Update README.md

README.md

@@ -1,32 +1,8 @@
-title: Advanced Instance Segmentation emoji: 🖼️✨ colorFrom: blue colorTo: green sdk: gradio sdk_version: 4.28.3 app_file: app.py pinned: false
-Advanced Instance Segmentation with Mask2Former
-This Hugging Face Space provides an interactive demo for Instance Segmentation, a computer vision task that locates and delineates each distinct object of interest in an image.
-
-This application uses the powerful Mask2Former model (facebook/mask2former-swin-large-coco-instance), a state-of-the-art architecture for panoptic, instance, and semantic segmentation.
-
-How to Use
-Upload an image using the panel on the left. You can also drag and drop a file.
-
-If you don't have an image, simply click one of the example images provided below the upload box.
-
-The model will process the image and display the output on the right. Each detected object will have:
-
-A colored mask overlay.
-
-A bounding box.
-
-A label with its confidence score.
-
-Target Classes
-The model is configured to specifically detect the following classes:
-
-Vehicles: car, truck, bus
-
-People: person
-
-Animals: cat, dog
-
-Limitations
-Building Detection: The COCO dataset, on which this model was trained, does not have a generic "building" class. Therefore, buildings will not be segmented. To detect buildings, the model would need to be fine-tuned on a dataset that includes them (e.g., ADE20K).
-
-Performance: This is a large model. Processing on free CPU hardware can take 20-40 seconds. For real-time performance, upgrading the Space to GPU hardware is recommended.
+title: Advanced Instance Segmentation
+emoji: 🖼️✨
+colorFrom: blue
+colorTo: green
+sdk: gradio
+sdk_version: 4.28.3
+app_file: app.py
+pinned: falseAdvanced Instance Segmentation with Mask2FormerThis Hugging Face Space provides an interactive demo for Instance Segmentation, a computer vision task that locates and delineates each distinct object of interest in an image.This application uses the powerful Mask2Former model (facebook/mask2former-swin-large-coco-instance), a state-of-the-art architecture for panoptic, instance, and semantic segmentation.How to UseUpload an image using the panel on the left. You can also drag and drop a file.If you don't have an image, simply click one of the example images provided below the upload box.The model will process the image and display the output on the right. Each detected object will have:A colored mask overlay.A bounding box.A label with its confidence score.Target ClassesThe model is configured to specifically detect the following classes:Vehicles: car, truck, busPeople: personAnimals: cat, dogLimitationsBuilding Detection: The COCO dataset, on which this model was trained, does not have a generic "building" class. Therefore, buildings will not be segmented. To detect buildings, the model would need to be fine-tuned on a dataset that includes them (e.g., ADE20K).Performance: This is a large model. Processing on free CPU hardware can take 20-40 seconds. For real-time performance, upgrading the Space to GPU hardware is recommended.