Update README.md

README.md

@@ -4,16 +4,19 @@ base_model: facebook/convnextv2-nano-22k-384
 tags:
 - image-classification
 - vision
-- generated_from_trainer
+- boulderspot
+- climbing
+- aerial imagery
+- remote sensing
+- bouldering
 metrics:
 - accuracy
 - f1
 - precision
 - recall
 - matthews_correlation
-model-index:
-- name: convnextv2-nano-22k-384-boulderspot-vN
-  results: []
+datasets:
+- pszemraj/boulderspot
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -21,6 +24,14 @@ should probably proofread and complete it, then remove this comment. -->
 
 # convnextv2-nano-22k-384-boulderspot-vN
 
+
+This is a model fine-tuned to classify whether an aerial/satellite image contains a climbing area or not.
+
+You can find some images to test inference with [in this old repo from the original project](https://github.com/pszemraj/BoulderAreaDetector/tree/cbb22bdb3373b4b72d798dedfcb28543c0dc769d/test_images)
+
+
+## Model description
+
 This model is a fine-tuned version of [facebook/convnextv2-nano-22k-384](https://huggingface.co/facebook/convnextv2-nano-22k-384) on the pszemraj/boulderspot dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.0340
@@ -30,17 +41,9 @@ It achieves the following results on the evaluation set:
 - Recall: 0.9883
 - Matthews Correlation: 0.8962
 
-## Model description
-
-More information needed
-
 ## Intended uses & limitations
 
-More information needed
-
-## Training and evaluation data
-
-More information needed
+Classification of aerial/satellite imagery, ideally with spacial resolution 10-25 cm (_i.e. for 10 cm, each pixel in the image corresonds to approx. 10 cm x 10 cm area on the ground_). It may be suitable outside of that, but should be validated as other resolutions were not present in the training data.
 
 ## Training procedure