文件列表:

CMakeLists.txt (2012, 2019-01-10)
CONTRIBUTING.md (1449, 2019-01-10)
FAQ.md (3484, 2019-01-10)
GETTING_STARTED.md (6217, 2019-01-10)
INSTALL.md (8924, 2019-01-10)
LICENSE (10255, 2019-01-10)
MODEL_ZOO.md (120112, 2019-01-10)
Makefile (491, 2019-01-10)
NOTICE (1344, 2019-01-10)
cmake (0, 2019-01-10)
cmake\Summary.cmake (1020, 2019-01-10)
cmake\legacy (0, 2019-01-10)
cmake\legacy\Cuda.cmake (9531, 2019-01-10)
cmake\legacy\Dependencies.cmake (1341, 2019-01-10)
cmake\legacy\Modules (0, 2019-01-10)
cmake\legacy\Modules\FindCuDNN.cmake (2100, 2019-01-10)
cmake\legacy\Summary.cmake (940, 2019-01-10)
cmake\legacy\Utils.cmake (10724, 2019-01-10)
cmake\legacy\legacymake.cmake (1621, 2019-01-10)
configs (0, 2019-01-10)
configs\04_2018_gn_baselines (0, 2019-01-10)
configs\04_2018_gn_baselines\e2e_mask_rcnn_R-101-FPN_2x_gn.yaml (1693, 2019-01-10)
configs\04_2018_gn_baselines\e2e_mask_rcnn_R-101-FPN_3x_gn.yaml (1693, 2019-01-10)
configs\04_2018_gn_baselines\e2e_mask_rcnn_R-50-FPN_2x_gn.yaml (1691, 2019-01-10)
configs\04_2018_gn_baselines\e2e_mask_rcnn_R-50-FPN_3x_gn.yaml (1691, 2019-01-10)
configs\04_2018_gn_baselines\mask_rcnn_R-50-FPN_1x_gn.yaml (2258, 2019-01-10)
configs\04_2018_gn_baselines\scratch_e2e_mask_rcnn_R-101-FPN_3x_gn.yaml (1596, 2019-01-10)
configs\04_2018_gn_baselines\scratch_e2e_mask_rcnn_R-50-FPN_3x_gn.yaml (1595, 2019-01-10)
configs\12_2017_baselines (0, 2019-01-10)
configs\12_2017_baselines\e2e_faster_rcnn_R-101-FPN_1x.yaml (902, 2019-01-10)
configs\12_2017_baselines\e2e_faster_rcnn_R-101-FPN_2x.yaml (905, 2019-01-10)
configs\12_2017_baselines\e2e_faster_rcnn_R-50-C4_1x.yaml (821, 2019-01-10)
configs\12_2017_baselines\e2e_faster_rcnn_R-50-C4_2x.yaml (821, 2019-01-10)
configs\12_2017_baselines\e2e_faster_rcnn_R-50-FPN_1x.yaml (900, 2019-01-10)
configs\12_2017_baselines\e2e_faster_rcnn_R-50-FPN_2x.yaml (903, 2019-01-10)
... ...

# Cascade R-CNN: Delving into High Quality Object Detection by Zhaowei Cai and Nuno Vasconcelos This repository is written by Zhaowei Cai at UC San Diego, on the base of [Detectron](https://github.com/facebookresearch/Detectron) @ [e8942c8](https://github.com/facebookresearch/Detectron/tree/e8942c882abf6e28fe68a626ec55028c9bdfe1cf). ## Introduction This repository re-implements Cascade R-CNN on the base of [Detectron](https://github.com/facebookresearch/Detectron). Very consistent gains are available for all tested models, regardless of baseline strength. Please follow [Detectron](https://github.com/facebookresearch/Detectron) on how to install and use Detectron-Cascade-RCNN. It is also recommended to use our original implementation, [cascade-rcnn](https://github.com/zhaoweicai/cascade-rcnn) based on Caffe, and the third-party implementation, [mmdetection](https://github.com/open-mmlab/mmdetection) based on PyTorch and [tensorpack](https://github.com/tensorpack/tensorpack/tree/master/examples/FasterRCNN) based on TensorFlow. ## Citation If you use our code/model/data, please cite our paper: ``` @inproceedings{cai18cascadercnn, author = {Zhaowei Cai and Nuno Vasconcelos}, Title = {Cascade R-CNN: Delving into High Quality Object Detection}, booktitle = {CVPR}, Year = {2018} } ``` and Detectron: ``` @misc{Detectron2018, author = {Ross Girshick and Ilija Radosavovic and Georgia Gkioxari and Piotr Doll\'{a}r and Kaiming He}, title = {Detectron}, howpublished = {\url{https://github.com/facebookresearch/detectron}}, year = {2018} } ``` ## Benchmarking ### End-to-End Faster & Mask R-CNN Baselines

backbone	type	lr schd	im/ gpu	box AP	box AP50	box AP75	mask AP	mask AP50	mask AP75	download links
R-50-FPN-baseline	Faster	1x	2	36.7	58.4	39.6	-	-	-	model | boxes
R-50-FPN-cascade	Faster	1x	2	40.9	59.0	44.6	-	-	-	model | boxes
R-101-FPN-baseline	Faster	1x	2	39.4	61.2	43.4	-	-	-	model | boxes
R-101-FPN-cascade	Faster	1x	2	42.8	61.4	46.1	-	-	-	model | boxes
X-101-***x4d-FPN-baseline	Faster	1x	1	41.5	63.8	44.9	-	-	-	model | boxes
X-101-***x4d-FPN-cascade	Faster	1x	1	45.4	***.0	49.8	-	-	-	model | boxes
X-101-32x8d-FPN-baseline	Faster	1x	1	41.3	63.7	44.7	-	-	-	model | boxes
X-101-32x8d-FPN-cascade	Faster	1x	1	44.7	63.7	48.8	-	-	-	model | boxes
R-50-FPN-baseline	Mask	1x	2	37.7	59.2	40.9	33.9	55.8	35.8	model | boxes | masks
R-50-FPN-cascade	Mask	1x	2	41.3	59.6	44.9	35.4	56.2	37.8	model | boxes | masks
R-101-FPN-baseline	Mask	1x	2	40.0	61.8	43.7	35.9	58.3	38.0	model | boxes | masks
R-101-FPN-cascade	Mask	1x	2	43.3	61.7	47.2	37.1	58.6	39.8	model | boxes | masks
X-101-***x4d-FPN-baseline	Mask	1x	1	42.4	***.3	4***	37.5	60.6	39.9	model | boxes | masks
X-101-***x4d-FPN-cascade	Mask	1x	1	45.9	***.4	50.2	38.8	61.3	41.6	model | boxes | masks
X-101-32x8d-FPN-baseline	Mask	1x	1	42.1	***.1	45.9	37.3	60.3	39.5	model | boxes | masks
X-101-32x8d-FPN-cascade	Mask	1x	1	45.8	***.1	50.3	38.6	60.6	41.5	model | boxes | masks

### Mask R-CNN with Bells & Whistles

backbone	type	lr schd	im/ gpu	box AP	box AP50	box AP75	mask AP	mask AP50	mask AP75	download links
X-152-32x8d-FPN-IN5k-b ... ... 近期下载者： 相关文件： 评论：[我要评论] [举报此文件] 收藏者： © 联合开发网 from 2004 | 联系站长 | 湘ICP备2023001425号 | 网安备43010502000604 |