Create README.md

README.md

@@ -1,12 +1,35 @@
----
-license: apache-2.0
-language:
-- en
-metrics:
-- accuracy
-base_model:
-- microsoft/resnet-50
-pipeline_tag: image-segmentation
-datasets:
-- bnsapa/road-detection
----
+# Waynet - A Road Segmentation project
+
+## Author
+ - **Vishal Adithya.A**
+
+## Overview
+
+This model demonstrates a road segmentation implemented using deep learning techniques which predics the road regions in the input image and returns it in a grayscale image.
+
+## Features
+
+1. ### Architecture
+    - Basic Resnet50 model with few upsampling and batch normalisation layers.
+    - Contains over _____ Trainable paramameters.
+    - Training Duration: 1 hour.
+2. ### Training Data
+    - Source: ([]())
+    - Format: The dataset includes RGB images of roads around the globe and thrie corresponding segment and lane.
+    - Preprocessing: With the help of torch and torchvission api basic preprocessing like resizing and convertion to tensor were implemented.
+3. ### CostFunctions Score
+    - BCE:
+    - MSE:
+
+## Requirements
+ - 'PIL'
+ - 'timm'
+ - 'numpy'
+ - 'torch'
+ - 'opencv2'
+ - 'datasets'
+ - 'matplotlib'
+ - 'torchvission'
+
+## License
+This project is licensed under the Apache License 2.0.