Update Model Card (#4)

- Update Model Card (1ec986062cfaf8bf63a2b8d0ae16040cec4835ba)


Co-authored-by: Pavel Iakubovskii <[email protected]>

README.md

@@ -1,77 +1,119 @@
 ---
 library_name: transformers
-tags: []
+license: apache-2.0
+language:
+- en
+pipeline_tag: object-detection
+tags:
+  - object-detection
+  - vision
+datasets:
+  - coco
+widget:
+  - src: >-
+      https://huggingface.co/datasets/mishig/sample_images/resolve/main/savanna.jpg
+    example_title: Savanna
+  - src: >-
+      https://huggingface.co/datasets/mishig/sample_images/resolve/main/football-match.jpg
+    example_title: Football Match
+  - src: >-
+      https://huggingface.co/datasets/mishig/sample_images/resolve/main/airport.jpg
+    example_title: Airport
 ---
 
-# Model Card for Model ID
 
-<!-- Provide a quick summary of what the model is/does. -->
+# Model Card for RT-DETR
 
 
+## Table of Contents
 
-## Model Details
-
-### Model Description
-
-<!-- Provide a longer summary of what this model is. -->
-
-This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
-
-- **Developed by:** [More Information Needed]
-- **Funded by [optional]:** [More Information Needed]
-- **Shared by [optional]:** [More Information Needed]
-- **Model type:** [More Information Needed]
-- **Language(s) (NLP):** [More Information Needed]
-- **License:** [More Information Needed]
-- **Finetuned from model [optional]:** [More Information Needed]
-
-### Model Sources [optional]
+1. [Model Details](#model-details)
+2. [Model Sources](#model-sources)
+3. [How to Get Started with the Model](#how-to-get-started-with-the-model)
+4. [Training Details](#training-details)
+5. [Evaluation](#evaluation)
+6. [Model Architecture and Objective](#model-architecture-and-objective)
+7. [Citation](#citation)
 
-<!-- Provide the basic links for the model. -->
-
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
 
-## Uses
+## Model Details
 
-<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/6579e0eaa9e58aec614e9d97/WULSDLsCVs7RNEs9KB0Lr.png)
 
-### Direct Use
+> The YOLO series has become the most popular framework for real-time object detection due to its reasonable trade-off between speed and accuracy. 
+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. 
+Nevertheless, the high computational cost limits their practicality and hinders them from fully exploiting the advantage of excluding NMS. 
+In this paper, we propose the Real-Time DEtection TRansformer (RT-DETR), the first real-time end-to-end object detector to our best knowledge that addresses the above dilemma. 
+We build RT-DETR in two steps, drawing on the advanced DETR: 
+first we focus on maintaining accuracy while improving speed, followed by maintaining speed while improving accuracy. 
+Specifically, we design an efficient hybrid encoder to expeditiously process multi-scale features by decoupling intra-scale interaction and cross-scale fusion to improve speed. 
+Then, we propose the uncertainty-minimal query selection to provide high-quality initial queries to the decoder, thereby improving accuracy. 
+In addition, RT-DETR supports flexible speed tuning by adjusting the number of decoder layers to adapt to various scenarios without retraining. 
+Our RT-DETR-R50 / R101 achieves 53.1% / 54.3% AP on COCO and 108 / 74 FPS on T4 GPU, outperforming previously advanced YOLOs in both speed and accuracy. 
+We also develop scaled RT-DETRs that outperform the lighter YOLO detectors (S and M models). 
+Furthermore, RT-DETR-R50 outperforms DINO-R50 by 2.2% AP in accuracy and about 21 times in FPS. 
+After pre-training with Objects365, RT-DETR-R50 / R101 achieves 55.3% / 56.2% AP. The project page: this [https URL](https://zhao-yian.github.io/RTDETR/).
 
-<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
 
-[More Information Needed]
 
-### Downstream Use [optional]
+This is the model card of a 🤗 [transformers](https://huggingface.co/docs/transformers/index) model that has been pushed on the Hub.
 
-<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+- **Developed by:** Yian Zhao and Sangbum Choi
+- **Funded by:**  National Key R&D Program of China (No.2022ZD0118201), Natural Science Foundation of China (No.61972217, 32071459, 62176249, 62006133, 62271465),
+and the Shenzhen Medical Research Funds in China (No.
+B2302037). 
+- **Shared by:** Sangbum Choi
+- **Model type:** [RT-DETR](https://huggingface.co/docs/transformers/main/en/model_doc/rt_detr)
+- **License:** Apache-2.0
 
-[More Information Needed]
+### Model Sources
 
-### Out-of-Scope Use
+<!-- Provide the basic links for the model. -->
 
-<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+- **HF Docs:** [RT-DETR](https://huggingface.co/docs/transformers/main/en/model_doc/rt_detr)
+- **Repository:** https://github.com/lyuwenyu/RT-DETR
+- **Paper:** https://arxiv.org/abs/2304.08069
+- **Demo:** [RT-DETR Tracking](https://huggingface.co/spaces/merve/RT-DETR-tracking-coco)
 
-[More Information Needed]
+## How to Get Started with the Model
 
-## Bias, Risks, and Limitations
+Use the code below to get started with the model.
 
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+```python
+import torch
+import requests
 
-[More Information Needed]
+from PIL import Image
+from transformers import RTDetrForObjectDetection, RTDetrImageProcessor
 
-### Recommendations
+url = 'http://images.cocodataset.org/val2017/000000039769.jpg' 
+image = Image.open(requests.get(url, stream=True).raw)
 
-<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+image_processor = RTDetrImageProcessor.from_pretrained("PekingU/rtdetr_r34vd")
+model = RTDetrForObjectDetection.from_pretrained("PekingU/rtdetr_r34vd")
 
-Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+inputs = image_processor(images=image, return_tensors="pt")
 
-## How to Get Started with the Model
+with torch.no_grad():
+    outputs = model(**inputs)
 
-Use the code below to get started with the model.
+results = image_processor.post_process_object_detection(outputs, target_sizes=torch.tensor([image.size[::-1]]), threshold=0.3)
 
-[More Information Needed]
+for result in results:
+    for score, label_id, box in zip(result["scores"], result["labels"], result["boxes"]):
+        score, label = score.item(), label_id.item()
+        box = [round(i, 2) for i in box.tolist()]
+        print(f"{model.config.id2label[label]}: {score:.2f} {box}")
+```
+This should output
+```
+sofa: 0.97 [0.14, 0.38, 640.13, 476.21]
+cat: 0.96 [343.38, 24.28, 640.14, 371.5]
+cat: 0.96 [13.23, 54.18, 318.98, 472.22]
+remote: 0.95 [40.11, 73.44, 175.96, 118.48]
+remote: 0.92 [333.73, 76.58, 369.97, 186.99]
+```
 
 ## Training Details
 
@@ -79,121 +121,72 @@ Use the code below to get started with the model.
 
 <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
 
-[More Information Needed]
+The RTDETR model was trained on [COCO 2017 object detection](https://cocodataset.org/#download), a dataset consisting of 118k/5k annotated images for training/validation respectively. 
 
 ### Training Procedure
 
 <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
 
-#### Preprocessing [optional]
-
-[More Information Needed]
+We conduct experiments on COCO and Objects365 datasets, where RT-DETR is trained on COCO train2017 and validated on COCO val2017 dataset. 
+We report the standard COCO metrics, including AP (averaged over uniformly sampled IoU thresholds ranging from 0.50-0.95 with a step size of 0.05), 
+AP50, AP75, as well as AP at different scales: APS, APM, APL.
 
+### Preprocessing
 
-#### Training Hyperparameters
+Images are resized to 640x640 pixels and rescaled with `image_mean=[0.485, 0.456, 0.406]` and `image_std=[0.229, 0.224, 0.225]`.
 
-- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+### Training Hyperparameters
 
-#### Speeds, Sizes, Times [optional]
+- **Training regime:** <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
 
-<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/6579e0eaa9e58aec614e9d97/E15I9MwZCtwNIms-W8Ra9.png)
 
-[More Information Needed]
 
 ## Evaluation
 
-<!-- This section describes the evaluation protocols and provides the results. -->
-
-### Testing Data, Factors & Metrics
-
-#### Testing Data
-
-<!-- This should link to a Dataset Card if possible. -->
-
-[More Information Needed]
-
-#### Factors
-
-<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
-
-[More Information Needed]
-
-#### Metrics
-
-<!-- These are the evaluation metrics being used, ideally with a description of why. -->
 
-[More Information Needed]
+| Model                      | #Epochs | #Params (M) | GFLOPs | FPS_bs=1 | AP (val) | AP50 (val) | AP75 (val) | AP-s (val) | AP-m (val) | AP-l (val) |
+|----------------------------|---------|-------------|--------|----------|--------|-----------|-----------|----------|----------|----------|
+| RT-DETR-R18   | 72      | 20          | 60.7   | 217      | 46.5   | 63.8      | 50.4      | 28.4     | 49.8     | 63.0     |
+| RT-DETR-R34   | 72      | 31         | 91.0   | 172      | 48.5   | 66.2      | 52.3      | 30.2     | 51.9     | 66.2     |
+| RT-DETR R50 | 72      | 42          | 136    | 108      | 53.1   | 71.3      | 57.7      | 34.8     | 58.0     | 70.0     |
+| RT-DETR R101| 72      | 76          | 259    | 74       | 54.3   | 72.7      | 58.6      | 36.0     | 58.8     | 72.1     |
+| RT-DETR-R18 (Objects 365 pretrained)   | 60      | 20          | 61     | 217      | 49.2  | 66.6      | 53.5      | 33.2     | 52.3     | 64.8     |
+| RT-DETR-R50 (Objects 365 pretrained)   | 24      | 42          | 136    | 108      | 55.3  | 73.4      | 60.1      | 37.9     | 59.9     | 71.8     |
+| RT-DETR-R101 (Objects 365 pretrained)  | 24      | 76          | 259    | 74       | 56.2  | 74.6      | 61.3      | 38.3     | 60.5     | 73.5     |
 
-### Results
 
-[More Information Needed]
-
-#### Summary
-
-
-
-## Model Examination [optional]
-
-<!-- Relevant interpretability work for the model goes here -->
-
-[More Information Needed]
-
-## Environmental Impact
-
-<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
-
-Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
-
-- **Hardware Type:** [More Information Needed]
-- **Hours used:** [More Information Needed]
-- **Cloud Provider:** [More Information Needed]
-- **Compute Region:** [More Information Needed]
-- **Carbon Emitted:** [More Information Needed]
-
-## Technical Specifications [optional]
 
 ### Model Architecture and Objective
 
-[More Information Needed]
-
-### Compute Infrastructure
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/6579e0eaa9e58aec614e9d97/sdIwTRlHNwPzyBNwHja60.png)
 
-[More Information Needed]
+Overview of RT-DETR. We feed the features from the last three stages of the backbone into the encoder. The efficient hybrid
+encoder transforms multi-scale features into a sequence of image features through the Attention-based Intra-scale Feature Interaction (AIFI)
+and the CNN-based Cross-scale Feature Fusion (CCFF). Then, the uncertainty-minimal query selection selects a fixed number of encoder
+features to serve as initial object queries for the decoder. Finally, the decoder with auxiliary prediction heads iteratively optimizes object
+queries to generate categories and boxes.
 
-#### Hardware
 
-[More Information Needed]
-
-#### Software
-
-[More Information Needed]
-
-## Citation [optional]
+## Citation
 
 <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
 
 **BibTeX:**
 
-[More Information Needed]
-
-**APA:**
-
-[More Information Needed]
-
-## Glossary [optional]
-
-<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
-
-[More Information Needed]
-
-## More Information [optional]
-
-[More Information Needed]
-
-## Model Card Authors [optional]
+```bibtex
+@misc{lv2023detrs,
+      title={DETRs Beat YOLOs on Real-time Object Detection},
+      author={Yian Zhao and Wenyu Lv and Shangliang Xu and Jinman Wei and Guanzhong Wang and Qingqing Dang and Yi Liu and Jie Chen},
+      year={2023},
+      eprint={2304.08069},
+      archivePrefix={arXiv},
+      primaryClass={cs.CV}
+}
+```
 
-[More Information Needed]
+## Model Card Authors
 
-## Model Card Contact
+[Sangbum Choi](https://huggingface.co/danelcsb)  
+[Pavel Iakubovskii](https://huggingface.co/qubvel-hf)
 
-[More Information Needed]