drjpepper44
commited on
Commit
•
30a81d6
1
Parent(s):
92c2917
Update README.md
Browse files
README.md
CHANGED
@@ -54,9 +54,9 @@ See the [Glossary](#Glossary) below for a detailed list of the properties genera
|
|
54 |
|
55 |
|
56 |
- **Developed by:** Joel Pepper and Kevin Karnani
|
57 |
-
|
58 |
-
- **Model type:**
|
59 |
-
|
60 |
- **License:** MIT <!-- As listed on the repo -->
|
61 |
- **Finetuned from model:** [detectron2 v0.6](https://github.com/facebookresearch/detectron2)
|
62 |
|
@@ -89,30 +89,31 @@ Object detection is currently being performed on 5 detection classes (fish, fish
|
|
89 |
8. These do not need to be adhered to if properly set up/modified for a specific use case.
|
90 |
|
91 |
|
92 |
-
|
|
|
93 |
|
94 |
-
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
95 |
|
96 |
[More Information Needed]
|
97 |
|
98 |
### Out-of-Scope Use
|
99 |
|
100 |
-
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
101 |
|
102 |
-
[More Information Needed]
|
103 |
|
104 |
## Bias, Risks, and Limitations
|
105 |
|
106 |
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
107 |
|
108 |
-
This model was trained solely for use on fish specimens.
|
|
|
|
|
109 |
|
110 |
<!-- [More Information Needed] -->
|
111 |
|
112 |
The authors have declared that no conflict of interest exists.
|
113 |
|
114 |
|
115 |
-
|
116 |
|
117 |
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
118 |
|
@@ -213,21 +214,15 @@ pipenv run python3 train_model.py
|
|
213 |
|
214 |
#### Preprocessing [optional]
|
215 |
|
216 |
-
|
217 |
-
|
218 |
|
219 |
#### Training Hyperparameters
|
220 |
|
221 |
-
-
|
222 |
-
|
223 |
-
#### Speeds, Sizes, Times [optional]
|
224 |
-
|
225 |
-
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
226 |
-
|
227 |
-
[More Information Needed]
|
228 |
|
229 |
## Evaluation
|
230 |
|
|
|
231 |
<!-- This section describes the evaluation protocols and provides the results. -->
|
232 |
|
233 |
### Testing Data, Factors & Metrics
|
@@ -235,33 +230,25 @@ pipenv run python3 train_model.py
|
|
235 |
#### Testing Data
|
236 |
|
237 |
<!-- This should link to a Data Card if possible. -->
|
238 |
-
|
239 |
-
[More Information Needed]
|
240 |
|
241 |
#### Factors
|
242 |
|
|
|
243 |
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
244 |
|
245 |
-
[More Information Needed]
|
246 |
-
|
247 |
#### Metrics
|
248 |
|
|
|
249 |
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
250 |
|
251 |
-
[More Information Needed]
|
252 |
|
253 |
### Results
|
254 |
|
255 |
-
|
256 |
|
257 |
#### Summary
|
258 |
|
259 |
-
|
260 |
-
|
261 |
-
## Model Examination
|
262 |
-
|
263 |
-
<!-- Relevant interpretability work for the model goes here -->
|
264 |
-
|
265 |
### Goal
|
266 |
|
267 |
To develop a tool to check the validity of metadata associated with an image, and generate things that are missing. Also includes various geometric and statistical properties on the mask generated over the biological specimen presented.
|
@@ -279,33 +266,18 @@ The metadata generated produces various statistical and geometric properties of
|
|
279 |
|
280 |
## Environmental Impact
|
281 |
|
282 |
-
|
283 |
-
|
284 |
-
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://doi.org/10.48550/arXiv.1910.09700).
|
285 |
-
|
286 |
-
- **Hardware Type:** [More Information Needed]
|
287 |
-
- **Hours used:** [More Information Needed]
|
288 |
-
- **Cloud Provider:** [More Information Needed]
|
289 |
-
- **Compute Region:** [More Information Needed]
|
290 |
-
- **Carbon Emitted:** [More Information Needed]
|
291 |
|
292 |
## Technical Specifications [optional]
|
293 |
|
294 |
### Model Architecture and Objective
|
295 |
|
296 |
-
|
297 |
|
298 |
### Compute Infrastructure
|
299 |
|
300 |
-
|
301 |
-
|
302 |
-
#### Hardware
|
303 |
-
|
304 |
-
[More Information Needed]
|
305 |
-
|
306 |
-
#### Software
|
307 |
|
308 |
-
[More Information Needed]
|
309 |
|
310 |
## Citation
|
311 |
|
|
|
54 |
|
55 |
|
56 |
- **Developed by:** Joel Pepper and Kevin Karnani
|
57 |
+
<!--- **Shared by [optional]:** [More Information Needed]-->
|
58 |
+
- **Model type:** Pytorch pickle file (.pth)
|
59 |
+
<!--- **Language(s) (NLP):** [More Information Needed]-->
|
60 |
- **License:** MIT <!-- As listed on the repo -->
|
61 |
- **Finetuned from model:** [detectron2 v0.6](https://github.com/facebookresearch/detectron2)
|
62 |
|
|
|
89 |
8. These do not need to be adhered to if properly set up/modified for a specific use case.
|
90 |
|
91 |
|
92 |
+
<!--### Downstream Use [optional]
|
93 |
+
|
94 |
|
|
|
95 |
|
96 |
[More Information Needed]
|
97 |
|
98 |
### Out-of-Scope Use
|
99 |
|
|
|
100 |
|
101 |
+
[More Information Needed]-->
|
102 |
|
103 |
## Bias, Risks, and Limitations
|
104 |
|
105 |
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
106 |
|
107 |
+
- This model was trained solely for use on fish specimens.
|
108 |
+
- The model can detect and process multiple fish within a single image, although the capability is not extensively tested.
|
109 |
+
- The model was only trained on rectangular, machine printed tags that are aligned with the image (i.e. tags placed at an angle may not be handled correctly).
|
110 |
|
111 |
<!-- [More Information Needed] -->
|
112 |
|
113 |
The authors have declared that no conflict of interest exists.
|
114 |
|
115 |
|
116 |
+
<!--### Recommendations-->
|
117 |
|
118 |
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
119 |
|
|
|
214 |
|
215 |
#### Preprocessing [optional]
|
216 |
|
217 |
+
- Manual image preprocessing is not necessary. Some versions of the code do however contrast enhance the images internally (see [Citation](#Citation))
|
|
|
218 |
|
219 |
#### Training Hyperparameters
|
220 |
|
221 |
+
- See [Citation](#Citation)/source code.
|
|
|
|
|
|
|
|
|
|
|
|
|
222 |
|
223 |
## Evaluation
|
224 |
|
225 |
+
- See [Citation](#Citation)
|
226 |
<!-- This section describes the evaluation protocols and provides the results. -->
|
227 |
|
228 |
### Testing Data, Factors & Metrics
|
|
|
230 |
#### Testing Data
|
231 |
|
232 |
<!-- This should link to a Data Card if possible. -->
|
233 |
+
- See [Citation](#Citation)
|
|
|
234 |
|
235 |
#### Factors
|
236 |
|
237 |
+
- See [Citation](#Citation)
|
238 |
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
239 |
|
|
|
|
|
240 |
#### Metrics
|
241 |
|
242 |
+
- See [Citation](#Citation)
|
243 |
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
244 |
|
|
|
245 |
|
246 |
### Results
|
247 |
|
248 |
+
- See [Citation](#Citation)
|
249 |
|
250 |
#### Summary
|
251 |
|
|
|
|
|
|
|
|
|
|
|
|
|
252 |
### Goal
|
253 |
|
254 |
To develop a tool to check the validity of metadata associated with an image, and generate things that are missing. Also includes various geometric and statistical properties on the mask generated over the biological specimen presented.
|
|
|
266 |
|
267 |
## Environmental Impact
|
268 |
|
269 |
+
Extremely minimal as a regular workstation computer was used for this paper.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
270 |
|
271 |
## Technical Specifications [optional]
|
272 |
|
273 |
### Model Architecture and Objective
|
274 |
|
275 |
+
- See [Citation](#Citation)
|
276 |
|
277 |
### Compute Infrastructure
|
278 |
|
279 |
+
- Desktop computer with an Intel(R) Xeon(R) W-2175 CPU and an Nvidia Quadro RTX 4000 GPU.
|
|
|
|
|
|
|
|
|
|
|
|
|
280 |
|
|
|
281 |
|
282 |
## Citation
|
283 |
|