topher217 commited on
Commit
5cfe7fc
·
1 Parent(s): aef2cd8

Reducing modelcard size template

Browse files
Files changed (1) hide show
  1. README.md +25 -120
README.md CHANGED
@@ -1,7 +1,6 @@
1
  ---
2
  language: en
3
- library_name: keras
4
- license: mit
5
  ---
6
 
7
  # Model Card for yolo5_beachbot_160
@@ -19,54 +18,34 @@ license: mit
19
  A finetune of Yolo5 intended for identifying beach trash.
20
 
21
  - **Developed by:** Jeffrey Queisser, Christopher Buckley
22
- - **Funded by [optional]:** Okinawa Institute of Science and Technology COI Next Grant
23
- - **Shared by [optional]:** [More Information Needed]
24
  - **Model type:** Yolo5
25
- - **Language(s) (NLP):** en
26
  - **License:** CC BY-NC 4.0
27
- - **Finetuned from model [optional]:** Yolo5
28
 
29
- ### Model Sources [optional]
30
 
31
  <!-- Provide the basic links for the model. -->
32
 
33
  - **Repository:** https://github.com/okinawa-ai-beach-robot/yolo5_beachbot_160
34
- - **Paper [optional]:** [More Information Needed]
35
- - **Demo [optional]:** [More Information Needed]
36
-
37
- ## Uses
38
-
39
- <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
40
-
41
- ### Direct Use
42
-
43
- <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
44
-
45
- [More Information Needed]
46
-
47
- ### Downstream Use [optional]
48
-
49
- <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
50
-
51
- [More Information Needed]
52
-
53
- ### Out-of-Scope Use
54
-
55
- <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
56
-
57
- [More Information Needed]
58
 
59
  ## Bias, Risks, and Limitations
60
 
61
  <!-- This section is meant to convey both technical and sociotechnical limitations. -->
62
 
63
- [More Information Needed]
 
 
 
64
 
65
  ### Recommendations
66
 
67
  <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
68
 
69
- Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
 
 
70
 
71
  ## How to Get Started with the Model
72
 
@@ -86,25 +65,19 @@ https://universe.roboflow.com/okinawaaibeachrobot/beach-cleaning-object-detectio
86
 
87
  <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
88
 
89
- #### Preprocessing [optional]
90
 
91
 
92
- {'preprocessing': {'auto-orient': True, 'resize': {'width': 1280, 'height': 800, 'format': 'Fill (with center crop) in'}}}
93
- See https://docs.roboflow.com/api-reference/versions/create-a-project-version for more information
94
-
95
 
96
 
97
  #### Training Hyperparameters
98
 
99
  - **Training regime:**
100
- TODO populate with any hyperparameters
101
- <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
102
-
103
- #### Speeds, Sizes, Times [optional]
104
-
105
- <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
106
-
107
- [More Information Needed]
108
 
109
  ## Evaluation
110
 
@@ -118,92 +91,24 @@ https://universe.roboflow.com/okinawaaibeachrobot/beach-cleaning-object-detectio
118
 
119
  https://universe.roboflow.com/okinawaaibeachrobot/beach-cleaning-object-detection/dataset/1/images?split=test
120
 
121
- #### Factors
122
-
123
- <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
124
-
125
- [More Information Needed]
126
-
127
  #### Metrics
128
 
129
  <!-- These are the evaluation metrics being used, ideally with a description of why. -->
130
 
131
 
132
- TODO populate with any metrics
133
- e.g. loss function
134
-
135
 
136
  ### Results
137
 
138
 
139
- TODO populate with any results
140
-
141
-
142
- #### Summary
143
-
144
-
145
- TODO
146
-
147
-
148
- ## Model Examination [optional]
149
-
150
- <!-- Relevant interpretability work for the model goes here -->
151
-
152
- [More Information Needed]
153
 
154
- ## Environmental Impact
155
-
156
- <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
157
-
158
- 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).
159
-
160
- - **Hardware Type:** TODO
161
- - **Hours used:** TODO
162
- - **Cloud Provider:** TODO
163
- - **Compute Region:** TODO
164
- - **Carbon Emitted:** TODO
165
-
166
- ## Technical Specifications [optional]
167
-
168
- ### Model Architecture and Objective
169
-
170
- [More Information Needed]
171
-
172
- ### Compute Infrastructure
173
-
174
- [More Information Needed]
175
-
176
- #### Hardware
177
-
178
- [More Information Needed]
179
-
180
- #### Software
181
-
182
- [More Information Needed]
183
-
184
- ## Citation [optional]
185
-
186
- <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
187
-
188
- **BibTeX:**
189
-
190
- [More Information Needed]
191
-
192
- **APA:**
193
-
194
- [More Information Needed]
195
-
196
- ## Glossary [optional]
197
-
198
- <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
199
-
200
- [More Information Needed]
201
-
202
- ## More Information [optional]
203
-
204
- [More Information Needed]
205
 
206
- ## Model Card Authors [optional]
207
 
208
  Christopher Buckley
209
 
 
1
  ---
2
  language: en
3
+ license: cc-by-nc-4.0
 
4
  ---
5
 
6
  # Model Card for yolo5_beachbot_160
 
18
  A finetune of Yolo5 intended for identifying beach trash.
19
 
20
  - **Developed by:** Jeffrey Queisser, Christopher Buckley
21
+ - **Funded by:** Okinawa Institute of Science and Technology COI Next Grant
 
22
  - **Model type:** Yolo5
 
23
  - **License:** CC BY-NC 4.0
24
+ - **Finetuned from model:** Yolo5
25
 
26
+ ### Model Sources
27
 
28
  <!-- Provide the basic links for the model. -->
29
 
30
  - **Repository:** https://github.com/okinawa-ai-beach-robot/yolo5_beachbot_160
31
+ - **Demo:** [Work in Progress]
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
32
 
33
  ## Bias, Risks, and Limitations
34
 
35
  <!-- This section is meant to convey both technical and sociotechnical limitations. -->
36
 
37
+
38
+ Note the dataset is small and test set can have quite similar images to the train set.
39
+ This was an early version of the dataset so results are not reliable
40
+
41
 
42
  ### Recommendations
43
 
44
  <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
45
 
46
+
47
+ Use later version of the dataset
48
+
49
 
50
  ## How to Get Started with the Model
51
 
 
65
 
66
  <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
67
 
68
+ #### Preprocessing
69
 
70
 
71
+ {'preprocessing': {'auto-orient': True, 'resize': {'width': 1280, 'height': 800, 'format': 'Fill (with center crop) in'}}}
72
+ See https://docs.roboflow.com/api-reference/versions/create-a-project-version for more information
73
+
74
 
75
 
76
  #### Training Hyperparameters
77
 
78
  - **Training regime:**
79
+ TODO populate with any hyperparameters
80
+ <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
 
 
 
 
 
 
81
 
82
  ## Evaluation
83
 
 
91
 
92
  https://universe.roboflow.com/okinawaaibeachrobot/beach-cleaning-object-detection/dataset/1/images?split=test
93
 
 
 
 
 
 
 
94
  #### Metrics
95
 
96
  <!-- These are the evaluation metrics being used, ideally with a description of why. -->
97
 
98
 
99
+ TODO populate with any metrics
100
+ e.g. loss function
101
+
102
 
103
  ### Results
104
 
105
 
106
+ TODO populate with any results
107
+
 
 
 
 
 
 
 
 
 
 
 
 
108
 
109
+ ## Technical Specifications
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
110
 
111
+ ## Model Card Authors
112
 
113
  Christopher Buckley
114