detect.py

import argparse

import time
from pathlib import Path
from PIL import Image

import torch

from models.experimental import attempt_load
from utils.datasets import LoadImages
from utils.general import (
    check_img_size, non_max_suppression, apply_classifier, scale_coords, xyxy2xywh, plot_one_box, strip_optimizer)
from utils.torch_utils import select_device, load_classifier, time_synchronized


def detect():
    out, source, weights, view_img, save_txt, imgsz = \
        opt.output, opt.source, opt.weights, opt.view_img, opt.save_txt, opt.img_size
    webcam = source == '0' or source.startswith('rtsp') or source.startswith('http') or source.endswith('.txt')

    # Initialize
    device = select_device(opt.device)
    half = device.type != 'cpu'  # half precision only supported on CUDA

    # Load model
    model = attempt_load(weights, map_location=device)  # load FP32 model
    imgsz = check_img_size(imgsz, s=model.stride.max())  # check img_size
    if half:
        model.half()  # to FP16

    # Set Dataloader
    dataset = LoadImages(source, img_size=imgsz)

    # Get names and colors
    names = model.module.names if hasattr(model, 'module') else model.names
 
    # Run inference
    t0 = time.time()
    img = torch.zeros((1, 3, imgsz, imgsz), device=device)  # init img
    _ = model(img.half() if half else img) if device.type != 'cpu' else None  # run once
    for path, img, im0s, vid_cap in dataset:
        if img is None:
            print("Image not found:", path)
            continue
        try:
            img = torch.from_numpy(img).to(device)
            img = img.half() if half else img.float()  # uint8 to fp16/32
            img /= 255.0  # 0 - 255 to 0.0 - 1.0
            if img.ndimension() == 3:
                img = img.unsqueeze(0)

            # Inference
            pred = model(img, augment=opt.augment)[0]

            # Apply NMS
            pred = non_max_suppression(pred, opt.conf_thres, opt.iou_thres, classes=opt.classes, agnostic=opt.agnostic_nms)

            # Process detections
            for i, det in enumerate(pred):  # detections per image
                if webcam:  # batch_size >= 1
                    p, s, im0 = path[i], '%g: ' % i, im0s[i].copy()
                else:
                    p, s, im0 = path, '', im0s

                save_path = str(Path(out) / Path(p).name)
                s += '%gx%g ' % img.shape[2:]  # print string
                
                if det is not None and len(det):
                    # Rescale boxes from img_size to im0 size
                    det[:, :4] = scale_coords(img.shape[2:], det[:, :4], im0.shape).round()

                    # Print results
                    for c in det[:, -1].unique():
                        n = (det[:, -1] == c).sum()  # detections per class
                        s += '%g %ss, ' % (n, names[int(c)])  # add to string
                    
                    # Write results
                    for *xyxy, _, _ in det:
                        box = (int(xyxy[0]), int(xyxy[1]), int(xyxy[2]), int(xyxy[3]))
                        process(p, save_path, box)
                        break
                else:
                    process(p, save_path)
        except KeyboardInterrupt:
            raise
        except:
            print("Error processing file", path)
                    
    print('Done. (%.3fs)' % (time.time() - t0))

def process(in_file, out_file, box=None):
    img = Image.open(in_file)

    if box is None:
       box = [0,0,img.size[0],img.size[0]]

    img_pad = 25

    box_l = int(box[0]) - img_pad
    box_t = int(box[1]) - img_pad
    box_r = int(box[2]) + img_pad
    box_b = int(box[3]) + img_pad
    
    # normalize box coordinates
    box_l = max(0, box_l)
    box_t = max(0, box_t)
    box_r = min(img.size[0], box_r)
    box_b = min(img.size[1], box_b)

    # calculate box width and height
    box_w = int(box_r-box_l)
    box_h = int(box_b-box_t)

    print("image size", img.size)
    print("original box", (box_l, box_t, box_r, box_b))
    print("original box size", box_w, "x", box_h)

    # find the smaller dimension
    box_d = min(box_w, box_h)

    # adjust box coordinates to be square
    box_l = int(box_l + (box_w - box_d)/2)
    box_t = int(box_t + (box_h - box_d)/2)
    box_r = int(box_l + box_d)
    box_b = int(box_t + box_d)
    
    box_w = int(box_r-box_l)
    box_h = int(box_b-box_t)   
    
    print("adjusted box", (box_l, box_t, box_r, box_b))
    print("adjusted size", box_w, "x", box_h)

    im_new = img.crop((box_l, box_t, box_r, box_b)).resize((300,300), Image.Resampling.LANCZOS)
    im_new.save(out_file)

if __name__ == '__main__':
    parser = argparse.ArgumentParser()
    parser.add_argument('--weights', nargs='+', type=str, default='weights/yolov5x_anime.pt', help='model.pt path(s)')
    parser.add_argument('--source', type=str, help='source', required=True)  # file/folder, 0 for webcam
    parser.add_argument('--output', type=str, help='output folder', required=True)  # output folder
    parser.add_argument('--img-size', type=int, default=640, help='inference size (pixels)')
    parser.add_argument('--conf-thres', type=float, default=0.4, help='object confidence threshold')
    parser.add_argument('--iou-thres', type=float, default=0.5, help='IOU threshold for NMS')
    parser.add_argument('--device', default='', help='cuda device, i.e. 0 or 0,1,2,3 or cpu')
    parser.add_argument('--view-img', action='store_true', help='display results')
    parser.add_argument('--save-txt', action='store_true', help='save results to *.txt')
    parser.add_argument('--classes', nargs='+', type=int, help='filter by class: --class 0, or --class 0 2 3')
    parser.add_argument('--agnostic-nms', action='store_true', help='class-agnostic NMS')
    parser.add_argument('--augment', action='store_true', help='augmented inference')
    parser.add_argument('--update', action='store_true', help='update all models')
    opt = parser.parse_args()
    print(opt)

    with torch.no_grad():
        if opt.update:  # update all models (to fix SourceChangeWarning)
            for opt.weights in ['yolov5s.pt', 'yolov5m.pt', 'yolov5l.pt', 'yolov5x.pt']:
                detect()
                strip_optimizer(opt.weights)
        else:
            detect()