_pascal_resdcn101_512.sh (423, 2019-09-20)
CenterNet\experiments\ctdet_pascal_resdcn18_384.sh (354, 2019-09-20)
CenterNet\experiments\ctdet_pascal_resdcn18_512.sh (402, 2019-09-20)
CenterNet\experiments\ddd_3dop.sh (249, 2019-09-20)
CenterNet\experiments\ddd_sub.sh (251, 2019-09-20)
CenterNet\experiments\exdet_coco_dla.sh (418, 2019-09-20)
CenterNet\experiments\exdet_coco_hg.sh (460, 2019-09-20)
CenterNet\experiments\multi_pose_dla_1x.sh (401, 2019-09-20)
CenterNet\experiments\multi_pose_dla_3x.sh (699, 2019-09-20)
CenterNet\experiments\multi_pose_hg_1x.sh (452, 2019-09-20)
CenterNet\experiments\multi_pose_hg_3x.sh (743, 2019-09-20)
CenterNet\images (0, 2019-09-20)
CenterNet\images\004504.jpg (103637, 2019-09-20)
CenterNet\images\NOTICE (917, 2019-09-20)
CenterNet\images\bird_000002.JPEG (3127, 2019-09-20)
CenterNet\models (0, 2019-09-20)
... ...

# kitti_eval `evaluate_object_3d_offline.cpp`evaluates your KITTI detection locally on your own computer using your validation data selected from KITTI training dataset, with the following metrics: - overlap on image (AP) - oriented overlap on image (AOS) - overlap on ground-plane (AP) - overlap in 3D (AP) Compile `evaluate_object_3d_offline.cpp` with dependency of Boost and Linux `dirent.h` (You should already have it under most Linux). Run the evalutaion by: ./evaluate_object_3d_offline groundtruth_dir result_dir Note that you don't have to detect over all KITTI training data. The evaluator only evaluates samples whose result files exist. ### Updates - June, 2017: * Fixed the bug of detection box filtering based on min height according to KITTI's note on 25.04.2017.

近期下载者：

相关文件：

评论：[我要评论] [举报此文件]

收藏者：