Update README.md

README.md

@@ -1,6 +1,6 @@
 ---
-title: ObjectDetectionWithYOLOv3
-emoji: 😻
+title: Object Detection - YOLOV3
+emoji: 🚀
 colorFrom: green
 colorTo: purple
 sdk: gradio
@@ -40,15 +40,6 @@ The model supports following classes:
    * train 🚊
    * tvmonitor 📺
 
-### How to Use:
-* You can upload an image and click submit to generate the detections, the corresponding bounding boxes, and the saliency maps.
-* The saliency map can be configured to be applied only inside the bounding box using the "Renormalize activations to bounding boxes" checkbox.
-* The "Activation overlay Opacity" adjusts the relative transparency between the image, and the saliency map.
-* You can control the detection threshold and the IOU threshold to filter the predictions 
-* The "show sample images" check button toggles whether to show a gallery of examples from the test dataset.
-* **Note**: Since the model runs on CPU, the processing time can sometimes be long! please be patient! Optionally, you can check out some precomputed examples at the bottom of the page too!
-
-### Code Links
-* The entire source code for YOLO model can be found [here](https://github.com/jyanivaddi/dl_hub/tree/main/YOLO_V3). This is provided as part of the class notes in session 13 of the ERA V1 course (Thanks Rohan! :smile: )
-* The EigenCAM explainability maps were generated using the [pytorch-gradcam](https://github.com/jacobgil/pytorch-grad-cam) library.  
-* The PASCAL VOC dataset used to train the model is from [Kaggle](https://www.kaggle.com/datasets/aladdinpersson/pascal-voc-dataset-used-in-yolov3-video?resource=download).
+### Steps to Use:
+* Upload an image and click submit to generate the detections, the corresponding bounding boxes, and the saliency maps.
+* Control the degree of detection threshold and the IOU threshold to filter the predictions