File size: 10,576 Bytes
c1c95fc b95a330 c1c95fc 3ca3114 c1c95fc 3ca3114 d2f1c62 3ca3114 2b0232f c1c95fc b95a330 c1c95fc 3ca3114 c1c95fc 3ca3114 d2f1c62 3ca3114 b875465 3ca3114 2b0232f c1c95fc d2f1c62 c1c95fc d2f1c62 c1c95fc ea71b68 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 |
from typing import Tuple
import gradio as gr
import numpy as np
import supervision as sv
from ultralytics import YOLO
import os
MARKDOWN = """
<h1 style='text-align: left'>YOLO-Application Toolkit 🚀</h1>
<p>Welcome to the YOLO-Application Toolkit! This demo highlights the powerful detection capabilities of various YOLO models pre-trained on different datasets. 🎉
Easily detect different objects for various contexts in images on the go. Perfect for quick experimentation and practical use. 🎉🔍</p>
**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-yolo11-object-detection-on-custom-dataset.ipynb?ref=blog.roboflow.com" style="margin-right: 10px;">
<img src="https://colab.research.google.com/assets/colab-badge.svg">
</a>
</div>
Powered by
[Ultralytics](https://github.com/ultralytics/ultralytics).🔥
"""
# Roboflow [Inference](https://github.com/roboflow/inference), [Supervision](https://github.com/roboflow/supervision) and [Ultralytics](https://github.com/ultralytics/ultralytics).🔥
# Load models dynamically
MODELS = {
"YOLO11m (COCO128)": YOLO("https://huggingface.co/mbar0075/YOLO-Application-Toolkit/resolve/main/yolo11m.pt"),
"American Sign Language (ASL) (YOLO11m)": YOLO("https://huggingface.co/mbar0075/YOLO-Application-Toolkit/resolve/main/yolo11m_sign_language.pt"),
# "Microscopic Cell Detection (YOLO11m)": YOLO("https://huggingface.co/mbar0075/YOLO-Application-Toolkit/resolve/main/yolo11m_microscope_cells.pt"),
"Website Screenshots (YOLO11m)": YOLO("https://huggingface.co/mbar0075/YOLO-Application-Toolkit/resolve/main/yolo11m_website_screenshots.pt"),
"Zoo Animals (YOLO11m)": YOLO("https://huggingface.co/mbar0075/YOLO-Application-Toolkit/resolve/main/yolo11m_zoo_animals.pt"),
"Pinned Circuit Boards (YOLO11m)": YOLO("https://huggingface.co/mbar0075/YOLO-Application-Toolkit/resolve/main/yolo11m_circuit_boards.pt"),
"Smoke Detection (YOLO11m)": YOLO("https://huggingface.co/mbar0075/YOLO-Application-Toolkit/resolve/main/yolo11m_smoke_detection.pt"),
"Blood Cell Detection (YOLO11m)": YOLO("https://huggingface.co/mbar0075/YOLO-Application-Toolkit/resolve/main/yolo11m_blood_cells.pt"),
"Coins Detection (YOLO11m)": YOLO("https://huggingface.co/mbar0075/YOLO-Application-Toolkit/resolve/main/yolo11m_coins.pt"),
"Pizza Toppings Detection (YOLOv8s)": YOLO("https://huggingface.co/mbar0075/YOLO-Application-Toolkit/resolve/main/yolov8s_pizza.pt"),
"Aquarium Fish Detection (YOLO11m)": YOLO("https://huggingface.co/mbar0075/YOLO-Application-Toolkit/resolve/main/yolo11m_aquarium_fish.pt"),
# "Pelvis X-ray Detection (YOLO11m)": YOLO("https://huggingface.co/mbar0075/YOLO-Application-Toolkit/resolve/main/yolo11m_pelvis_xray.pt"),
"Road Signs Detection (YOLO11m)": YOLO("https://huggingface.co/mbar0075/YOLO-Application-Toolkit/resolve/main/yolo11m_road_signs.pt"),
# "Pizza Toppings Detection (YOLO11m)": YOLO("https://huggingface.co/mbar0075/YOLO-Application-Toolkit/resolve/main/yolo11s_pizza.pt"),
"Pelvis X-ray Segmentation (YOLO11s)": YOLO("https://huggingface.co/mbar0075/YOLO-Application-Toolkit/resolve/main/yolo11s_seg_pelvis_xray.pt"),
"Teeth X-ray Segmentation (YOLO11s)": YOLO("https://huggingface.co/mbar0075/YOLO-Application-Toolkit/resolve/main/yolo11s_seg_teeth_xray.pt"),
"Football Players Detection (YOLO11s)": YOLO("https://huggingface.co/mbar0075/YOLO-Application-Toolkit/resolve/main/yolo11s_football_players.pt"),
# "Litter Detection (YOLO11s)": YOLO("https://huggingface.co/mbar0075/YOLO-Application-Toolkit/resolve/main/yolo11s_litter_detection.pt"),
"Wheat Detection (YOLO11s)": YOLO("https://huggingface.co/mbar0075/YOLO-Application-Toolkit/resolve/main/yolo11s_wheat_detection.pt"),
"Signatures Detection (YOLO11s)": YOLO("https://huggingface.co/mbar0075/YOLO-Application-Toolkit/resolve/main/yolo11s_signatures_detection.pt"),
"Billiards Detection (YOLO11s)": YOLO("https://huggingface.co/mbar0075/YOLO-Application-Toolkit/resolve/main/yolo11s_billiards_detection.pt"),
"Car Parts Segmentation (YOLO11s)": YOLO("https://huggingface.co/mbar0075/YOLO-Application-Toolkit/resolve/main/yolo11s_seg_car_parts.pt"),
"YOLO11s-Pose (COCO128)": YOLO("https://huggingface.co/mbar0075/YOLO-Application-Toolkit/resolve/main/yolo11s-pose.pt"),
"Hand Keypoints Detection (YOLO11s)": YOLO("https://huggingface.co/mbar0075/YOLO-Application-Toolkit/resolve/main/yolo11s_hand_keypoints.pt"),
"Garbage Detection (YOLO11m)": YOLO("https://huggingface.co/mbar0075/YOLO-Application-Toolkit/resolve/main/yolo11m_garbage_detection.pt"),
}
example_dir = "https://huggingface.co/spaces/mbar0075/YOLO-Application-Toolkit/resolve/main/examples/"
# Your existing example dictionary
EXAMPLE_DICT = {
"YOLO11m (COCO128)": example_dir + "1.jpg",
"American Sign Language (ASL) (YOLO11m)": example_dir + "2.jpg",
# "Microscopic Cell Detection (YOLO11m)": example_dir + "3.jpg",
"Website Screenshots (YOLO11m)": example_dir + "4.jpg",
"Zoo Animals (YOLO11m)": example_dir + "5.jpg",
"Pinned Circuit Boards (YOLO11m)": example_dir + "6.jpg",
"Smoke Detection (YOLO11m)": example_dir + "7.jpg",
"Blood Cell Detection (YOLO11m)": example_dir + "8.jpg",
"Coins Detection (YOLO11m)": example_dir + "9.jpg",
"Pizza Toppings Detection (YOLOv8s)": example_dir + "10.jpg",
"Aquarium Fish Detection (YOLO11m)": example_dir + "11.jpg",
# "Pelvis X-ray Detection (YOLO11m)": example_dir + "12.jpg",
"Road Signs Detection (YOLO11m)": example_dir + "13.jpg",
# "Pizza Toppings Detection (YOLO11m)": example_dir + "10.jpg",
"Pelvis X-ray Segmentation (YOLO11s)": example_dir + "12.jpg",
"Teeth X-ray Segmentation (YOLO11s)": example_dir + "14.jpg",
"Football Players Detection (YOLO11s)": example_dir + "15.jpg",
# "Litter Detection (YOLO11s)": example_dir + "16.jpg",
"Wheat Detection (YOLO11s)": example_dir + "17.png",
"Signatures Detection (YOLO11s)": example_dir + "18.jpg",
"Billiards Detection (YOLO11s)": example_dir + "19.jpg",
"Car Parts Segmentation (YOLO11s)": example_dir + "20.jpg",
"YOLO11s-Pose (COCO128)": example_dir + "21.jpg",
"Hand Keypoints Detection (YOLO11s)": example_dir + "22.jpg",
"Garbage Detection (YOLO11m)": example_dir + "23.jpg",
}
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]
# Extracting Annotated Image
return result.plot()
# For supervision annotations:
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,
yolov11_confidence_threshold: float,
iou_threshold: float,
model_name: str
) -> np.ndarray:
# Load the selected model from the preloaded models
model = MODELS[model_name]
# Process the image
return detect_and_annotate(model, np.array(input_image), yolov11_confidence_threshold, iou_threshold)
# Gradio UI components
yolo_11s_confidence_threshold_component = gr.Slider(
minimum=0,
maximum=1.0,
value=0.3,
step=0.01,
label="YOLO 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."
)
)
model_dropdown = gr.Dropdown(
choices=list(MODELS.keys()),
label="Select Model",
value="YOLO11m (COCO128)",
info=(
"Choose the YOLO model you want to use for object detection. Each model is "
"trained on a specific dataset, making them suitable for various detection tasks."
)
)
def update_example(model_name):
return EXAMPLE_DICT[model_name]
with gr.Blocks() as demo:
gr.Markdown(MARKDOWN)
with gr.Accordion("Configuration", open=False):
yolo_11s_confidence_threshold_component.render()
iou_threshold_component.render()
with gr.Row():
model_dropdown.render()
with gr.Row():
image_input_component = gr.Image(type='pil', label='Input Image')
yolo_11s_output_component = gr.Image(type='pil', label='YOLO Output')
submit_button = gr.Button(value='Submit', scale=1, variant='primary')
gr.Examples(
fn=process_image,
examples=[[EXAMPLE_DICT[i], 0.3, 0.5, i] for i in EXAMPLE_DICT.keys()],
inputs=[image_input_component, yolo_11s_confidence_threshold_component, iou_threshold_component, model_dropdown],
outputs=[yolo_11s_output_component]
)
model_dropdown.change(fn=update_example, inputs=model_dropdown, outputs=image_input_component)
submit_button.click(
fn=process_image,
inputs=[image_input_component, yolo_11s_confidence_threshold_component, iou_threshold_component, model_dropdown],
outputs=[yolo_11s_output_component]
)
demo.launch(debug=False, show_error=True, max_threads=1) |