amyeroberts HF staff danelcsb commited on
Commit
6a7e585
·
verified ·
1 Parent(s): dd63d92

Update README.md (#3)

Browse files

- Update README.md (2acf113f73a8325ebb459e2a7753bc4aa7ad6e09)


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

Files changed (1) hide show
  1. README.md +10 -45
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:** [More Information Needed]
55
- - **Funded by [optional]:** [More Information Needed]
56
- - **Shared by [optional]:** [More Information Needed]
57
- - **Model type:** [More Information Needed]
58
- - **Language(s) (NLP):** [More Information Needed]
59
- - **License:** [More Information Needed]
60
- - **Finetuned from model [optional]:** [More Information Needed]
 
 
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:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
169
 
170
  ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6579e0eaa9e58aec614e9d97/E15I9MwZCtwNIms-W8Ra9.png)
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
  ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6579e0eaa9e58aec614e9d97/E15I9MwZCtwNIms-W8Ra9.png)
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