Object Detection Models

Model · Object detection

CytoSPM

Smitih

Model weights of CytoSPM: Open-Vocabulary Cytopathology Detection with Structured Prompt Bank (BIBM 2026). This is the model reported in the paper (Table III). The numbers above were measured with the released code on an RTX 3090; the paper values (33.55 / 52.20 / 38.17 and 15.00 / 21.00 / 17.20) were measured on an RTX 4090. Base AP is the COCO AP over the 24 base categories of PentaCyto; novel AP is the zero-shot COCO AP over the 9 held-out categories. The file contains model weights only (statedict) and loads with torch.load(..., weightsonly=True). See the code repository for installation, data preparation and training. The PentaCyto images and annotations are not included.

Model · Object detection

DEIMv2_nano_license_plate

Nguyen Trung Kien

Mô hình phát hiện biển số xe thời gian thực, fine-tune từ DEIMv2 Nano (backbone HGNetv2-B0, pretrained COCO) trên bộ dữ liệu License Plate Recognition của Roboflow Universe. - Kiến trúc: DETR thời gian thực, không cần NMS khi suy luận - Mã nguồn train, inference, export: kienkk-0808/DEIMv2-nano-custom Chỉ số được tính bằng COCO mAP qua lệnh --test-only (xem mục Evaluation). 2. Inference 3. Export ONNX Dữ liệu. Tải dataset từ Roboflow Universe ở định dạng YOLO và sắp xếp: Đặt numclasses trong configs/dataset/customdetection.yml khớp với data.yaml. Huấn luyện. Kết quả lưu tại --output-dir: beststg1.pth, last.pth, log.txt, summary/ (TensorBoard). Tiếp tục train với -r last.pth. Cần truyền lại…

End-to-end 32-class FDI tooth detector trained on the IOP-Compass clinical photographic dataset (700 patients, 3,500 photos).

Model · Object detection

docverify-yolo-fields

Ghost Sas

Finds the 10 fields of a French payslip so that an edit found by the tamper model can be pinned to net pay or gross salary instead of "pixels at (812, 640)". In docverify, an edit inside a money field is what turns a page into high risk. Part of docverify: project · netpaye (net pay) · brut (gross salary) · salairebase (base salary) · netavantimpot (net before tax) · cotisations (total contributions) · test pages, scans and phone photos mixed. 19 ms per page on a T4; part of the 6.7 s full pipeline on 4 CPU threads. Synthetic French payslips only (generated, fake people and companies); other layouts need their own field list. AGPL-3.0, inherited from Ultralytics YOLO. The rest of docverify…

Model · Object detection

factory-safety-isaac-yolo

Intelligence Big Data Processing Laboratory

YOLO weights for factory-safety-isaac — a body-camera-only factory safety agent built on NVIDIA Isaac Sim. These are the two trained detection models the project uses; no other model files are hosted here (MediaPipe's hand landmarker and the Qwen2.5-7B LLM are pulled from their own upstream sources at first run, see the project README). on 7,700 synthetic images generated in Isaac Sim (Replicator auto-labeling), 70% bodycam / 30% free-viewpoint. Or with the project's own scripts (scripts/runpatrol.py --weights, scripts/runpatrol.py --pinch-weights ). Trained entirely on synthetic data (NVIDIA Isaac Sim warehouse assets + Poly Haven CC0 tool scans). See the main repository for full…

This model is a fine-tuned version of facebook/detr-resnet-50 on an unknown dataset. The following hyperparameters were used during training: - learningrate: 1e-05 - trainbatchsize: 8 - evalbatchsize: 8 - lrschedulertype: linear - numepochs: 100 - mixedprecisiontraining: Native AMP - Transformers 4.57.6 - Pytorch 2.11.0+cu130 - Datasets 4.8.5 - Tokenizers 0.22.2

This model is a fine-tuned version of facebook/detr-resnet-50 on an unknown dataset. The following hyperparameters were used during training: - learningrate: 1e-05 - trainbatchsize: 8 - evalbatchsize: 8 - lrschedulertype: linear - numepochs: 100 - mixedprecisiontraining: Native AMP - Transformers 4.57.6 - Pytorch 2.11.0+cu130 - Datasets 4.8.5 - Tokenizers 0.22.2

This model is a fine-tuned version of facebook/detr-resnet-50 on an unknown dataset. The following hyperparameters were used during training: - learningrate: 1e-05 - trainbatchsize: 8 - evalbatchsize: 8 - lrschedulertype: linear - numepochs: 100 - mixedprecisiontraining: Native AMP - Transformers 4.57.6 - Pytorch 2.11.0+cu130 - Datasets 4.8.5 - Tokenizers 0.22.2

Model · Object detection

Hockey-Vision

Alex Haigh

runmodels.py needs the five YOLO models below to run the pipeline. They are not in git (CVModels/Models/ is in.gitignore), so copy them into CVModels/Models/ before running: The file names are set in MODELFILES in runmodels.py, and the folder in MODELSDIR. On the Jetson, python exportengines.py builds a TensorRT engine next to each model (CVModels/Models/.engine), and runmodels.py uses the engine in place of the.pt from then on. See jetson/README.md.

This repository distributes an existing OpenVINO IR conversion of the TensorFlow SSDLite MobileNet V2 COCO object-detection model for the Advantech Intel EdgeAI SDK benchmark. Advantech did not train the original model. Download both model files into the same directory and retain their filenames. FP16 describes the stored weights; it does not guarantee that all operations execute with FP16 precision on every device. The tensor names and shapes describe the XML in this repository. Other upstream conversions can use different output names or preprocessing. The original artifact metadata records OpenVINO 2024.6.0 conversion tooling. The existing XML and BIN were retained without reconversion…

This model detects text lines and mathematical formula rows in scanned Cambodian textbooks for OCR line cropping and document layout analysis.

Model · Object detection

moku-v4

Kaya

Go board detector used by Kaya to turn a photo of a goban into a position (SGF). Trained with moku. Kaya computes a homography from the 4 corners and snaps every stone onto the grid. - model.safetensors, config.json, preprocessorconfig.json: transformers checkpoint. - model.onnx: what Kaya runs (ONNX Runtime Web). Input pixelvalues (batch, 3, 640, 640), RGB scaled to [0, 1] with no mean/std normalization; outputs logits (batch, 300, 3) (apply a sigmoid) and predboxes (batch, 300, 4), normalized (cx, cy, w, h). With the corner head, a third output cornerpoints (batch, 8, 3) holds the 8 best board-corner peaks (x, y, score), x and y normalized to [0, 1] (class-agnostic). The stone-threshold…

SurgHint is a surgical visual question answering system developed for the FRAME and SEGMENT tracks of the ORena FOCUS Challenge. This repository provides the detector checkpoints and Qwen LoRA adapters for answering questions about foreign objects in surgical images and video clips. VLMMAXXING — Orhun Utku Aydin, Frank te Nijenhuis, Dietmar Frey. Sign in and request access on this model page to download the checkpoints. Qwen base weights and FRAME's frozen DINOv3 backbone are not included; please obtain them separately under their upstream licences and access terms. SurgHint inference uses greedy decoding (dosample=False) with thinking disabled. The inference code overrides the sampling…

Model · Object detection

oriented-det-pretrained

Deep Learning for Earth Observation (DL4EO)

Checkpoints for oriented-det (pip install oriented-det). Download by slug (not by filename): Repo: dl4eo/oriented-det-pretrained. Docs: pretrained/README.md. Finetune from 1×, not 3×. DOTA 3× is on Hub for AP75; leaky eval-val is train+val tile memorization. SSDD / HRSID / FAIR1M have no Hub zoo — finetune these DOTA 1× slugs locally. DOTA evalmap50 in the package manifest is leaky val tiles. Advertised DOTA mAP50 below is official Task 1. HRSC mAP50 is held-out ImageSets test. From v0.3.1, un-suffixed Rotated RetinaNet slugs are OBB (usehbbformatching: false). Circum-HBB lives at hbb. v0.3.0 unsuffixed filenames stay on this repo for old clients. Each slug has a content-addressed.pth plus…

YOLO26 models that find 11 kinds of electronic components on printed circuit boards. They are the vision part of a PCB automated optical inspection (AOI) machine built at Rajamangala University of Technology Thanyaburi (RMUTT): a 4K camera on an XY gantry visits every point of a board, the model detects the parts in each frame, and the machine compares them with a golden reference board to decide PASS / FAIL for every part (OK, MISSING, WRONG type, EXTRA). Every other folder is an earlier experiment (25 training runs in total), kept with its args.yaml, results.csv and plots so the work can be traced. Each folder is one run: weights/best.pt, weights/last.pt, training curves, confusion…

Does the "best" polyp detector stay the best if you train it differently? This repository releases every model from a controlled benchmark that answers that question: 12 detectors × 3 white-light colonoscopy datasets × 6 training regimes × 3 seeds = 648 best.pt checkpoints, together with cached per-image predictions and ensemble outputs. RT-DETR-X (seed 88) on two Kvasir-SEG test frames under the Scratch, Pretrained and Aug-10× regimes. Green = reference box, cyan = matched detection, pink = unmatched detection (score > 0.20, IoU ≥ 0.50). These examples are illustrative, not typical accuracy. Only the 648 completed canonical runs are included. Interrupted runs, last.pt files, worker logs…

Research profile hub on Hugging Face for Deborah Akuoko Minka (also Deborah Akuoko-Minka, A. Akuoko, AMA Akuoko). These pages are maintained to publish accurate biographical and research information for Deborah Akuoko Minka and common name variants. Keywords: signal processing, SPAD, object detection, material sensing, optical sensing, image annotation, segmentation, PyTorch Name variants (same person): Akuoko arXiv - Hounsfield volumetric breast density on radiotherapy CT (Deborah E. M. Akuoko) Deborah Akuoko Minka — also AMA Akuoko and the name spellings below — is a researcher in signal processing, machine intelligence, and SPAD sensing. Research focus: Researches signal processing…

本仓库提供由 ultralytics/ultralytics YOLO11s ONNX 转换得到的 RKNN CNN 模型。 - Model ID：RKNNAI/RK182X-CNN-YOLO11s - 模型显示名称：RK182X-CNN-YOLO11s - 源模型：ultralytics/ultralytics YOLO11s ONNX - 模型类型：CNN ModelScope 完整下载： Hugging Face 完整下载： ModelScope 指定配置下载： Hugging Face 指定配置下载： - 使用配套 RKNN Runtime 和驱动；运行前用 rknn-smi -v 检查设备端版本。 源模型采用 GNU Affero General Public License v3.0，正文见 LICENSE，归属及转换说明见 NOTICE。同时遵守 RKNN Toolkit 和 RKNN Runtime 相关许可。

本仓库提供由 ultralytics/ultralytics 转换得到的 RKNN CNN 模型。 - Model ID：RKNNAI/RK182X-CNN-YOLO26s - 模型显示名称：RK182X-CNN-YOLO26s - 源模型：ultralytics/ultralytics - 模型类型：CNN ModelScope 完整下载： Hugging Face 完整下载： ModelScope 指定配置下载： Hugging Face 指定配置下载： - 使用配套 RKNN Runtime 和驱动；运行前用 rknn-smi -v 检查设备端版本。 源模型采用 GNU Affero General Public License v3.0，正文见 LICENSE，归属及转换说明见 NOTICE。同时遵守 RKNN Toolkit 和 RKNN Runtime 相关许可。

本仓库提供由 ultralytics/yolov5 转换得到的 RKNN CNN 模型。 - Model ID：RKNNAI/RK182X-CNN-YOLOv5s - 模型显示名称：RK182X-CNN-YOLOv5s - 源模型：ultralytics/yolov5 - 模型类型：CNN ModelScope 完整下载： Hugging Face 完整下载： ModelScope 指定配置下载： Hugging Face 指定配置下载： - 使用配套 RKNN Runtime 和驱动；运行前用 rknn-smi -v 检查设备端版本。 - 源模型许可证：GNU Affero General Public License v3.0，正文见 LICENSE，归属和转换说明见 NOTICE。 - 本仓库交付物是源模型的 RKNN 转换衍生物，仍受源模型许可和使用限制约束。 - 同时遵守 RKNN Toolkit、RKNN Runtime 相关许可；本仓库不包含运行库。

本仓库提供由 meituan/YOLOv6 转换得到的 RKNN CNN 模型。 - Model ID：RKNNAI/RK182X-CNN-YOLOv6s - 模型显示名称：RK182X-CNN-YOLOv6s - 源模型：meituan/YOLOv6 - 模型类型：CNN ModelScope 完整下载： Hugging Face 完整下载： ModelScope 指定配置下载： Hugging Face 指定配置下载： - 使用配套 RKNN Runtime 和驱动；运行前用 rknn-smi -v 检查设备端版本。 - 源模型许可证：GNU General Public License v3.0，正文见 LICENSE，归属和转换说明见 NOTICE。 - 本仓库交付物是源模型的 RKNN 转换衍生物，仍受源模型许可和使用限制约束。 - 同时遵守 RKNN Toolkit、RKNN Runtime 相关许可；本仓库不包含运行库。

本仓库提供由 airockchip/rknnmodelzoo YOLOv8 RKNN3 ONNX 转换得到的 RKNN CNN 模型。 - Model ID：RKNNAI/RK182X-CNN-YOLOv8s - 模型显示名称：RK182X-CNN-YOLOv8s - 源模型：airockchip/rknnmodelzoo YOLOv8 RKNN3 ONNX - 模型类型：CNN ModelScope 完整下载： Hugging Face 完整下载： ModelScope 指定配置下载： Hugging Face 指定配置下载： - 使用配套 RKNN Runtime 和驱动；运行前用 rknn-smi -v 检查设备端版本。 源模型采用 GNU Affero General Public License v3.0，正文见 LICENSE，归属及转换说明见 NOTICE。同时遵守 RKNN Toolkit 和 RKNN Runtime 相关许可。

Detector weights and derived bases from a controlled study of occlusion compensation in aerial wildlife monitoring, along two axes: single view vs multi view, and sensor (pixel) space vs embedding space. container it ran in, every scored metric behind the paper's tables, and a step-by-step in REPLICATION.md. Run directory names here are the run identifiers used there, so a checkpoint joins directly against metrics/.json under the arms key. Backbones are not included. DINOv3 and V-JEPA 2.1 are used frozen and unmodified — obtain them from their original sources. Only self-trained artefacts are here. Nearly everything here is cross-validated. A run directory whose name carries f belongs to…

Model · Object detection

web-sdk-pp-rotated-detection

Chen Mohan

由chenmohan维护，非Paddle官方账号。PP-YOLOE-R-s 1024 FP32，DOTA15类单帧遥感旋转框检测，33,161,415字节。 Apache-2.0采用依据为固定官方项目声明与模型表，未发现独立权重许可文本；完整来源、转换和边界见模型卡及LICENSE/NOTICE。 Maintained by chenmohan, not the official Paddle account. Single-image DOTA15 rotated detection, PP-YOLOE-R-s 1024 FP32. Apache-2.0 is adopted from the pinned project license and model table; no separate weight-specific license text was found. See the cards for provenance, conversion and desktop verification scope.

Central model repository for ILoveSeafood AI Engineering Ecosystem. 1. YOLO Box Detection (yolo/yolo11n.pt): Real-time seafood box detection from surveillance camera feeds. 2. ARIMA Demand Forecasting (arima/arimaFrozenSeafood.pkl): Optimal stock inventory prediction.

MCCbena's YOLOv7-tiny, fine-tuned for 35 classes using the local open-images-4s-yolo dataset. This is a modified/fine-tuned release, not an official upstream release. Training continues until all 300 epochs complete; the final checkpoint is published automatically after completion. This page is also updated with interim checkpoints during training. Recommended for inference: best.pt, validation epoch 128, [email protected] 54.47%, [email protected]:0.95 40.55%. It is selected by the upstream fitness score; last.pt remains the latest resumable checkpoint. When available, DATASETEXPANSION.json records a supplemental Hammer/Drill subset from the original Zenodo publisher, CC BY 4.0. SUPPLEMENTALDATASETLICENSE.md…