import gradio as gr import torch # from sahi.prediction import ObjectPrediction # from sahi.utils.cv import visualize_object_predictions, read_image import os import requests import json from PIL import Image from huggingface_hub import hf_hub_download from ultralyticsplus import YOLO, render_result # from ultralyticsplus import render_result # import requests # import cv2 image_path = [['test_images/2a998cfb0901db5f8210.jpg','linhcuem/cham_diem_yolov8', 640, 0.25, 0.45],['test_images/2ce19ce0191acb44920b.jpg','linhcuem/cham_diem_yolov8', 640, 0.25, 0.45], ['test_images/2daab6ea3310e14eb801.jpg','linhcuem/cham_diem_yolov8', 640, 0.25, 0.45], ['test_images/4a137deefb14294a7005 (1).jpg','linhcuem/cham_diem_yolov8', 640, 0.25, 0.45], ['test_images/7e77c596436c9132c87d.jpg','linhcuem/cham_diem_yolov8', 640, 0.25, 0.45], ['test_images/170f914014bac6e49fab.jpg','linhcuem/cham_diem_yolov8', 640, 0.25, 0.45], ['test_images/3355ec3269c8bb96e2d9.jpg','linhcuem/cham_diem_yolov8', 640, 0.25, 0.45], ['test_images/546306a88052520c0b43.jpg','linhcuem/cham_diem_yolov8', 640, 0.25, 0.45], ['test_images/33148464019ed3c08a8f.jpg','linhcuem/cham_diem_yolov8', 640, 0.25, 0.45], ['test_images/a17a992a1cd0ce8e97c1.jpg','linhcuem/cham_diem_yolov8', 640, 0.25, 0.45], ['test_images/b5db5e42d8b80ae653a9 (1).jpg','linhcuem/cham_diem_yolov8', 640, 0.25, 0.45],['test_images/b8ee1f5299a84bf612b9.jpg','linhcuem/cham_diem_yolov8', 640, 0.25, 0.45], ['test_images/b272fec7783daa63f32c.jpg','linhcuem/cham_diem_yolov8', 640, 0.25, 0.45],['test_images/bb202b3eaec47c9a25d5.jpg','linhcuem/cham_diem_yolov8', 640, 0.25, 0.45], ['test_images/bf1e22b0a44a76142f5b.jpg','linhcuem/cham_diem_yolov8', 640, 0.25, 0.45], ['test_images/ea5473c5f53f27617e2e.jpg','linhcuem/cham_diem_yolov8', 640, 0.25, 0.45], ['test_images/ee106392e56837366e79.jpg','linhcuem/cham_diem_yolov8', 640, 0.25, 0.45], ['test_images/f88d2214a4ee76b02fff.jpg','linhcuem/cham_diem_yolov8', 640, 0.25, 0.45]] # Load YOLO model model = YOLO('linhcuem/cham_diem_yolov8') # model = YOLO('linhcuem/cham_diem_yolov8_ver20') ################################################### def yolov8_img_inference( image: gr.inputs.Image = None, model_path: gr.inputs.Dropdown = None, image_size: gr.inputs.Slider = 640, conf_threshold: gr.inputs.Slider = 0.25, iou_threshold: gr.inputs.Slider = 0.45, ): model = YOLO(model_path) # model.conf = conf_threshold # model.iou = iou_threshold model.overrides['conf'] = conf_threshold model.overrides['iou'] = iou_threshold model.overrides['agnostic_nms'] = False model.overrides['max_det'] = 1000 # image = read_image results = model.predict(image) render = render_result(model=model, image=image, result=results[0]) # get the model names list names = model.names # get the 'obj' class id # obj_id = list(names)[list(names.values()).index('lo_ytv')] # ('hop_dln','hop_jn','hop_vtg','hop_ytv','lo_kids', 'lo_ytv','loc_dln','loc_jn','loc_kids','loc_ytv')] # obj_id = list(names)[list(names.values()).index([0])] # count 'car' objects in the results # count_result = results[0].boxes.cls[0].item() # count_result = results[0].boxes.cls.tolist() object_counts = {x: 0 for x in names} for r in results: for c in r.boxes.cls: c = int(c) if c in names: object_counts[c] += 1 elif c not in names: object_counts[c] = 1 # clist = results[0].boxes.cls # cls = set() # for cno in clist: # cls.add(model.names[int(cno)]) # if cno in names: # object_counts[cno] += 1 # elif cno not in names: # object_counts[cno] = 1 present_objects = object_counts.copy() for i in object_counts: if object_counts[i] < 1: present_objects.pop(i) # clist= results[0].boxes.cls.tolist() # cls = set() # for cno in clist: # cls.add(model.names[int(cno)]) # count_result = results.pandas().xyxy[0].value_counts('name') return render, present_objects # results = model.predict(image, imgsz=image_size, return_outputs=True) # results = model.predict(image) # object_prediction_list = [] # for _, image_results in enumerate(results): # if len(image_results)!=0: # image_predictions_in_xyxy_format = image_results['det'] # for pred in image_predictions_in_xyxy_format: # x1, y1, x2, y2 = ( # int(pred[0]), # int(pred[1]), # int(pred[2]), # int(pred[3]), # ) # bbox = [x1, y1, x2, y2] # score = pred[4] # category_name = model.model.names[int(pred[5])] # category_id = pred[5] # object_prediction = ObjectPrediction( # bbox=bbox, # category_id=int(category_id), # score=score, # category_name=category_name, # ) # object_prediction_list.append(object_prediction) # image = read_image(image) # output_image = visualize_object_predictions(image=image, object_prediction_list=object_prediction_list) # return output_image['image'] # render = render_result(model=model, image=image, result=results[0]) inputs_image = [ # gr.inputs.Image(type="filepath", label="Input Image"), gr.inputs.Image(type="pil"), gr.inputs.Dropdown(["linhcuem/linhcuem/cham_diem_yolov8"], default="linhcuem/cham_diem_yolov8", label="Model"), gr.inputs.Slider(minimum=320, maximum=1280, default=640, step=32, label="Image Size"), gr.inputs.Slider(minimum=0.0, maximum=1.0, default=0.25, step=0.05, label="Confidence Threshold"), gr.inputs.Slider(minimum=0.0, maximum=1.0, default=0.45, step=0.05, label="IOU Threshold"), ] # outputs_image =gr.outputs.Image(type="filepath", label="Output Image") # count_obj = gr.Textbox(show_label=False) title = "Tất cả do anh Đạt" interface_image = gr.Interface( fn=yolov8_img_inference, inputs=inputs_image, outputs=[gr.Image(type="pil"),gr.Textbox(show_label=False)], title=title, examples=image_path, cache_examples=True, theme='huggingface' ) # gr.TabbedInterface( # [interface_image], # tab_names=['Image inference'] # ).queue().launch() interface_image.launch(debug=True, enable_queue=True)