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 = "

SAHI is a lightweight vision library for performing large scale object detection/ instance segmentation.. SAHI Github | SAHI Blog | YOLOv5 Github

" 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)