The RT-DETRv2 model was proposed in RT-DETRv2: Improved Baseline with Bag-of-Freebies for Real-Time Detection Transformer by Wenyu Lv, Yian Zhao, Qinyao Chang, Kui Huang, Guanzhong Wang, Yi Liu. RT-DETRv2 refines RT-DETR by introducing selective multi-scale feature extraction, a discrete sampling operator for broader deployment compatibility, and improved training strategies like dynamic data augmentation and scale-adaptive hyperparameters. These changes enhance flexibility and practicality while maintaining real-time performance. This model was contributed by @jadechoghari with the help of @cyrilvallez and @qubvel-hf This is RT-DETRv2 consistently outperforms its predecessor across all…
Open-weight model · Object detection
rtdetr_r101vd_coco_o365
by Peking University PekingU/rtdetr_r101vd_coco_o365
However, we observe that the speed and accuracy of YOLOs are negatively affected by the NMS. Recently, end-to-end Transformer-based detectors (DETRs) have provided an alternative to eliminating NMS.
Parameters77M
Context—
Weights307.3 MB
Licenseapache-2.0
AccessOpen weights
Monthly Downloads894.9k
Runs On
What it takes to serve rtdetr_r101vd_coco_o365 (77M parameters): the memory its weights need at each precision, and the cheapest way to rent enough data-center GPUs to hold them.
| Precision | Weights | Memory needed | Cheapest setup | Per hour | Also fits |
|---|---|---|---|---|---|
| 16-bit | 0.2 GB | 0.2 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 0.1 GB | 0.1 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 0.0 GB | 0.0 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
Memory is the weights at that precision plus 20% for the runtime and a short context; a long context needs more. Prices are the lowest on-demand hourly rates in the SAVRN Index, read Sep 18, 2026.
SAVRN's Notes on rtdetr_r101vd_coco_o365
An object detector that fits in 0.2 GB turns the question from which GPU to how many streams per GPU. Peking University published this one at 77 million parameters, weighing 307 MB; at 16-bit it needs 0.2 GB of memory and at 8-bit 0.1 GB. The cheapest setup on our Index is a single MI300X with 192 GB at $1.85 per hour, so the operator's work is packing image pipelines onto that card rather than finding room for weights.
Apache 2.0 covers commercial use, modification and redistribution, provided you keep the license, copyright notices and any NOTICE file and state significant changes, and it carries an express patent grant from contributors. Check the training relation before you commit: the file records coco as the training set and arXiv:2304.08069 as the paper, so confirm the object classes you need are covered there. Access is open; the last update is dated 2024-07-01.
Model Card
By Peking University, published under apache-2.0, revision ff44b69152a7.
Model Card for RT-DETR
Table of Contents
- Model Details
- Model Sources
- How to Get Started with the Model
- Training Details
- Evaluation
- Model Architecture and Objective
- Citation
Model Details
Configuration
- Architecture
- RTDetrForObjectDetection
- Stored precision
- float32
- Model type
- rt_detr
Identity and Version
- Repository
- PekingU/rtdetr_r101vd_coco_o365
- Publisher
- Peking University
- Task
- Object detection
- Modality
- Image
- Library
- transformers
- Parameters
- 77M parameters
- Languages
- en
- Revision
- ff44b69152a72cc752677665fb4539507d56a99d
- First published
- 2024-06-05
- Last updated
- 2024-07-01
Files and Weights
5 files, 307.3 MB in total. The weights are 1 file totalling 307.3 MB in safetensors.
Weights1 file · 307.3 MB
Configuration2 files · 6.0 KB
Documentation1 file · 9.1 KB
Repository1 file · 1.5 KB
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model.safetensors | Weights | 307.3 MB | 48681f4087d2 |
| config.json | Configuration | 5.2 KB | — |
| preprocessor_config.json | Configuration | 841 B | — |
| README.md | Documentation | 9.1 KB | — |
| .gitattributes | Repository | 1.5 KB | — |
License and Download
- License
- apache-2.0
- Access
- Open weights, no gate
- Download size
- 307.3 MB
Download from Peking University
Released by Peking University through its official repository on Hugging Face. Read the license.
Built From
- Described by arXiv:2304.08069
- Trained on (disclosed) coco
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 307.3 MB |
| 16-bit | 0.2 GB |
| 8-bit | 0.1 GB |
| 4-bit | 0.0 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Built on This Model
Questions About rtdetr_r101vd_coco_o365
How much GPU memory does rtdetr_r101vd_coco_o365 need?
About 0.2 GB at 16-bit and 0 GB at 4-bit: the weights (77M parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run rtdetr_r101vd_coco_o365 on?
At 16-bit, 1x MI300X from $1.85 an hour; at 4-bit, 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists.
Can I use rtdetr_r101vd_coco_o365 commercially?
Yes. rtdetr_r101vd_coco_o365 is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors.
Similar Models
Roof detection model for remote sensing imagery, fine-tuned using RT-DETR. The following example shows roof detections produced by the model: Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. Use the code below to get started with the model.
This model is a fine-tuned version of YOLOv8x specialized in detecting two specific classes: Face and Person. It has been trained on a large-scale proprietary dataset consisting of approximately 150,000 images. The high capacity of the YOLOv8x architecture combined with a diverse proprietary dataset ensures high accuracy and robustness in various scenarios. You can load the model using the Hugging Face transformers library by enabling custom code execution. If you prefer the standard Ultralytics API, you can download the weights from the Hub and load them directly. This method automatically handles model downloading for ultralytics YOLO model. This model is based on the Ultralytics YOLOv8…
The D-FINE model was proposed in D-FINE: Redefine Regression Task in DETRs as Fine-grained Distribution Refinement by Yansong Peng, Hebei Li, Peixi Wu, Yueyi Zhang, Xiaoyan Sun, Feng Wu This model was contributed by VladOS95-cyber with the help of @qubvel-hf This is the HF transformers implementation for D-FINE coco -> model trained on COCO obj365 -> model trained on Object365 obj2coco -> model trained on Object365 and then finetuned on COCO D-FINE, a powerful real-time object detector that achieves outstanding localization precision by redefining the bounding box regression task in DETR models. D-FINE comprises two key components: Fine-grained Distribution Refinement (FDR) and Global…
The D-FINE model was proposed in D-FINE: Redefine Regression Task in DETRs as Fine-grained Distribution Refinement by Yansong Peng, Hebei Li, Peixi Wu, Yueyi Zhang, Xiaoyan Sun, Feng Wu This model was contributed by VladOS95-cyber with the help of @qubvel-hf This is the HF transformers implementation for D-FINE coco -> model trained on COCO obj365 -> model trained on Object365 obj2coco -> model trained on Object365 and then finetuned on COCO D-FINE, a powerful real-time object detector that achieves outstanding localization precision by redefining the bounding box regression task in DETR models. D-FINE comprises two key components: Fine-grained Distribution Refinement (FDR) and Global…
DEtection TRansformer (DETR) model trained end-to-end on COCO 2017 object detection (118k annotated images). It was introduced in the paper End-to-End Object Detection with Transformers by Carion et al. and first released in this repository. Disclaimer: The team releasing DETR did not write a model card for this model so this model card has been written by the Hugging Face team. The DETR model is an encoder-decoder transformer with a convolutional backbone. Two heads are added on top of the decoder outputs in order to perform object detection: a linear layer for the class labels and a MLP (multi-layer perceptron) for the bounding boxes. The model uses so-called object queries to detect…