Update README.md (#3)
Browse files- Update README.md (2acf113f73a8325ebb459e2a7753bc4aa7ad6e09)
Co-authored-by: Sangbum Choi <[email protected]>
README.md
CHANGED
|
@@ -51,13 +51,15 @@ After pre-training with Objects365, RT-DETR-R50 / R101 achieves 55.3% / 56.2% AP
|
|
| 51 |
|
| 52 |
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
|
| 53 |
|
| 54 |
-
- **Developed by:**
|
| 55 |
-
- **Funded by [optional]:**
|
| 56 |
-
|
| 57 |
-
|
| 58 |
-
- **
|
| 59 |
-
- **
|
| 60 |
-
- **
|
|
|
|
|
|
|
| 61 |
|
| 62 |
### Model Sources [optional]
|
| 63 |
|
|
@@ -81,20 +83,14 @@ You can use the raw model for object detection. See the [model hub](https://hugg
|
|
| 81 |
|
| 82 |
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 83 |
|
| 84 |
-
[More Information Needed]
|
| 85 |
-
|
| 86 |
### Out-of-Scope Use
|
| 87 |
|
| 88 |
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 89 |
|
| 90 |
-
[More Information Needed]
|
| 91 |
-
|
| 92 |
## Bias, Risks, and Limitations
|
| 93 |
|
| 94 |
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 95 |
|
| 96 |
-
[More Information Needed]
|
| 97 |
-
|
| 98 |
### Recommendations
|
| 99 |
|
| 100 |
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
|
@@ -165,7 +161,7 @@ Images are resized/rescaled such that the shortest side is at 640 pixels.
|
|
| 165 |
|
| 166 |
#### Training Hyperparameters
|
| 167 |
|
| 168 |
-
- **Training regime:**
|
| 169 |
|
| 170 |

|
| 171 |
|
|
@@ -173,8 +169,6 @@ Images are resized/rescaled such that the shortest side is at 640 pixels.
|
|
| 173 |
|
| 174 |
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 175 |
|
| 176 |
-
[More Information Needed]
|
| 177 |
-
|
| 178 |
## Evaluation
|
| 179 |
|
| 180 |
<!-- This section describes the evaluation protocols and provides the results. -->
|
|
@@ -187,24 +181,16 @@ This model achieves an AP (average precision) of 53.1 on COCO 2017 validation. F
|
|
| 187 |
|
| 188 |
<!-- This should link to a Dataset Card if possible. -->
|
| 189 |
|
| 190 |
-
[More Information Needed]
|
| 191 |
-
|
| 192 |
#### Factors
|
| 193 |
|
| 194 |
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 195 |
|
| 196 |
-
[More Information Needed]
|
| 197 |
-
|
| 198 |
#### Metrics
|
| 199 |
|
| 200 |
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 201 |
|
| 202 |
-
[More Information Needed]
|
| 203 |
-
|
| 204 |
### Results
|
| 205 |
|
| 206 |
-
[More Information Needed]
|
| 207 |
-
|
| 208 |
#### Summary
|
| 209 |
|
| 210 |
|
|
@@ -213,19 +199,12 @@ This model achieves an AP (average precision) of 53.1 on COCO 2017 validation. F
|
|
| 213 |
|
| 214 |
<!-- Relevant interpretability work for the model goes here -->
|
| 215 |
|
| 216 |
-
[More Information Needed]
|
| 217 |
-
|
| 218 |
## Environmental Impact
|
| 219 |
|
| 220 |
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 221 |
|
| 222 |
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).
|
| 223 |
|
| 224 |
-
- **Hardware Type:** [More Information Needed]
|
| 225 |
-
- **Hours used:** [More Information Needed]
|
| 226 |
-
- **Cloud Provider:** [More Information Needed]
|
| 227 |
-
- **Compute Region:** [More Information Needed]
|
| 228 |
-
- **Carbon Emitted:** [More Information Needed]
|
| 229 |
|
| 230 |
## Technical Specifications [optional]
|
| 231 |
|
|
@@ -235,16 +214,10 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
|
|
| 235 |
|
| 236 |
### Compute Infrastructure
|
| 237 |
|
| 238 |
-
[More Information Needed]
|
| 239 |
-
|
| 240 |
#### Hardware
|
| 241 |
|
| 242 |
-
[More Information Needed]
|
| 243 |
-
|
| 244 |
#### Software
|
| 245 |
|
| 246 |
-
[More Information Needed]
|
| 247 |
-
|
| 248 |
## Citation [optional]
|
| 249 |
|
| 250 |
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
|
@@ -264,22 +237,14 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
|
|
| 264 |
|
| 265 |
**APA:**
|
| 266 |
|
| 267 |
-
[More Information Needed]
|
| 268 |
-
|
| 269 |
## Glossary [optional]
|
| 270 |
|
| 271 |
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 272 |
|
| 273 |
-
[More Information Needed]
|
| 274 |
-
|
| 275 |
## More Information [optional]
|
| 276 |
|
| 277 |
-
[More Information Needed]
|
| 278 |
-
|
| 279 |
## Model Card Authors [optional]
|
| 280 |
|
| 281 |
[Sangbum Choi](https://huggingface.co/danelcsb)
|
| 282 |
|
| 283 |
## Model Card Contact
|
| 284 |
-
|
| 285 |
-
[More Information Needed]
|
|
|
|
| 51 |
|
| 52 |
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
|
| 53 |
|
| 54 |
+
- **Developed by:** Yian Zhao and Sangbum Choi
|
| 55 |
+
- **Funded by [optional]:** National Key R&D Program of China (No.2022ZD0118201), Natural Science Foundation of China (No.61972217, 32071459, 62176249, 62006133, 62271465),
|
| 56 |
+
and the Shenzhen Medical Research Funds in China (No.
|
| 57 |
+
B2302037).
|
| 58 |
+
- **Shared by [optional]:** Sangbum Choi
|
| 59 |
+
- **Model type:**
|
| 60 |
+
- **Language(s) (NLP):**
|
| 61 |
+
- **License:** Apache-2.0
|
| 62 |
+
- **Finetuned from model [optional]:**
|
| 63 |
|
| 64 |
### Model Sources [optional]
|
| 65 |
|
|
|
|
| 83 |
|
| 84 |
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 85 |
|
|
|
|
|
|
|
| 86 |
### Out-of-Scope Use
|
| 87 |
|
| 88 |
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 89 |
|
|
|
|
|
|
|
| 90 |
## Bias, Risks, and Limitations
|
| 91 |
|
| 92 |
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 93 |
|
|
|
|
|
|
|
| 94 |
### Recommendations
|
| 95 |
|
| 96 |
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
|
|
|
| 161 |
|
| 162 |
#### Training Hyperparameters
|
| 163 |
|
| 164 |
+
- **Training regime:** <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 165 |
|
| 166 |

|
| 167 |
|
|
|
|
| 169 |
|
| 170 |
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 171 |
|
|
|
|
|
|
|
| 172 |
## Evaluation
|
| 173 |
|
| 174 |
<!-- This section describes the evaluation protocols and provides the results. -->
|
|
|
|
| 181 |
|
| 182 |
<!-- This should link to a Dataset Card if possible. -->
|
| 183 |
|
|
|
|
|
|
|
| 184 |
#### Factors
|
| 185 |
|
| 186 |
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 187 |
|
|
|
|
|
|
|
| 188 |
#### Metrics
|
| 189 |
|
| 190 |
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 191 |
|
|
|
|
|
|
|
| 192 |
### Results
|
| 193 |
|
|
|
|
|
|
|
| 194 |
#### Summary
|
| 195 |
|
| 196 |
|
|
|
|
| 199 |
|
| 200 |
<!-- Relevant interpretability work for the model goes here -->
|
| 201 |
|
|
|
|
|
|
|
| 202 |
## Environmental Impact
|
| 203 |
|
| 204 |
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 205 |
|
| 206 |
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).
|
| 207 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 208 |
|
| 209 |
## Technical Specifications [optional]
|
| 210 |
|
|
|
|
| 214 |
|
| 215 |
### Compute Infrastructure
|
| 216 |
|
|
|
|
|
|
|
| 217 |
#### Hardware
|
| 218 |
|
|
|
|
|
|
|
| 219 |
#### Software
|
| 220 |
|
|
|
|
|
|
|
| 221 |
## Citation [optional]
|
| 222 |
|
| 223 |
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
|
|
|
| 237 |
|
| 238 |
**APA:**
|
| 239 |
|
|
|
|
|
|
|
| 240 |
## Glossary [optional]
|
| 241 |
|
| 242 |
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 243 |
|
|
|
|
|
|
|
| 244 |
## More Information [optional]
|
| 245 |
|
|
|
|
|
|
|
| 246 |
## Model Card Authors [optional]
|
| 247 |
|
| 248 |
[Sangbum Choi](https://huggingface.co/danelcsb)
|
| 249 |
|
| 250 |
## Model Card Contact
|
|
|
|
|
|