rwood-97 commited on
Commit
3c16556
1 Parent(s): b48e84c

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +22 -127
README.md CHANGED
@@ -17,161 +17,56 @@ tags:
17
 
18
  # Model Card for mr_resnest50d_4s2x40d_timm_pretrain
19
 
20
- <!-- Provide a quick summary of what the model is/does. -->
21
-
22
- {{ model_summary | default("", true) }}
23
 
24
  ## Model Details
25
 
26
  ### Model Description
27
 
28
- <!-- Provide a longer summary of what this model is. -->
29
-
30
- {{ model_description | default("", true) }}
31
-
32
- - **Developed by:** {{ developers | default("[More Information Needed]", true)}}
33
- - **Shared by [optional]:** {{ shared_by | default("[More Information Needed]", true)}}
34
- - **Model type:** {{ model_type | default("[More Information Needed]", true)}}
35
- - **Language(s) (NLP):** {{ language | default("[More Information Needed]", true)}}
36
- - **License:** {{ license | default("[More Information Needed]", true)}}
37
- - **Finetuned from model [optional]:** {{ finetuned_from | default("[More Information Needed]", true)}}
38
-
39
- ### Model Sources [optional]
40
-
41
- <!-- Provide the basic links for the model. -->
42
-
43
- - **Repository:** {{ repo | default("[More Information Needed]", true)}}
44
- - **Paper [optional]:** {{ paper | default("[More Information Needed]", true)}}
45
- - **Demo [optional]:** {{ demo | default("[More Information Needed]", true)}}
46
 
47
  ## Uses
48
 
49
- <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
50
-
51
- ### Direct Use
52
-
53
- <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
54
-
55
- {{ direct_use | default("[More Information Needed]", true)}}
56
-
57
- ### Downstream Use [optional]
58
-
59
- <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
60
-
61
- {{ downstream_use | default("[More Information Needed]", true)}}
62
-
63
- ### Out-of-Scope Use
64
-
65
- <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
66
-
67
- {{ out_of_scope_use | default("[More Information Needed]", true)}}
68
-
69
- ## Bias, Risks, and Limitations
70
-
71
- <!-- This section is meant to convey both technical and sociotechnical limitations. -->
72
-
73
- {{ bias_risks_limitations | default("[More Information Needed]", true)}}
74
-
75
- ### Recommendations
76
-
77
- <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
78
-
79
- {{ bias_recommendations | default("Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.", true)}}
80
-
81
- ## How to Get Started with the Model
82
-
83
- Use the code below to get started with the model.
84
-
85
- {{ get_started_code | default("[More Information Needed]", true)}}
86
-
87
- ## Training Details
88
-
89
- ### Training Data
90
 
91
- <!-- This should link to a Data Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
92
 
93
- {{ training_data | default("[More Information Needed]", true)}}
94
 
95
- ### Training Procedure
96
 
97
- <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
98
 
99
- #### Preprocessing [optional]
100
 
101
- {{ preprocessing | default("[More Information Needed]", true)}}
102
 
 
103
 
104
- #### Training Hyperparameters
105
-
106
- - **Training regime:** {{ training_regime | default("[More Information Needed]", true)}} <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
107
-
108
- #### Speeds, Sizes, Times [optional]
109
-
110
- <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
111
-
112
- {{ speeds_sizes_times | default("[More Information Needed]", true)}}
113
-
114
- ## Evaluation
115
-
116
- <!-- This section describes the evaluation protocols and provides the results. -->
117
-
118
- ### Testing Data, Factors & Metrics
119
-
120
- #### Testing Data
121
-
122
- <!-- This should link to a Data Card if possible. -->
123
-
124
- {{ testing_data | default("[More Information Needed]", true)}}
125
-
126
- #### Factors
127
-
128
- <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
129
-
130
- {{ testing_factors | default("[More Information Needed]", true)}}
131
-
132
- #### Metrics
133
-
134
- <!-- These are the evaluation metrics being used, ideally with a description of why. -->
135
-
136
- {{ testing_metrics | default("[More Information Needed]", true)}}
137
 
138
  ### Results
139
 
140
- {{ results | default("[More Information Needed]", true)}}
141
-
142
- #### Summary
143
-
144
- {{ results_summary | default("", true) }}
145
-
146
- ## Model Examination [optional]
147
-
148
- <!-- Relevant interpretability work for the model goes here -->
149
-
150
- {{ model_examination | default("[More Information Needed]", true)}}
151
-
152
- ## Citation [optional]
153
-
154
- <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
155
-
156
- **BibTeX:**
157
-
158
- {{ citation_bibtex | default("[More Information Needed]", true)}}
159
 
160
- **APA:**
161
 
162
- {{ citation_apa | default("[More Information Needed]", true)}}
163
 
164
- ## More Information [optional]
165
 
166
- {{ more_information | default("[More Information Needed]", true)}}
167
 
168
- ## Model Card Authors [optional]
169
 
170
- {{ model_card_authors | default("[More Information Needed]", true)}}
 
171
 
172
  ## Model Card Contact
173
 
174
- {{ model_card_contact | default("[More Information Needed]", true)}}
175
 
176
  ## Funding Statement
177
 
 
17
 
18
  # Model Card for mr_resnest50d_4s2x40d_timm_pretrain
19
 
20
+ A ResNeSt (ResNet based architecture with Split Attention) image classification model.
21
+ Trained on ImageNet-1k by paper authors and fine-tuned on gold standard annotations and outputs from early experiments using MapReader (found [here](https://huggingface.co/datasets/Livingwithmachines/MapReader_Data_SIGSPATIAL_2022)).
 
22
 
23
  ## Model Details
24
 
25
  ### Model Description
26
 
27
+ - **Model type:** Image classification /feature backbone
28
+ - **Finetuned from model:** https://huggingface.co/timm/resnest50d_4s2x40d.in1k
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
29
 
30
  ## Uses
31
 
32
+ This fine-tuned version of the model is an output of the MapReader pipeline. It was used to classify 'patch' images (cells/regions) of scanned nineteenth-century series maps of Britain provided by the National Library of Scotland (learn more [here](https://maps.nls.uk/os/)). We classified patches to indicate the presence of buildings and railway infrastructure. See [our paper](https://dl.acm.org/doi/10.1145/3557919.3565812) for more details about labels.
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
33
 
34
+ ## How to Get Started with the Model in MapReader
35
 
36
+ Please go to [the MapReader documentation](https://mapreader.readthedocs.io/en/latest/User-guide/Classify.html) for instructions on how to use this model in MapReader.
37
 
38
+ ## Training, Evaluation and Testing Details
39
 
40
+ ### Training, Evaluation and Testing Data
41
 
42
+ This model was fine-tuned on [manually-annotated data](https://huggingface.co/datasets/Livingwithmachines/MapReader_Data_SIGSPATIAL_2022).
43
 
44
+ ### Training, Evaluation and Testing Procedure
45
 
46
+ Details can be found [here](https://dl.acm.org/doi/10.1145/3557919.3565812).
47
 
48
+ Open access version of the article available [here](https://arxiv.org/abs/2111.15592).
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
49
 
50
  ### Results
51
 
52
+ Data outputs can be found [here](https://huggingface.co/datasets/Livingwithmachines/MapReader_Data_SIGSPATIAL_2022).
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
53
 
54
+ Further details can be found [here](https://dl.acm.org/doi/10.1145/3557919.3565812).
55
 
56
+ ## More Information
57
 
58
+ This model was fine-tuned using MapReader.
59
 
60
+ The code for MapReader can be found [here](https://github.com/Living-with-machines/MapReader) and the documentation can be found [here](https://mapreader.readthedocs.io/en/latest/).
61
 
62
+ ## Model Card Authors
63
 
64
+ - Katie McDonough (k.mcdonough@lancaster.ac.uk)
65
+ - Rosie Wood (rwood@turing.ac.uk)
66
 
67
  ## Model Card Contact
68
 
69
+ Katie McDonough (k.mcdonough@lancaster.ac.uk)
70
 
71
  ## Funding Statement
72