Update README.md

README.md

@@ -87,42 +87,41 @@ Users should be informed about the model's limitations and potential biases. Fur
 To get started with the YOLOv8s object Detection and Classification model, follow these steps:
 
 ```bash
-pip install ultralyticsplus==0.0.28 ultralytics==8.0.43
+pip install transformers
 ```
 
 - Load model and perform prediction:
 
 ```python
-from ultralyticsplus import YOLO, render_result
 
-# load model
-model = YOLO('foduucom/thermal-image-object-detection')
+from transformers import YolosImageProcessor, YolosForObjectDetection
+from PIL import Image
+import torch
+import requests
 
-# set model parameters
-model.overrides['conf'] = 0.25  # NMS confidence threshold
-model.overrides['iou'] = 0.45  # NMS IoU threshold
-model.overrides['agnostic_nms'] = False  # NMS class-agnostic
-model.overrides['max_det'] = 1000  # maximum number of detections per image
+url = "http://images.cocodataset.org/val2017/000000039769.jpg"
+image = Image.open(requests.get(url, stream=True).raw)
 
-# set image
-image = '/path/to/your/document/images'
+model = YolosForObjectDetection.from_pretrained('foduucom/thermal-image-object-detection')
+image_processor = YolosImageProcessor.from_pretrained("foduucom/thermal-image-object-detection")
 
-# perform inference
-results = model.predict(image)
+inputs = image_processor(images=image, return_tensors="pt")
+outputs = model(**inputs)
 
-# observe results
-print(results[0].boxes)
-render = render_result(model=model, image=image, result=results[0])
-render.show()
-```
-
-
-- Finetune the model on your custom dataset:
+# model predicts bounding boxes and corresponding COCO classes
+logits = outputs.logits
+bboxes = outputs.pred_boxes
 
-```bash
-yolov8 train --data dataset.yaml --img 640 --batch -1 --weights foduucom/object_detection--epochs 10
-```
 
+# print results
+target_sizes = torch.tensor([image.size[::-1]])
+results = image_processor.post_process_object_detection(outputs, threshold=0.9, target_sizes=target_sizes)[0]
+for score, label, box in zip(results["scores"], results["labels"], results["boxes"]):
+    box = [round(i, 2) for i in box.tolist()]
+    print(
+        f"Detected {model.config.id2label[label.item()]} with confidence "
+        f"{round(score.item(), 3)} at location {box}"
+    )
 
 
 ### Compute Infrastructure