app.py

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
import cv2 

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','cham_diem_yolov8', 640, 0.25, 0.45],['test_images/2ce19ce0191acb44920b.jpg','cham_diem_yolov8', 640, 0.25, 0.45],
             ['test_images/2daab6ea3310e14eb801.jpg','cham_diem_yolov8', 640, 0.25, 0.45], ['test_images/4a137deefb14294a7005 (1).jpg','cham_diem_yolov8', 640, 0.25, 0.45],
             ['test_images/7e77c596436c9132c87d.jpg','cham_diem_yolov8', 640, 0.25, 0.45], ['test_images/170f914014bac6e49fab.jpg','cham_diem_yolov8', 640, 0.25, 0.45],
             ['test_images/3355ec3269c8bb96e2d9.jpg','cham_diem_yolov8', 640, 0.25, 0.45], ['test_images/546306a88052520c0b43.jpg','cham_diem_yolov8', 640, 0.25, 0.45],
             ['test_images/33148464019ed3c08a8f.jpg','cham_diem_yolov8', 640, 0.25, 0.45], ['test_images/a17a992a1cd0ce8e97c1.jpg','cham_diem_yolov8', 640, 0.25, 0.45],
             ['test_images/b5db5e42d8b80ae653a9 (1).jpg','cham_diem_yolov8', 640, 0.25, 0.45],['test_images/b8ee1f5299a84bf612b9.jpg','cham_diem_yolov8', 640, 0.25, 0.45],
             ['test_images/b272fec7783daa63f32c.jpg','cham_diem_yolov8', 640, 0.25, 0.45],['test_images/bb202b3eaec47c9a25d5.jpg','cham_diem_yolov8', 640, 0.25, 0.45],
             ['test_images/bf1e22b0a44a76142f5b.jpg','cham_diem_yolov8', 640, 0.25, 0.45], ['test_images/ea5473c5f53f27617e2e.jpg','cham_diem_yolov8', 640, 0.25, 0.45],
             ['test_images/ee106392e56837366e79.jpg','cham_diem_yolov8', 640, 0.25, 0.45], ['test_images/f88d2214a4ee76b02fff.jpg','cham_diem_yolov8', 640, 0.25, 0.45]]

# Load YOLO model
model = YOLO('linhcuem/cham_diem_yolov8')
# model = YOLO('linhcuem/chamdiemgianhang_yolov8_300epochs')
# model = YOLO('linhcuem/chamdiemgianhang_yolov8_ver21')
# model = YOLO('linhcuem/cham_diem_yolov8_ver20')
# model_ids = ['linhcuem/checker_TB_yolov8_ver1', 'linhcuem/cham_diem_yolov8', 'linhcuem/chamdiemgianhang_yolov8_300epochs', 'linhcuem/cham_diem_yolov8_ver20', 'linhcuem/chamdiemgianhang_yolov8_ver21']
# model = YOLO('linhcuem/checker_TB_yolov8_ver1')
# current_model_id = model_ids[-1]
# model = YOLO(current_model_id)
# model = YOLO(model_path)

###################################################
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, imgsz=image_size, conf=conf_threshold, iou=iou_threshold)
    render = render_result(model=model, image=image, result=results[0])
    # get the model names list
    names = model.names
  
    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

    present_objects = object_counts.copy()

    for i in object_counts:
        if object_counts[i] < 1:
            present_objects.pop(i)
    

    return render, {names[k]: v for k, v in present_objects.items()}


def yolov8_vid_inference(video_path):
    cap = cv2.VideoCapture(video_path)
    while cap.isOpened():
        success, frame = cap.read()

        if success:
            frame_copy = frame.copy()
            outputs = model.predict(source=frame)
            results = outputs[0].cpu().numpy()
            for i, det in enumerate(results.boxes.xyxy):
                cv2.rectangle(
                    frame_copy,
                    (int(det[0]), int(det[1])),
                    (int(det[2]), int(det[3])),
                    color=(0, 0, 255),
                    thickness=2,
                    lineType=cv2.LINE_AA
                )
            yield cv2.cvtColor(frame_copy, cv2.COLOR_BGR2RGB)
    

inputs_vid = [
    gr.components.Video(type="filepath", label="Input Video"),
]

outputs_vid = [
    gr.components.Image(type="numpy", label="Output Image"),
              ]

interface_vid = gr.Interface(
    fn=yolov8_vid_inference,
    inputs = inputs_vid,
    outputs = outputs_vid,
    title = "Detect Thiên Việt productions",
    cache_examples = False,
    
)

# inputs_image = [
#     # gr.inputs.Image(type="filepath", label="Input Image"),
#     gr.Image(type="pil"),
#     # gr.Dropdown(["linhcuem/linhcuem/chamdiemgianhang_yolov8_ver1"], 
#                         default="linhcuem/chamdiemgianhang_yolov8_ver1", label="Model"),
    
#     gr.Slider(maximum=1280, step=32, value = 640, label="Image Size"),
#     gr.Slider(maximum=1.0 , step=0.05, value = 0.25, label="Confidence Threshold"),
#     gr.Slider(maximum=1.0, step=0.05, value = 0.45, label="IOU Threshold"),
    
    
# ]

# outputs_image =gr.outputs.Image(type="filepath", label="Output Image")
# count_obj = gr.Textbox(show_label=False)

title = "Detect Thiên Việt productions"

interface_image = gr.Interface(
    fn=yolov8_img_inference,
    inputs=[
        gr.inputs.Image(type='pil'),
        gr.inputs.Dropdown(["linhcuem/checker_TB_yolov8_ver1"],
                   default="linhcuem/checker_TB_yolov8_ver1", 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=[gr.Image(type="pil"),gr.Textbox(show_label=False)],
    title=title,
    examples=image_path,
    cache_examples=True if image_path else False,
    
)

gr.TabbedInterface(
    [interface_image, interface_vid],
    tab_names=['Image inference', 'Video inference']
).queue().launch()

# interface_image.launch(debug=True, enable_queue=True)