Update README.md (#2)

- Update README.md (4e385cf644c8cdc1c2dd709b8ed48302da225528)


Co-authored-by: Sangbum Choi <[email protected]>

README.md

@@ -1,6 +1,9 @@
 ---
 library_name: transformers
-tags: []
+license: apache-2.0
+language:
+- en
+pipeline_tag: object-detection
 ---
 
 # Model Card for Model ID
@@ -13,7 +16,22 @@ tags: []
 
 ### Model Description
 
-<!-- Provide a longer summary of what this model is. -->
+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/).
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/6579e0eaa9e58aec614e9d97/WULSDLsCVs7RNEs9KB0Lr.png)
 
 This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
 
@@ -29,8 +47,8 @@ This is the model card of a 🤗 transformers model that has been pushed on the
 
 <!-- Provide the basic links for the model. -->
 
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
+- **Repository:** https://github.com/lyuwenyu/RT-DETR
+- **Paper [optional]:** https://arxiv.org/abs/2304.08069
 - **Demo [optional]:** [More Information Needed]
 
 ## Uses
@@ -41,7 +59,7 @@ This is the model card of a 🤗 transformers model that has been pushed on the
 
 <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
 
-[More Information Needed]
+You can use the raw model for object detection. See the [model hub](https://huggingface.co/models?search=rtdetr) to look for all available RTDETR models.
 
 ### Downstream Use [optional]
 
@@ -71,7 +89,40 @@ Users (both direct and downstream) should be made aware of the risks, biases and
 
 Use the code below to get started with the model.
 
-[More Information Needed]
+```
+import torch
+import requests
+
+from PIL import Image
+from transformers import RTDetrForObjectDetection, RTDetrImageProcessor
+
+url = 'http://images.cocodataset.org/val2017/000000039769.jpg' 
+image = Image.open(requests.get(url, stream=True).raw)
+
+image_processor = RTDetrImageProcessor.from_pretrained("PekingU/rtdetr_r50vd")
+model = RTDetrForObjectDetection.from_pretrained("PekingU/rtdetr_r50vd")
+
+inputs = image_processor(images=image, return_tensors="pt")
+
+with torch.no_grad():
+    outputs = model(**inputs)
+
+results = image_processor.post_process_object_detection(outputs, target_sizes=torch.tensor([image.size[::-1]]), threshold=0.3)
+
+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
 
@@ -79,21 +130,29 @@ 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]
+We conduct experiments on
+COCO [20] and Objects365 [35], 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.
 
-[More Information Needed]
+#### Preprocessing [optional]
 
+Images are resized/rescaled such that the shortest side is at 640 pixels.
 
 #### Training Hyperparameters
 
 - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
 
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/6579e0eaa9e58aec614e9d97/E15I9MwZCtwNIms-W8Ra9.png)
+
 #### Speeds, Sizes, Times [optional]
 
 <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
@@ -104,6 +163,8 @@ Use the code below to get started with the model.
 
 <!-- This section describes the evaluation protocols and provides the results. -->
 
+This model achieves an AP (average precision) of 53.1 on COCO 2017 validation. For more details regarding evaluation results, we refer to table 2 of the original paper.
+
 ### Testing Data, Factors & Metrics
 
 #### Testing Data
@@ -154,7 +215,7 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
 
 ### Model Architecture and Objective
 
-[More Information Needed]
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/6579e0eaa9e58aec614e9d97/sdIwTRlHNwPzyBNwHja60.png)
 
 ### Compute Infrastructure
 
@@ -174,7 +235,16 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
 
 **BibTeX:**
 
-[More Information Needed]
+```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}
+}
+```
 
 **APA:**
 
@@ -192,7 +262,7 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
 
 ## Model Card Authors [optional]
 
-[More Information Needed]
+[Sangbum Choi](https://huggingface.co/danelcsb)
 
 ## Model Card Contact