Papers › PP-YOLOE: An evolved version of YOLO

PP-YOLOE: An evolved version of YOLO

30 Mar 2022arXiv:2203.16250archive 2025-07-28

Shangliang Xu, Xinxin Wang, Wenyu Lv, Qinyao Chang, Cheng Cui, Kaipeng Deng, Guanzhong Wang, Qingqing Dang, Shengyu Wei, Yuning Du, Baohua Lai

In this report, we present PP-YOLOE, an industrial state-of-the-art object detector with high performance and friendly deployment. We optimize on the basis of the previous PP-YOLOv2, using anchor-free paradigm, more powerful backbone and neck equipped with CSPRepResStage, ET-head and dynamic label assignment algorithm TAL. We provide s/m/l/x models for different practice scenarios. As a result, PP-YOLOE-l achieves 51.4 mAP on COCO test-dev and 78.1 FPS on Tesla V100, yielding a remarkable improvement of (+1.9 AP, +13.35% speed up) and (+1.3 AP, +24.96% speed up), compared to the previous state-of-the-art industrial models PP-YOLOv2 and YOLOX respectively. Further, PP-YOLOE inference speed achieves 149.2 FPS with TensorRT and FP16-precision. We also conduct extensive experiments to verify the effectiveness of our designs. Source code and pre-trained models are available at https://github.com/PaddlePaddle/PaddleDetection.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2203.16250")

Code

Syntology Ran 17 of 27 code samples harvested from 3 repositories linked to this paper; 10 have no recorded run. Of those that ran: 2 ran · honoured contract; 1 ran · fixture could not drive it; 14 ran with no contract checked.

By repository: official repository: 2 samples from 1 repository, 2 ran; community (archive-listed): 25 samples from 2 repositories, 15 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

PaddlePaddle/PaddleDetection officialmentioned in papermentioned on GitHubpaddle report
Nioolek/PPYOLOE_pytorch mentioned on GitHubpytorchApache-2.0 report
open-mmlab/mmyolo pytorchGPL-3.0 report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

27 samples harvested; 17 ran; 2 honoured the contract we drafted; 10 have no recorded run. Read from Syntology's graph 2026-09-25; that is when this build read the record, not when the samples ran.

2ran · honoured contract
1ran · fixture could not drive it
14ran
10unverified

Licence: 0 of the 27 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 3 repositories linked to this paper, official or community; each sample names its own and says which. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

action_preprocess PaddlePaddle/PaddleDetection/deploy/pipeline/pphuman/action_infer.py official repository ran · honoured contract Apache-2.0 (permissive) · 67b9b64fa4f0eb95 · report
get_test_skeletons PaddlePaddle/PaddleDetection/deploy/pipeline/pphuman/action_infer.py official repository ran · honoured contract Apache-2.0 (permissive) · 21726a1d426815d5 · report
bbox2delta Gaurav14cs17/YOLOE/assigners/bbox_utils.py community (archive-listed) ran MIT (permissive) · 8d93cc301411cb3c · report
bbox_center Nioolek/PPYOLOE_pytorch/ppyoloe/bbox/utils.py community (archive-listed) ran fingerprinted Apache-2.0 (permissive) · e81d4f8b00cb3f47 · report
bbox_iou Gaurav14cs17/YOLOE/models/iou_loss.py community (archive-listed) ran MIT (permissive) · 68a39442eb36f371 · report
bbox_overlaps Nioolek/PPYOLOE_pytorch/ppyoloe/bbox/iou2d_calculator.py community (archive-listed) ran Apache-2.0 (permissive) · ba3cd93918de5e4c · report
bbox_overlaps_np Nioolek/PPYOLOE_pytorch/ppyoloe/bbox/utils.py community (archive-listed) ran Apache-2.0 (permissive) · 12c3f01c59fd6b68 · report
collate_fn Gaurav14cs17/YOLOE/dataset.py community (archive-listed) ran MIT (permissive) · b7c795ceaa23e7d4 · report
compute_max_iou_anchor Gaurav14cs17/YOLOE/assigners/utils.py community (archive-listed) ran fingerprinted MIT (permissive) · 9f6d72530b1f1353 · report
create_coco_format_dataset Gaurav14cs17/YOLOE/download_test_data.py community (archive-listed) ran MIT (permissive) · 8c7672b432e60d47 · report
create_synthetic_dataset Gaurav14cs17/YOLOE/download_test_data.py community (archive-listed) ran MIT (permissive) · f35bb01e40ab10f9 · report
delta2bbox Gaurav14cs17/YOLOE/assigners/bbox_utils.py community (archive-listed) ran MIT (permissive) · d5b6b0de00896b5e · report
drop_path Nioolek/PPYOLOE_pytorch/ppyoloe/models/drop.py community (archive-listed) ran · fixture could not drive it Apache-2.0 (permissive) · 39eace7e2822504f · report
fp16_clamp Nioolek/PPYOLOE_pytorch/ppyoloe/bbox/iou2d_calculator.py community (archive-listed) ran fingerprinted Apache-2.0 (permissive) · 4f25740ddf1557a5 · report
get_activation Nioolek/PPYOLOE_pytorch/ppyoloe/models/network_blocks.py community (archive-listed) ran Apache-2.0 (permissive) · ce42ee8e2a1370d2 · report
iou_similarity Gaurav14cs17/YOLOE/models/iou_loss.py community (archive-listed) ran fingerprinted MIT (permissive) · cbe8ad0c6532215a · report
process_image Gaurav14cs17/YOLOE/inference.py community (archive-listed) ran MIT (permissive) · ead7b82265ee7f37 · report
build_yoloe Gaurav14cs17/YOLOE/models/yoloe.py community (archive-listed) unverified MIT (permissive) · 3d5a979d22be4926 · report
cast_tensor_type Nioolek/PPYOLOE_pytorch/ppyoloe/bbox/iou2d_calculator.py community (archive-listed) unverified Apache-2.0 (permissive) · 346b0a8d4a5df2c4 · report
check_points_inside_bboxes Nioolek/PPYOLOE_pytorch/ppyoloe/bbox/utils.py community (archive-listed) unverified Apache-2.0 (permissive) · 214fcbe11f817297 · report
compute_max_iou_gt Gaurav14cs17/YOLOE/assigners/utils.py community (archive-listed) unverified MIT (permissive) · 5a20a4a84a359e79 · report
create_dataloader Gaurav14cs17/YOLOE/dataset.py community (archive-listed) unverified MIT (permissive) · 16c920160161420a · report
draw_detections Gaurav14cs17/YOLOE/inference.py community (archive-listed) unverified MIT (permissive) · 684c21a6fdd90d43 · report
drop_block_2d Nioolek/PPYOLOE_pytorch/ppyoloe/models/drop.py community (archive-listed) unverified Apache-2.0 (permissive) · 653d5a3aa2c473be · report
drop_block_fast_2d Nioolek/PPYOLOE_pytorch/ppyoloe/models/drop.py community (archive-listed) unverified Apache-2.0 (permissive) · 97aa7c942cfb7d3d · report
expand_bbox Gaurav14cs17/YOLOE/assigners/bbox_utils.py community (archive-listed) unverified MIT (permissive) · c434ee22884ca564 · report
generate_anchors_for_grid_cell Gaurav14cs17/YOLOE/assigners/utils.py community (archive-listed) unverified MIT (permissive) · 2146112c111105c4 · report

Tasks

2D Object DetectionDense Object DetectionMulti-Object TrackingMultiple Object TrackingObject DetectionOnline Multi-Object TrackingReal-Time Object Detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Multi-Object Tracking MOT16 PPTracking MOTA 77.7 #1 of 24 Archive leaderboard report
Multiple Object Tracking CroHD PP-Tracking MOTA 72.6 #1 of 5 Archive leaderboard report
Object Detection COCO test-dev PP-YOLOE-x(CSPRepResNet-x, 640x640, single-scale ) AP50 69.9 #73 of 225 Archive leaderboard report
Object Detection COCO test-dev PP-YOLOE-x(CSPRepResNet-x, 640x640, single-scale ) AP75 56.5 #73 of 225 Archive leaderboard report
Object Detection COCO test-dev PP-YOLOE-x(CSPRepResNet-x, 640x640, single-scale ) APL 66.4 #73 of 225 Archive leaderboard report
Object Detection COCO test-dev PP-YOLOE-x(CSPRepResNet-x, 640x640, single-scale ) APM 56.3 #73 of 225 Archive leaderboard report
Object Detection COCO test-dev PP-YOLOE-x(CSPRepResNet-x, 640x640, single-scale ) APS 33.3 #73 of 225 Archive leaderboard report
Object Detection COCO test-dev PP-YOLOE-x(CSPRepResNet-x, 640x640, single-scale ) box mAP 52.2 #73 of 225 Archive leaderboard report
Object Detection COCO test-dev PP-YOLOE-l(CSPRepResNet-l, 640x640, single-scale ) AP50 68.9 #79 of 225 Archive leaderboard report
Object Detection COCO test-dev PP-YOLOE-l(CSPRepResNet-l, 640x640, single-scale ) AP75 55.6 #79 of 225 Archive leaderboard report
Object Detection COCO test-dev PP-YOLOE-l(CSPRepResNet-l, 640x640, single-scale ) APL 66.1 #79 of 225 Archive leaderboard report
Object Detection COCO test-dev PP-YOLOE-l(CSPRepResNet-l, 640x640, single-scale ) APM 55.3 #79 of 225 Archive leaderboard report
Object Detection COCO test-dev PP-YOLOE-l(CSPRepResNet-l, 640x640, single-scale ) APS 31.4 #79 of 225 Archive leaderboard report
Object Detection COCO test-dev PP-YOLOE-l(CSPRepResNet-l, 640x640, single-scale ) box mAP 51.4 #79 of 225 Archive leaderboard report
Object Detection COCO test-dev PP-YOLOE-m(CSPRepResNet-m, 640x640, single-scale ) AP50 66.5 #101 of 225 Archive leaderboard report
Object Detection COCO test-dev PP-YOLOE-m(CSPRepResNet-m, 640x640, single-scale ) AP75 53.0 #101 of 225 Archive leaderboard report
Object Detection COCO test-dev PP-YOLOE-m(CSPRepResNet-m, 640x640, single-scale ) APL 63.8 #101 of 225 Archive leaderboard report
Object Detection COCO test-dev PP-YOLOE-m(CSPRepResNet-m, 640x640, single-scale ) APM 52.9 #101 of 225 Archive leaderboard report
Object Detection COCO test-dev PP-YOLOE-m(CSPRepResNet-m, 640x640, single-scale ) APS 28.6 #101 of 225 Archive leaderboard report
Object Detection COCO test-dev PP-YOLOE-m(CSPRepResNet-m, 640x640, single-scale ) box mAP 48.9 #101 of 225 Archive leaderboard report
Object Detection COCO test-dev PP-YOLOE-s(CSPRepResNet-s, 640x640, single-scale ) AP50 60.5 #163 of 225 Archive leaderboard report
Object Detection COCO test-dev PP-YOLOE-s(CSPRepResNet-s, 640x640, single-scale ) AP75 46.6 #163 of 225 Archive leaderboard report
Object Detection COCO test-dev PP-YOLOE-s(CSPRepResNet-s, 640x640, single-scale ) APL 56.9 #163 of 225 Archive leaderboard report
Object Detection COCO test-dev PP-YOLOE-s(CSPRepResNet-s, 640x640, single-scale ) APM 46.4 #163 of 225 Archive leaderboard report
Object Detection COCO test-dev PP-YOLOE-s(CSPRepResNet-s, 640x640, single-scale ) APS 23.2 #163 of 225 Archive leaderboard report
Object Detection COCO test-dev PP-YOLOE-s(CSPRepResNet-s, 640x640, single-scale ) box mAP 43.1 #163 of 225 Archive leaderboard report
Online Multi-Object Tracking MOT16 PP-Tracking MOTA 77.7 #1 of 5 Archive leaderboard report
Real-Time Object Detection COCO (Common Objects in Context) PP-YOLOE+_X FPS (V100, b=1) 45 #22 of 82 Archive leaderboard report
Real-Time Object Detection COCO (Common Objects in Context) PP-YOLOE+_X box AP 54.7 #22 of 82 Archive leaderboard report
Real-Time Object Detection COCO (Common Objects in Context) PP-YOLOE+_L(distillation) FPS (V100, b=1) 78 #27 of 82 Archive leaderboard report
Real-Time Object Detection COCO (Common Objects in Context) PP-YOLOE+_L(distillation) box AP 54.0 #27 of 82 Archive leaderboard report
Real-Time Object Detection COCO (Common Objects in Context) PP-YOLOE+_L FPS (V100, b=1) 78 #36 of 82 Archive leaderboard report
Real-Time Object Detection COCO (Common Objects in Context) PP-YOLOE+_L box AP 52.9 #36 of 82 Archive leaderboard report
Real-Time Object Detection COCO (Common Objects in Context) YOLOv3 FPS (V100, b=1) 123 #52 of 82 Archive leaderboard report
Real-Time Object Detection COCO (Common Objects in Context) YOLOv3 box AP 51.0 #52 of 82 Archive leaderboard report
Real-Time Object Detection COCO (Common Objects in Context) PP-YOLOE+_M box AP 49.8 #58 of 82 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

1x1 ConvolutionAverage PoolingBatch NormalizationBottleneck Residual BlockBottom-up Path AugmentationCSPDarknet53ConvolutionCoordConvDeformable ConvolutionDropBlockFPNGlobal Average PoolingGrid SensitiveKaiming InitializationMatrix NMSMax PoolingMixupPAFPNPP-YOLOPP-YOLOv2ReLUResidual BlockResidual ConnectionSPEEDSoftmaxSpatial Pyramid PoolingTanh ActivationYOLOX

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections