Added class threshold

.gitattributes

@@ -34,3 +34,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 20230216-soft-none/variables/variables.data-00000-of-00001 filter=lfs diff=lfs merge=lfs -text
+.DS_Store

README.md

@@ -3,9 +3,9 @@ license: cc-by-sa-4.0
 language:
 - en
 ---
-# phytoClassUCSC
+# phytoClassUCSC - A phytoplankton classifier for IFCB data
 
-Sections and prompts from the [model cards paper](https://arxiv.org/abs/1810.03993), v2.
+Note: Sections and prompts from the [model cards paper](https://arxiv.org/abs/1810.03993), v2.
 
 Jump to section:
 
@@ -21,17 +21,13 @@ Jump to section:
 
 ## Model details
 
-Review section 4.1 of the [model cards paper](https://arxiv.org/abs/1810.03993).
-
 - Developed by the Kudela Lab from the Ocean Sciences Department at University of California, Santa Cruz.
 - Current version trained in February, 2023.
-- phytoClassUCSC-SoftNone02162023
+- Version 1.0
 - phytoClassUCSC is a depthwise- CNN based on the Xception architecture [Chollet, F., 2017](https://arxiv.org/abs/1610.02357) with 134 layers using weights pretrained on ImageNet.
 - An average pooling layer is used.
-- Paper or other resource for more information
-- Citation details
-- License
-- Email Patrick Daniel ([pcdaniel@ucsc.edu](pcdaniel@ucsc.edu)) for questions
+- Licensed under CC-BY-SA-4.0
+- For Questions email Patrick Daniel ([pcdaniel@ucsc.edu](pcdaniel@ucsc.edu))
 
 ## Intended use
 
@@ -43,7 +39,7 @@ Review section 4.2 of the [model cards paper](https://arxiv.org/abs/1810.03993).
 
 ### Primary intended uses
 
-Generalized phytoplankton classifier for common taxa found in the Monterey Bay. 
+Generalized phytoplankton classifier for common taxa found in the Monterey Bay. This 
 
 ### Primary intended users
 
@@ -111,21 +107,10 @@ Review section 4.7 of the [model cards paper](https://arxiv.org/abs/1810.03993).
 
 ## Ethical considerations
 
-_This section is intended to demonstrate the ethical considerations that went into model development,
-surfacing ethical challenges and solutions to stakeholders. Ethical analysis does not always lead to
-precise solutions, but the process of ethical contemplation is worthwhile to inform on responsible
-practices and next steps in future work._
-
-Review section 4.8 of the [model cards paper](https://arxiv.org/abs/1810.03993).
+None
 
 ### Data
 
-### Human life
-
-### Mitigations
-
-### Risks and harms
-
 ### Use cases
 
 ## Caveats and recommendations

class_threshold_v1.0.json

@@ -0,0 +1 @@
+{"Akashiwo": 0.95, "Alexandrium_singlet": 0.49, "Amy_Gony_Protoc": 0.35, "Asterionellopsis": 0.56, "Boreadinium": 0.45, "Centric": 0.7, "Ceratium": 0.95, "Chaetoceros": 0.89, "Ciliates": 0.49, "Clusterflagellate": 0.55, "Cochlodinium": 0.48, "Corethron": 0.29, "Cryptophyte": 0.38, "Cyl_Nitz": 0.56, "Det_Cer_Lau": 0.52, "Dictyocha": 0.6, "Dinophysis": 0.92, "Ditylum": 0.27, "Entomoneis": 0.38, "Eucampia": 0.88, "FlagMix": 0.81, "Guin_Dact": 0.37, "Gymnodinium": 0.42, "Gyrodinium": 0.63, "Hemiaulus": 0.47, "Leptocylindrus": 0.62, "Licmophora": 0.57, "Lingulodinium": 0.56, "Mesodinium": 0.39, "NanoP_less10": 0.92, "Odontella": 0.51, "Pennate": 0.81, "Peridinium": 0.44, "Phaeocystis": 0.81, "Pleurosigma": 0.35, "Polykrikos": 0.79, "Prorocentrum": 0.92, "Protoperidinium": 0.73, "Pseudo-nitzschia": 0.62, "Pyramimonas": 0.4, "Rhiz_Prob": 0.47, "Scrip_Het": 0.71, "Skeletonema": 0.43, "Thalassionema": 0.62, "Thalassiosira": 0.36, "Tiarina": 0.44, "Tintinnid": 0.94, "Tontonia": 0.46, "Torodinium": 0.49, "Tropidoneis": 0.45, "Vicicitus": 0.41}