added model card info

README.md

@@ -1,3 +1,68 @@
 ---
 license: mit
 ---
+
+## Model Card for butterfly_segmentation_yolo_v8
+
+This model takes in an image of a butterfly (with or without body attached to wings) and segments out any existing hindwings and forewings, in addition to pictured equipment described below. 
+
+## Model Details
+
+yolov8m_shear_10.0_scale_0.5_translate_0.1_fliplr_0.0_best.pt is the butterfly segmentation model. 
+
+The butterfly segmentation model was trained on a dataset of 800 total images from the Jiggins, OM_STRI, and Monteiro datasets. The model architecture is based on YOLO v8 (yolov8m-seg.pt), which we fine-tune further on our dataset of 800 images. 
+
+## Model Description
+
+The model is responsible for taking an input image (RGB) and generating segmentation masks for all classes below that are found in the image. Data augmentations applied during training include shear (10.0), scale (0.5), and translate (0.1). The model was trained for 50 epochs with an image size of 256. Note that despite defining an image size of 256, the normalized masks predicted by yolo can be rescaled to the original image size. 
+
+### Segmentation Classes
+[`pixel class`] corresponding category
+
+- [0] background
+- [1] right_forewing
+- [2] left_forewing
+- [3] right_hindwing
+- [4] left_hindwing
+- [5] ruler
+- [6] white_balance
+- [7] label
+- [8] color_card
+- [9] body
+
+### Details
+
+model.train(data=YAML, 
+            imgsz=256,
+            epochs=50, 
+            batch=16,
+            device=DEVICE,
+            optimizer='auto',
+            verbose=True,
+            val=True,
+            shear=10.0,
+            scale=0.5, 
+            translate=0.1,
+            fliplr = 0.0 
+            )
+
+## Metrics
+
+                Class     Images  Instances      mAP50-95
+                   all         64        358      
+            background         64          3      0.20946
+        right_forewing         64         58      0.9845
+         left_forewing         64         51      0.9682 
+        right_hindwing         64         59      0.95296
+         left_hindwing         64         50      0.93961 
+                 ruler         64         31      0.73608
+         white_balance         64         18      0.90686
+                 label         64         50      0.80865
+            color_card         64         24      0.92653
+                  body         64         14      0.78283
+                  
+**Developed by:** Michelle Ramirez
+
+## How to Get Started with the Model
+
+To view applications of how to load in the model file and predict masks on images, please refer to [this github repository](https://github.com/Imageomics/wing-segmentation)