rwood-97 commited on
Commit
0eec939
1 Parent(s): 81c12d7

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +12 -2
README.md CHANGED
@@ -18,7 +18,7 @@ datasets:
18
  - Livingwithmachines/MapReader_Data_SIGSPATIAL_2022
19
  ---
20
 
21
- # Model Card for mr_resnest101e_timm_no_pretrain
22
 
23
  A ResNeSt (ResNet based architecture with Split Attention) image classification model.
24
  Trained on gold standard annotations and outputs from early experiments using MapReader (found [here](https://huggingface.co/datasets/Livingwithmachines/MapReader_Data_SIGSPATIAL_2022)).
@@ -30,9 +30,19 @@ Trained on gold standard annotations and outputs from early experiments using Ma
30
  - **Model type:** Image classification /feature backbone
31
  - **Finetuned from model:** https://huggingface.co/timm/resnest101e.in1k
32
 
 
 
 
 
 
 
 
33
  ## Uses
34
 
35
- 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.
 
 
 
36
 
37
  ## How to Get Started with the Model in MapReader
38
 
 
18
  - Livingwithmachines/MapReader_Data_SIGSPATIAL_2022
19
  ---
20
 
21
+ # Model Card for mr_resnest101e_timm_no_pretrain_railspace_and_building
22
 
23
  A ResNeSt (ResNet based architecture with Split Attention) image classification model.
24
  Trained on gold standard annotations and outputs from early experiments using MapReader (found [here](https://huggingface.co/datasets/Livingwithmachines/MapReader_Data_SIGSPATIAL_2022)).
 
30
  - **Model type:** Image classification /feature backbone
31
  - **Finetuned from model:** https://huggingface.co/timm/resnest101e.in1k
32
 
33
+ ### Classes and labels
34
+
35
+ - 0: no
36
+ - 1: railspace
37
+ - 2: building
38
+ - 3: railspace & building
39
+
40
  ## Uses
41
 
42
+ This fine-tuned version of the model is an output of the MapReader pipeline.
43
+ 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/)).
44
+ We classified patches to indicate the presence of buildings and railway infrastructure.
45
+ See [our paper](https://dl.acm.org/doi/10.1145/3557919.3565812) for more details about labels.
46
 
47
  ## How to Get Started with the Model in MapReader
48