Update README.md

README.md

@@ -6,22 +6,24 @@ metrics:
 pipeline_tag: image-classification
 tags:
 - biology
-- vision
+- efficientnet-b2
 - image-classification
-widgets:
-- src: https://upload.wikimedia.org/wikipedia/commons/thumb/4/45/Eopsaltria_australis_-_Mogo_Campground.jpg/640px-Eopsaltria_australis_-_Mogo_Campground.jpg
-  example_title: Eastern Yellow Robin
-- src: https://peregrinefund.org/sites/default/files/styles/raptor_banner_600x430/public/2019-11/raptor-er-bald-eagle-portrait-screaming-james-bodkin.jpg?itok=ruN52TUp
-  example_title: Bald Eagle
+- vision
 ---
 
 # Bird Classifier EfficientNet-B2 
 
 ## Model Description
 
+Have you look at a bird and said "Woahh if only I know what bird that is". 
+Unless you're an avid bird spotter (or just love birds in general), it's hard to differentiate some species of birds.
+Well you're in luck, turns out you can use a image classifier to identify bird species!
+
 This model is a fine-tuned version of [google/efficientnet-b2](https://huggingface.co/google/efficientnet-b2)
 on the [gpiosenka/100-bird-species](https://www.kaggle.com/datasets/gpiosenka/100-bird-species) dataset available on Kaggle.
-The dataset used to train the model was taken on September 24th, 2023.
+The dataset used to train the model was taken on September 24th, 2023. 
+
+The original model itself was trained on ImageNet-1K, thus it might still have some useful features for identifying creatures like birds.
 
 In theory, the accuracy for a random guess on this dataset is 0.0019047619 (essentially 1/525). 
 The model performed significantly well on all three sets with result being: