Initial Commit

README.md

@@ -1,13 +1,14 @@
 ---
-title: YOLO Playground
-emoji: 🐨
-colorFrom: green
-colorTo: yellow
+title: YOLO-Playground
+emoji: 📈
+colorFrom: blue
+colorTo: green
 sdk: gradio
-sdk_version: 5.25.2
+sdk_version: 4.39.0
 app_file: app.py
 pinned: false
 license: mit
+short_description: Identify objects in images using multiple YOLO models
 ---
 
 Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,283 @@
+from typing import Tuple
+
+import gradio as gr
+import numpy as np
+import supervision as sv
+from ultralytics import YOLO
+
+MARKDOWN = """
+<h1 style='text-align: left'>YOLO-Playground 📈</h1>
+Welcome to YOLO-Playground! This demo showcases the detection capabilities of various YOLO models pre-trained on the COCO Dataset. 🚀🔍👀
+
+A simple project just for fun for on the go object detection. 🎉
+
+Inspired from YOLO-ARENA by SkalskiP. 🙏
+
+- **YOLOv8**
+  <div style="display: flex; align-items: center;">
+    <a href="https://docs.ultralytics.com/models/yolov8/" style="margin-right: 10px;">
+      <img src="https://badges.aleen42.com/src/github.svg">
+    </a>
+    <a href="https://colab.research.google.com/github/roboflow-ai/notebooks/blob/main/notebooks/train-yolov8-object-detection-on-custom-dataset.ipynb" style="margin-right: 10px;">
+      <img src="https://colab.research.google.com/assets/colab-badge.svg">
+    </a>
+  </div>
+- **YOLOv9**
+  <div style="display: flex; align-items: center;">
+    <a href="https://github.com/WongKinYiu/yolov9" style="margin-right: 10px;">
+      <img src="https://badges.aleen42.com/src/github.svg">
+    </a>
+    <a href="https://arxiv.org/abs/2402.13616" style="margin-right: 10px;">
+      <img src="https://img.shields.io/badge/arXiv-2402.13616-b31b1b.svg">
+    </a>
+    <a href="https://colab.research.google.com/github/roboflow-ai/notebooks/blob/main/notebooks/train-yolov9-object-detection-on-custom-dataset.ipynb" style="margin-right: 10px;">
+      <img src="https://colab.research.google.com/assets/colab-badge.svg">
+    </a>
+  </div>
+- **YOLOv10**
+  <div style="display: flex; align-items: center;">
+    <a href="https://github.com/THU-MIG/yolov10" style="margin-right: 10px;">
+      <img src="https://badges.aleen42.com/src/github.svg">
+    </a>
+    <a href="https://arxiv.org/abs/2405.14458" style="margin-right: 10px;">
+      <img src="https://img.shields.io/badge/arXiv-2405.14458-b31b1b.svg">
+    </a>
+    <a href="https://colab.research.google.com/github/roboflow-ai/notebooks/blob/main/notebooks/train-yolov10-object-detection-on-custom-dataset.ipynb" style="margin-right: 10px;">
+      <img src="https://colab.research.google.com/assets/colab-badge.svg">
+    </a>
+  </div>
+- **YOLO11**
+<div style="display: flex; align-items: center;">
+    <a href="https://docs.ultralytics.com/models/yolo11/" style="margin-right: 10px;">
+      <img src="https://badges.aleen42.com/src/github.svg">
+    </a>
+    <a href="https://colab.research.google.com/github/roboflow-ai/notebooks/blob/main/notebooks/train-yolov8-object-detection-on-custom-dataset.ipynb" style="margin-right: 10px;">
+      <img src="https://colab.research.google.com/assets/colab-badge.svg">
+    </a>
+  </div>
+
+Powered by Roboflow [Inference](https://github.com/roboflow/inference), 
+[Supervision](https://github.com/roboflow/supervision) and [Ultralytics](https://github.com/ultralytics/ultralytics).🔥
+"""
+
+IMAGE_EXAMPLES = [
+    ['https://media.roboflow.com/supervision/image-examples/people-walking.png', 0.3, 0.3, 0.3, 0.3, 0.5],
+    ['https://media.roboflow.com/supervision/image-examples/vehicles.png', 0.3, 0.3, 0.3, 0.3, 0.5],
+    ['https://media.roboflow.com/supervision/image-examples/basketball-1.png', 0.3, 0.3, 0.3, 0.3, 0.5],
+]
+
+YOLO_V8S_MODEL = YOLO("yolov8s.pt")
+YOLO_V9S_MODEL = YOLO("yolov9s.pt")
+YOLO_V10S_MODEL = YOLO("yolov10s.pt")
+YOLO_11S_MODEL = YOLO("yolo11s.pt")
+
+LABEL_ANNOTATORS = sv.LabelAnnotator()
+BOUNDING_BOX_ANNOTATORS = sv.BoxAnnotator()
+
+
+def detect_and_annotate(
+    model,
+    input_image: np.ndarray,
+    confidence_threshold: float,
+    iou_threshold: float,
+    class_id_mapping: dict = None
+) -> np.ndarray:
+    result = model(
+        input_image,
+        conf=confidence_threshold,
+        iou=iou_threshold
+    )[0]
+    detections = sv.Detections.from_ultralytics(result)
+
+    if class_id_mapping:
+        detections.class_id = np.array([
+            class_id_mapping[class_id]
+            for class_id
+            in detections.class_id
+        ])
+
+    labels = [
+        f"{class_name} ({confidence:.2f})"
+        for class_name, confidence
+        in zip(detections['class_name'], detections.confidence)
+    ]
+
+    annotated_image = input_image.copy()
+    annotated_image = BOUNDING_BOX_ANNOTATORS.annotate(
+        scene=annotated_image, detections=detections)
+    annotated_image = LABEL_ANNOTATORS.annotate(
+        scene=annotated_image, detections=detections, labels=labels)
+    return annotated_image
+
+
+def process_image(
+    input_image: np.ndarray,
+    yolo_v8_confidence_threshold: float,
+    yolo_v9_confidence_threshold: float,
+    yolo_v10_confidence_threshold: float,
+    yolov11_confidence_threshold: float,
+    iou_threshold: float
+) -> Tuple[np.ndarray, np.ndarray, np.ndarray]:
+    # Validate iou_threshold before using it
+    if iou_threshold is None or not isinstance(iou_threshold, float):
+        iou_threshold = 0.3  # Default value, adjust as necessary
+
+    yolo_v8s_annotated_image = detect_and_annotate(
+        YOLO_V8S_MODEL, input_image, yolo_v8_confidence_threshold, iou_threshold)
+    yolo_v9s_annotated_image = detect_and_annotate(
+        YOLO_V9S_MODEL, input_image, yolo_v9_confidence_threshold, iou_threshold)
+    yolo_v10s_annotated_image = detect_and_annotate(
+        YOLO_V10S_MODEL, input_image, yolo_v10_confidence_threshold, iou_threshold)
+    yolo_11s_annnotated_image = detect_and_annotate(
+        YOLO_11S_MODEL, input_image, yolov11_confidence_threshold, iou_threshold)
+
+    return (
+        yolo_v8s_annotated_image,
+        yolo_v9s_annotated_image,
+        yolo_v10s_annotated_image,
+        yolo_11s_annnotated_image
+    )
+
+yolo_v8s_confidence_threshold_component = gr.Slider(
+    minimum=0,
+    maximum=1.0,
+    value=0.3,
+    step=0.01,
+    label="YOLOv8s Confidence Threshold",
+    info=(
+        "The confidence threshold for the YOLO model. Lower the threshold to "
+        "reduce false negatives, enhancing the model's sensitivity to detect "
+        "sought-after objects. Conversely, increase the threshold to minimize false "
+        "positives, preventing the model from identifying objects it shouldn't."
+    ))
+
+
+yolo_v9s_confidence_threshold_component = gr.Slider(
+    minimum=0,
+    maximum=1.0,
+    value=0.3,
+    step=0.01,
+    label="YOLOv9s Confidence Threshold",
+    info=(
+        "The confidence threshold for the YOLO model. Lower the threshold to "
+        "reduce false negatives, enhancing the model's sensitivity to detect "
+        "sought-after objects. Conversely, increase the threshold to minimize false "
+        "positives, preventing the model from identifying objects it shouldn't."
+    ))
+
+yolo_v10s_confidence_threshold_component = gr.Slider(
+    minimum=0,
+    maximum=1.0,
+    value=0.3,
+    step=0.01,
+    label="YOLOv10s Confidence Threshold",
+    info=(
+        "The confidence threshold for the YOLO model. Lower the threshold to "
+        "reduce false negatives, enhancing the model's sensitivity to detect "
+        "sought-after objects. Conversely, increase the threshold to minimize false "
+        "positives, preventing the model from identifying objects it shouldn't."
+    ))
+
+yolo_11s_confidence_threshold_component = gr.Slider(
+    minimum=0,
+    maximum=1.0,
+    value=0.3,
+    step=0.01,
+    label="YOLO11s Confidence Threshold",
+    info=(
+        "The confidence threshold for the YOLO model. Lower the threshold to "
+        "reduce false negatives, enhancing the model's sensitivity to detect "
+        "sought-after objects. Conversely, increase the threshold to minimize false "
+        "positives, preventing the model from identifying objects it shouldn't."
+    ))
+
+iou_threshold_component = gr.Slider(
+    minimum=0,
+    maximum=1.0,
+    value=0.5,
+    step=0.01,
+    label="IoU Threshold",
+    info=(
+        "The Intersection over Union (IoU) threshold for non-maximum suppression. "
+        "Decrease the value to lessen the occurrence of overlapping bounding boxes, "
+        "making the detection process stricter. On the other hand, increase the value "
+        "to allow more overlapping bounding boxes, accommodating a broader range of "
+        "detections."
+    ))
+
+
+with gr.Blocks() as demo:
+    gr.Markdown(MARKDOWN)
+    with gr.Accordion("Configuration", open=False):
+        with gr.Row():
+            yolo_v8s_confidence_threshold_component.render()
+            yolo_v9s_confidence_threshold_component.render()
+            yolo_v10s_confidence_threshold_component.render()
+            yolo_11s_confidence_threshold_component.render()
+        iou_threshold_component.render()
+    with gr.Row():
+        input_image_component = gr.Image(
+            type='pil',
+            label='Input'
+        )
+    with gr.Row():
+        yolo_v8s_output_image_component = gr.Image(
+            type='pil',
+            label='YOLOv8s'
+        )
+        yolo_v9s_output_image_component = gr.Image(
+            type='pil',
+            label='YOLOv9s'
+        )
+    with gr.Row():
+        yolo_v10s_output_image_component = gr.Image(
+            type='pil',
+            label='YOLOv10s'
+        )
+        yolo_11s_output_image_component = gr.Image(
+            type='pil',
+            label='YOLO11s'
+            )
+    submit_button_component = gr.Button(
+        value='Submit',
+        scale=1,
+        variant='primary'
+    )
+    gr.Examples(
+        fn=process_image,
+        examples=IMAGE_EXAMPLES,
+        inputs=[
+            input_image_component,
+            yolo_v8s_confidence_threshold_component,
+            yolo_v9s_confidence_threshold_component,
+            yolo_v10s_confidence_threshold_component,
+            yolo_11s_confidence_threshold_component,
+            iou_threshold_component
+        ],
+        outputs=[
+            yolo_v8s_output_image_component,
+            yolo_v9s_output_image_component,
+            yolo_v10s_output_image_component,
+            yolo_11s_output_image_component
+        ]
+    )
+
+    submit_button_component.click(
+        fn=process_image,
+        inputs=[
+            input_image_component,
+            yolo_v8s_confidence_threshold_component,
+            yolo_v9s_confidence_threshold_component,
+            yolo_v10s_confidence_threshold_component,
+            yolo_11s_confidence_threshold_component,
+            iou_threshold_component
+        ],
+        outputs=[
+            yolo_v8s_output_image_component,
+            yolo_v9s_output_image_component,
+            yolo_v10s_output_image_component,
+            yolo_11s_output_image_component
+        ]
+    )
+
+demo.launch(debug=False, show_error=True, max_threads=1)

requirements.txt

@@ -0,0 +1,9 @@
+setuptools<70.0.0
+awscli==1.29.54
+gradio
+pydantic==2.10.6
+inference
+supervision
+ultralytics
+dill
+timm