app.py

import gradio as gr
import yolov5
import sahi.utils
import sahi.model
import sahi.predict
from PIL import Image
import numpy

# Images
sahi.utils.file.download_from_url(
    "https://user-images.githubusercontent.com/34196005/142730935-2ace3999-a47b-49bb-83e0-2bdd509f1c90.jpg",
    "apple_tree.jpg",
)
sahi.utils.file.download_from_url(
    "https://user-images.githubusercontent.com/34196005/142730936-1b397756-52e5-43be-a949-42ec0134d5d8.jpg",
    "highway.jpg",
)

sahi.utils.file.download_from_url(
    "https://user-images.githubusercontent.com/34196005/142742871-bf485f84-0355-43a3-be86-96b44e63c3a2.jpg",
    "highway2.jpg",
)

sahi.utils.file.download_from_url(
    "https://user-images.githubusercontent.com/34196005/142742872-1fefcc4d-d7e6-4c43-bbb7-6b5982f7e4ba.jpg",
    "highway3.jpg",
)


# Model
model = sahi.model.Yolov5DetectionModel(
    model_path="yolov5s6.pt", device="cpu", confidence_threshold=0.5
)


def sahi_yolo_inference(
    image,
    slice_height=512,
    slice_width=512,
    overlap_height_ratio=0.2,
    overlap_width_ratio=0.2,
    image_size=640,
    postprocess_type="UNIONMERGE",
    postprocess_match_metric="IOS",
    postprocess_match_threshold=0.5,
    postprocess_class_agnostic=False,
):

    # standard inference
    prediction_result_1 = sahi.predict.get_prediction(
        image=image, detection_model=model, image_size=image_size
    )
    print(image)
    visual_result_1 = sahi.utils.cv.visualize_object_predictions(
        image=numpy.array(image),
        object_prediction_list=prediction_result_1.object_prediction_list,
    )
    output_1 = Image.fromarray(visual_result_1["image"])

    # sliced inference
    prediction_result_2 = sahi.predict.get_sliced_prediction(
        image=image,
        detection_model=model,
        image_size=image_size,
        slice_height=slice_height,
        slice_width=slice_width,
        overlap_height_ratio=overlap_height_ratio,
        overlap_width_ratio=overlap_width_ratio,
        postprocess_type=postprocess_type,
        postprocess_match_metric=postprocess_match_metric,
        postprocess_match_threshold=postprocess_match_threshold,
        postprocess_class_agnostic=postprocess_class_agnostic,
    )
    visual_result_2 = sahi.utils.cv.visualize_object_predictions(
        image=numpy.array(image),
        object_prediction_list=prediction_result_2.object_prediction_list,
    )

    output_2 = Image.fromarray(visual_result_2["image"])

    return output_1, output_2


inputs = [
    gr.inputs.Image(type="pil", label="Original Image"),
    gr.inputs.Number(default=512, label="slice_height"),
    gr.inputs.Number(default=512, label="slice_width"),
    gr.inputs.Number(default=0.2, label="overlap_height_ratio"),
    gr.inputs.Number(default=0.2, label="overlap_width_ratio"),
    gr.inputs.Number(default=640, label="image_size"),
    gr.inputs.Dropdown(
        ["NMS", "UNIONMERGE"],
        type="value",
        default="UNIONMERGE",
        label="postprocess_type",
    ),
    gr.inputs.Dropdown(
        ["IOU", "IOS"], type="value", default="IOS", label="postprocess_type"
    ),
    gr.inputs.Number(default=0.5, label="postprocess_match_threshold"),
    gr.inputs.Checkbox(default=True, label="postprocess_class_agnostic"),
]

outputs = [
    gr.outputs.Image(type="pil", label="Standard YOLOv5s Inference"),
    gr.outputs.Image(type="pil", label="Sliced YOLOv5s Inference"),
]

title = "SAHI + YOLOv5"
description = "SAHI + YOLOv5 Gradio demo for object detection. Upload an image or click an example image to use."
article = "<p style='text-align: center'>SAHI is a lightweight vision library for performing large scale object detection/ instance segmentation.. <a href='https://github.com/obss/sahi'>SAHI Github</a> | <a href='https://medium.com/codable/sahi-a-vision-library-for-performing-sliced-inference-on-large-images-small-objects-c8b086af3b80'>SAHI Blog</a> | <a href='https://github.com/fcakyon/yolov5-pip'>YOLOv5 Github</a> </p>"
examples = [
    ["apple_tree.jpg", 256, 256, 0.2, 0.2, 640, "UNIONMERGE", "IOS", 0.5, True],
    ["highway.jpg", 256, 256, 0.2, 0.2, 640, "UNIONMERGE", "IOS", 0.5, True],
    ["highway2.jpg", 512, 512, 0.2, 0.2, 640, "UNIONMERGE", "IOS", 0.5, True],
    ["highway3.jpg", 1024, 1024, 0.2, 0.2, 640, "UNIONMERGE", "IOS", 0.5, True],
]

gr.Interface(
    sahi_yolo_inference,
    inputs,
    outputs,
    title=title,
    description=description,
    article=article,
    examples=examples,
    theme="default",
).launch(debug=True)