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 page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 27 code samples harvested from 3 repositories linked to this paper: 22 ran (of which 0 constructed an object rather than computing a result; 19 with no instrument failure: 2 honoured, 0 violated, 17 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; 2 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 2 samples from 1 repository, 2 ran (2 with no instrument failure; 0 where Syntology's instrument failed); community (archive-listed): 25 samples from 2 repositories, 20 ran (17 with no instrument failure; 3 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

PaddlePaddle/PaddleDetection officialmentioned in papermentioned on GitHubpaddleSyntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report
Nioolek/PPYOLOE_pytorch mentioned on GitHubpytorchApache-2.0Syntology: 10 samples, 6 ran (3 instrument-failed) · 4 unverified report
2023-MindSpore-4/Code10 mindsporeSyntology: not harvested report
CycloneBoy/PPDetectionPytorch pytorchSyntology: not harvested report
Gaurav14cs17/YOLOE pytorchMITSyntology: 15 samples, 14 ran (0 instrument-failed) · 1 unverified report
Mind23-2/MindCode-130 mindsporeSyntology: not harvested report
PaddlePaddle/PaddleYOLO paddleGPL-3.0Syntology: not harvested report
open-mmlab/mmyolo pytorchGPL-3.0Syntology: not harvested 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: 22 ran (of which 0 constructed an object rather than computing a result; 19 with no instrument failure: 2 honoured, 0 violated, 17 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

2ran · honoured contract
1ran · our draft was wrong
2ran; the contract check could not run
17ran
5unverified

Licence: 1 of the 27 samples is pointer only, meaning Syntology does not serve that copy's text. For that sample, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. 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; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

PaddlePaddle/PaddleDetection official repository 2 samples, 2 ran (0 instrument-failed) · 0 unverified
action_preprocess deploy/pipeline/pphuman/action_infer.py ran · honoured contract Apache-2.0 (permissive) · 67b9b64fa4f0eb95 · report fixture: signature input:str/0/str, preprocess_ops:list/1/callable · returned ndarray · level recorded 2026-09-22
get_test_skeletons deploy/pipeline/pphuman/action_infer.py ran · honoured contract Apache-2.0 (permissive) · 21726a1d426815d5 · report fixture: signature input_file:str/0/str · returned list · level recorded 2026-09-22
Nioolek/PPYOLOE_pytorch community (archive-listed) 10 samples, 6 ran (3 instrument-failed) · 4 unverified
bbox_center ppyoloe/bbox/utils.py ran fingerprinted Apache-2.0 (permissive) · e81d4f8b00cb3f47 · report fixture: signature boxes:Tensor/2/float · returned Tensor · level recorded 2026-09-24
bbox_overlaps in 20 papers ppyoloe/bbox/iou2d_calculator.py ran; the contract check could not run (RAISES) Apache-2.0 (permissive) · ba3cd93918de5e4c · report fixture: signature bboxes1:Tensor/3/float, bboxes2:Tensor/3/float, mode:str/0/str, is_aligned:bool/0/bool, eps:float/0/float · returned Tensor · level recorded 2026-09-24
bbox_overlaps_np ppyoloe/bbox/utils.py ran Apache-2.0 (permissive) · 12c3f01c59fd6b68 · report fixture: signature bboxes1:ndarray/3/float, bboxes2:ndarray/3/float, mode:str/0/str, is_aligned:bool/0/bool, eps:float/0/float · returned ndarray · level recorded 2026-09-24
drop_path in 325 papers
census: 27 implementations from 61 papers, 5 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 4, kind float, dtype float32
ppyoloe/models/drop.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant Apache-2.0 (permissive) · 39eace7e2822504f · report fixture: signature x:Tensor/4/float, drop_prob:float/0/float, training:bool/0/bool · returned Tensor · level recorded 2026-09-22
fp16_clamp in 8 papers ppyoloe/bbox/iou2d_calculator.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 4f25740ddf1557a5 · report fixture: signature x:Tensor/2/float, min:float/0/float, max:float/0/float · returned Tensor · level recorded 2026-09-24
get_activation in 218 papers ppyoloe/models/network_blocks.py ran Apache-2.0 (permissive) · ce42ee8e2a1370d2 · report fixture: signature name:str/0/str, inplace:bool/0/bool · returned SiLU · level recorded 2026-09-24
cast_tensor_type ppyoloe/bbox/iou2d_calculator.py unverified Apache-2.0 (permissive) · 346b0a8d4a5df2c4 · report
check_points_inside_bboxes ppyoloe/bbox/utils.py unverified Apache-2.0 (permissive) · 214fcbe11f817297 · report
drop_block_2d in 13 papers ppyoloe/models/drop.py unverified Apache-2.0 (permissive) · 653d5a3aa2c473be · report
drop_block_fast_2d in 13 papers ppyoloe/models/drop.py unverified Apache-2.0 (permissive) here; the stored copy is pointer only · 97aa7c942cfb7d3d · report
Gaurav14cs17/YOLOE community (archive-listed) 15 samples, 14 ran (0 instrument-failed) · 1 unverified
bbox2delta assigners/bbox_utils.py ran MIT (permissive) · 8d93cc301411cb3c · report fixture: signature src_boxes:Tensor/2/float, tgt_boxes:Tensor/2/float, weights:tuple/1/float · returned Tensor · level recorded 2026-09-24
bbox_iou in 21 papers models/iou_loss.py ran MIT (permissive) · 68a39442eb36f371 · report fixture: signature box1:list/1/Tensor, box2:list/1/Tensor, giou:bool/0/bool, diou:bool/0/bool, ciou:bool/0/bool, eps:float/0/float · returned Tensor · level recorded 2026-09-24
collate_fn in 500 papers dataset.py ran MIT (permissive) · b7c795ceaa23e7d4 · report fixture: signature batch:list/1/tuple · returned tuple · level recorded 2026-09-24
compute_max_iou_anchor assigners/utils.py ran fingerprinted MIT (permissive) · 9f6d72530b1f1353 · report fixture: signature ious:Tensor/3/float · returned Tensor · level recorded 2026-09-24
compute_max_iou_gt assigners/utils.py ran MIT (permissive) · 5a20a4a84a359e79 · report fixture: returned Tensor · level recorded 2026-09-26
create_coco_format_dataset download_test_data.py ran MIT (permissive) · 8c7672b432e60d47 · report fixture: signature output_dir:str/0/str, num_train:int/0/int, num_val:int/0/int, img_size:int/0/int, num_classes:int/0/int · returned PosixPath · level recorded 2026-09-24
create_dataloader in 35 papers dataset.py ran MIT (permissive) · 16c920160161420a · report fixture: returned DataLoader · level recorded 2026-09-26
create_synthetic_dataset download_test_data.py ran MIT (permissive) · f35bb01e40ab10f9 · report fixture: signature output_dir:str/0/str, num_train:int/0/int, num_val:int/0/int, img_size:int/0/int, num_classes:int/0/int · returned PosixPath · level recorded 2026-09-24
delta2bbox assigners/bbox_utils.py ran MIT (permissive) · d5b6b0de00896b5e · report fixture: signature deltas:Tensor/2/float, boxes:Tensor/2/float, weights:tuple/1/float · returned Tensor · level recorded 2026-09-24
draw_detections inference.py ran MIT (permissive) · 684c21a6fdd90d43 · report fixture: returned ndarray · level recorded 2026-09-26
expand_bbox in 11 papers assigners/bbox_utils.py ran fingerprinted MIT (permissive) · c434ee22884ca564 · report fixture: signature bboxes:ndarray/2/float, scale:float/0/float · returned ndarray · level recorded 2026-09-25
generate_anchors_for_grid_cell assigners/utils.py ran MIT (permissive) · 2146112c111105c4 · report fixture: returned tuple · level recorded 2026-09-26
iou_similarity models/iou_loss.py ran fingerprinted MIT (permissive) · cbe8ad0c6532215a · report fixture: signature box1:Tensor/3/float, box2:Tensor/3/float, eps:float/0/float · returned Tensor · level recorded 2026-09-24
process_image in 43 papers inference.py ran MIT (permissive) · ead7b82265ee7f37 · report fixture: signature predictor:MockPredictor/0/?, image_path:PosixPath/0/?, output_dir:PosixPath/0/?, save_txt:bool/0/bool, save_img:bool/0/bool, show:bool/0/bool, filter_classes:NoneType/0/? · returned list · level recorded 2026-09-24
build_yoloe models/yoloe.py unverified MIT (permissive) · 3d5a979d22be4926 · 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