Update README.md (#5)

- Update README.md (ba74566142f4b2af096a2a0eaf1392804b6ea921)


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

README.md

@@ -22,17 +22,25 @@ widget:
 ---
 
 
-# Model Card for Model ID
+# Model Card for RT-DETR
 
-<!-- Provide a quick summary of what the model is/does. -->
 
+## Table of Contents
+
+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)
 
 
 ## Model Details
 
-### Model Description
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/6579e0eaa9e58aec614e9d97/WULSDLsCVs7RNEs9KB0Lr.png)
 
-The YOLO series has become the most popular framework for real-time object detection due to its reasonable trade-off between speed and accuracy. 
+> 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. 
@@ -47,61 +55,32 @@ We also develop scaled RT-DETRs that outperform the lighter YOLO detectors (S an
 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.
+
+This is the model card of a 🤗 [transformers](https://huggingface.co/docs/transformers/index) model that has been pushed on the Hub.
 
 - **Developed by:** Yian Zhao and Sangbum Choi
-- **Funded by [optional]:**  National Key R&D Program of China (No.2022ZD0118201), Natural Science Foundation of China (No.61972217, 32071459, 62176249, 62006133, 62271465),
+- **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 [optional]:** Sangbum Choi
-- **Model type:**
-- **Language(s) (NLP):** 
+- **Shared by:** Sangbum Choi
+- **Model type:** [RT-DETR](https://huggingface.co/docs/transformers/main/en/model_doc/rt_detr)
 - **License:** Apache-2.0
-- **Finetuned from model [optional]:** 
 
-### Model Sources [optional]
+### Model Sources
 
 <!-- Provide the basic links for the model. -->
 
+- **HF Docs:** [RT-DETR](https://huggingface.co/docs/transformers/main/en/model_doc/rt_detr)
 - **Repository:** https://github.com/lyuwenyu/RT-DETR
-- **Paper [optional]:** https://arxiv.org/abs/2304.08069
-- **Demo [optional]:** [More Information Needed]
-
-## Uses
-
-<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
-
-### Direct Use
-
-<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
-
-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]
-
-<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
-
-### Out-of-Scope Use
-
-<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
-
-## Bias, Risks, and Limitations
-
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
-
-### Recommendations
-
-<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
-
-Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+- **Paper:** https://arxiv.org/abs/2304.08069
+- **Demo:** [RT-DETR Tracking](https://huggingface.co/spaces/merve/RT-DETR-tracking-coco)
 
 ## How to Get Started with the Model
 
 Use the code below to get started with the model.
 
-```
+```python
 import torch
 import requests
 
@@ -148,77 +127,48 @@ The RTDETR model was trained on [COCO 2017 object detection](https://cocodataset
 
 <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
 
-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.
+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 [optional]
+### Preprocessing
 
-Images are resized/rescaled such that the shortest side is at 640 pixels.
+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 Hyperparameters
+### Training Hyperparameters
 
 - **Training regime:** <!--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. -->
 
 ## Evaluation
 
-<!-- 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
+| 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     |
 
-#### Testing Data
 
-<!-- This should link to a Dataset Card if possible. -->
-
-#### Factors
-
-<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
-
-#### Metrics
-
-<!-- These are the evaluation metrics being used, ideally with a description of why. -->
-
-### Results
-
-#### Summary
-
-
-
-## Model Examination [optional]
-
-<!-- Relevant interpretability work for the model goes here -->
-
-## 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).
-
-
-## Technical Specifications [optional]
 
 ### Model Architecture and Objective
 
 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6579e0eaa9e58aec614e9d97/sdIwTRlHNwPzyBNwHja60.png)
 
-### Compute Infrastructure
+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
 
-#### Software
-
-## 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. -->
 
@@ -235,16 +185,8 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
 }
 ```
 
-**APA:**
-
-## Glossary [optional]
-
-<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
-
-## More Information [optional]
-
-## Model Card Authors [optional]
+## Model Card Authors
 
-[Sangbum Choi](https://huggingface.co/danelcsb)
+[Sangbum Choi](https://huggingface.co/danelcsb)  
+[Pavel Iakubovskii](https://huggingface.co/qubvel-hf)
 
-## Model Card Contact