Initial Commit

README.md

@@ -1,8 +1,8 @@
 ---
 title: YOLO Application Toolkit
 emoji: 🌍
-colorFrom: pink
-colorTo: yellow
+colorFrom: yellow
+colorTo: purple
 sdk: gradio
 sdk_version: 4.44.1
 app_file: app.py

app.py

@@ -0,0 +1,161 @@
+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 objects in images and videos 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 Roboflow [Inference](https://github.com/roboflow/inference), 
+[Supervision](https://github.com/roboflow/supervision) and [Ultralytics](https://github.com/ultralytics/ultralytics).🔥
+"""
+
+MODEL_DIR = os.path.join(os.path.dirname(__file__), "models")
+
+# Load models dynamically
+MODELS = {
+    "YOLO11m (COCO128)": YOLO(os.path.join(MODEL_DIR, "yolo11m.pt")),
+    "American Sign Language (ASL) YOLO11m": YOLO(os.path.join(MODEL_DIR, "yolo11m_sign_language.pt")),
+    # "Microscopic Cell Detection YOLO11m": YOLO(os.path.join(MODEL_DIR, "yolo11m_microscope_cells.pt")),
+    "Website Screenshots YOLO11m": YOLO(os.path.join(MODEL_DIR, "yolo11m_website_screenshots.pt")),
+    "Zoo Animals YOLO11m": YOLO(os.path.join(MODEL_DIR, "yolo11m_zoo_animals.pt")),
+    "Pinned Circuit Boards YOLO11m": YOLO(os.path.join(MODEL_DIR, "yolo11m_circuit_boards.pt")),
+}
+
+example_dir = "https://huggingface.co/spaces/mbar0075/YOLO-Application-Toolkit/blob/main/"
+# Your existing example dictionary
+EXAMPLE_DICT = {
+    "YOLO11m (COCO128)": example_dir + "examples/1.jpg",
+    "American Sign Language (ASL) YOLO11m": example_dir + "examples/2.jpg",
+    # "Microscopic Cell Detection YOLO11m": example_dir + "examples/3.jpg",
+    "Website Screenshots YOLO11m": example_dir + "examples/4.jpg",
+    "Zoo Animals YOLO11m": example_dir + "examples/5.jpg",
+    "Pinned Circuit Boards YOLO11m": example_dir + "examples/6.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]
+    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="YOLO11m 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='YOLO11s 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)

models/yolo11m.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5ffc1a674953a08e11a8d21e022781b1b23a19b730afc309290bd9fb5305b95
+size 40684120

models/yolo11m_circuit_boards.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c417e1241d3f0fdcee4ed5fbc9432c489899f94cfd40e99e9f921e310e8a8f0c
+size 40551845

models/yolo11m_microscope_cells.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91180e565da11b9b152aa8dd459c6e003b6d67d9a23866be41d7c8c39c9aa2df
+size 40514469

models/yolo11m_sign_language.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:016cdb005dee92fa77b5c6719800a94cecadeb14c87fcec8047c9848f99e4425
+size 40569189

models/yolo11m_website_screenshots.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d1529998c0bc22bde5dd30ff87370aac6d389f636fa0d97ee18514ec38f82dc
+size 40516261

models/yolo11m_zoo_animals.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54d77afc923f0e3a5c0d5170105d0c453e06aa4ba8367171ed7e84a6b37b0422
+size 40534629

requirements.txt

@@ -0,0 +1,8 @@
+setuptools<70.0.0
+awscli==1.29.54
+gradio
+inference
+supervision
+ultralytics
+dill
+timm