English
patcdaniel commited on
Commit
8ca3ad4
1 Parent(s): cede70d

Update README.md

Browse files

Continue to fill in the model card

Files changed (1) hide show
  1. README.md +10 -3
README.md CHANGED
@@ -35,20 +35,27 @@ Review section 4.1 of the [model cards paper](https://arxiv.org/abs/1810.03993).
35
 
36
  ## Intended use
37
 
38
- _Use cases that were envisioned during development._
 
 
39
 
40
  Review section 4.2 of the [model cards paper](https://arxiv.org/abs/1810.03993).
41
 
42
  ### Primary intended uses
43
 
 
 
44
  ### Primary intended users
45
 
 
 
46
  ### Out-of-scope use cases
47
 
 
 
48
  ## Factors
49
 
50
- _Factors could include demographic or phenotypic groups, environmental conditions, technical
51
- attributes, or others listed in Section 4.3._
52
 
53
  Review section 4.3 of the [model cards paper](https://arxiv.org/abs/1810.03993).
54
 
 
35
 
36
  ## Intended use
37
 
38
+ This model was designed and trained to work with IFCB data generated in Monterey Bay. While that does not mean it may not perform well in other locations, the distribution of training images reflects common phytoplankton observed at the Santa Cruz Wharf and Power Buoy locations.
39
+
40
+ Independent model validation should be used when applying the model to other sites.
41
 
42
  Review section 4.2 of the [model cards paper](https://arxiv.org/abs/1810.03993).
43
 
44
  ### Primary intended uses
45
 
46
+ Generalized phytoplankton classifier for common taxa found in the Monterey Bay.
47
+
48
  ### Primary intended users
49
 
50
+ IFCB users or researchers interested in phytoplankton ecology.
51
+
52
  ### Out-of-scope use cases
53
 
54
+ Observing and identifying rare or non-endemic taxa.
55
+
56
  ## Factors
57
 
58
+ Model classes were chosen based on common and resolvable phytoplankton taxa. Taxonomic groupings were chosen based on what researchers in the lab felt groups that could be confidently identified, given the expertise and research intersts of the lab.
 
59
 
60
  Review section 4.3 of the [model cards paper](https://arxiv.org/abs/1810.03993).
61