detect_plate.py

# -*- coding: UTF-8 -*-
import argparse
import time
from pathlib import Path

import cv2
import torch
import torch.backends.cudnn as cudnn
from numpy import random
import copy

from models.experimental import attempt_load
from utils.datasets import letterbox
from utils.general import check_img_size, non_max_suppression_plate, apply_classifier, scale_coords, xyxy2xywh, \
    strip_optimizer, set_logging, increment_path
from utils.plots import plot_one_box
from utils.torch_utils import select_device, load_classifier, time_synchronized
import os


cv2.namedWindow("img", 0);
cv2.resizeWindow("img", 1280,720);

def load_model(weights, device):
    model = attempt_load(weights, map_location=device)  # load FP32 model
    return model


def scale_coords_landmarks(img1_shape, coords, img0_shape, ratio_pad=None):
    # Rescale coords (xyxy) from img1_shape to img0_shape
    if ratio_pad is None:  # calculate from img0_shape
        gain = min(img1_shape[0] / img0_shape[0], img1_shape[1] / img0_shape[1])  # gain  = old / new
        pad = (img1_shape[1] - img0_shape[1] * gain) / 2, (img1_shape[0] - img0_shape[0] * gain) / 2  # wh padding
    else:
        gain = ratio_pad[0][0]
        pad = ratio_pad[1]

    coords[:, [0, 2, 4, 6]] -= pad[0]  # x padding
    coords[:, [1, 3, 5, 7]] -= pad[1]  # y padding
    coords[:, :8] /= gain
    #clip_coords(coords, img0_shape)
    coords[:, 0].clamp_(0, img0_shape[1])  # x1
    coords[:, 1].clamp_(0, img0_shape[0])  # y1
    coords[:, 2].clamp_(0, img0_shape[1])  # x2
    coords[:, 3].clamp_(0, img0_shape[0])  # y2
    coords[:, 4].clamp_(0, img0_shape[1])  # x3
    coords[:, 5].clamp_(0, img0_shape[0])  # y3
    coords[:, 6].clamp_(0, img0_shape[1])  # x4
    coords[:, 7].clamp_(0, img0_shape[0])  # y4

    return coords

def show_results(img, xywh, conf, landmarks, class_num):
    h,w,c = img.shape
    #tl = 1 or round(0.002 * (h + w) / 2) + 1  # line/font thickness
    x1 = int(xywh[0] * w - 0.5 * xywh[2] * w)
    y1 = int(xywh[1] * h - 0.5 * xywh[3] * h)
    x2 = int(xywh[0] * w + 0.5 * xywh[2] * w)
    y2 = int(xywh[1] * h + 0.5 * xywh[3] * h)
    cv2.rectangle(img, (x1,y1), (x2, y2), (0,255,0), thickness=3, lineType=cv2.LINE_AA)

    clors = [(255,0,0),(0,255,0),(0,0,255),(255,255,0),(0,255,255)]

    for i in range(4):
        point_x = int(landmarks[2 * i] * w)
        point_y = int(landmarks[2 * i + 1] * h)
        cv2.circle(img, (point_x, point_y), 3, clors[i], -1)

    label = str(conf)[:5]
    return img



def detect_one(model, image_path, device):
    # Load model
    img_size = 800
    conf_thres = 0.3
    iou_thres = 0.5

    orgimg = cv2.imread(image_path)  # BGR
    sp = orgimg.shape
    h = sp[0]
    w = sp[1]
    #img_size = h
    print(w,h)
    img0 = copy.deepcopy(orgimg)
    assert orgimg is not None, 'Image Not Found ' + image_path
    h0, w0 = orgimg.shape[:2]  # orig hw
    r = img_size / max(h0, w0)  # resize image to img_size
    if r != 1:  # always resize down, only resize up if training with augmentation
        interp = cv2.INTER_AREA if r < 1  else cv2.INTER_LINEAR
        img0 = cv2.resize(img0, (int(w0 * r), int(h0 * r)), interpolation=interp)

    imgsz = check_img_size(img_size, s=model.stride.max())  # check img_size

    img = letterbox(img0, new_shape=imgsz)[0]
    # Convert
    img = img[:, :, ::-1].transpose(2, 0, 1).copy()  # BGR to RGB, to 3x416x416

    # Run inference
    t0 = time.time()

    img = torch.from_numpy(img).to(device)
    img = 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
    t1 = time_synchronized()
    pred = model(img)[0]

    # Apply NMS
    pred = non_max_suppression_plate(pred, conf_thres, iou_thres)

    print('img.shape: ', img.shape)
    print('orgimg.shape: ', orgimg.shape)

    # Process detections
    for i, det in enumerate(pred):  # detections per image
        gn = torch.tensor(orgimg.shape)[[1, 0, 1, 0]].to(device)  # normalization gain whwh
        gn_lks = torch.tensor(orgimg.shape)[[1, 0, 1, 0, 1, 0, 1, 0]].to(device)  # normalization gain landmarks
        if len(det):
            # Rescale boxes from img_size to im0 size
            det[:, :4] = scale_coords(img.shape[2:], det[:, :4], orgimg.shape).round()

            # Print results
            for c in det[:, -1].unique():
                n = (det[:, -1] == c).sum()  # detections per class

            det[:, 5:13] = scale_coords_landmarks(img.shape[2:], det[:, 5:13], orgimg.shape).round()

            for j in range(det.size()[0]):
                xywh = (xyxy2xywh(det[j, :4].view(1, 4)) / gn).view(-1).tolist()
                conf = det[j, 4].cpu().numpy()
                landmarks = (det[j, 5:13].view(1, 8) / gn_lks).view(-1).tolist()
                class_num = det[j, 13].cpu().numpy()
                orgimg = show_results(orgimg, xywh, conf, landmarks, class_num)
   
    cv2.imshow("img",orgimg)
    cv2.waitKey(0)

def show_files(path, all_files):
    # 首先遍历当前目录所有文件及文件夹
    file_list = os.listdir(path)
    # 准备循环判断每个元素是否是文件夹还是文件，是文件的话，把名称传入list，是文件夹的话，递归
    for file in file_list:
        # 利用os.path.join()方法取得路径全名，并存入cur_path变量，否则每次只能遍历一层目录
        cur_path = os.path.join(path, file)
        # 判断是否是文件夹
        if os.path.isdir(cur_path):
            show_files(cur_path, all_files)
        else:
            if not cur_path.endswith(('jpg')):
                continue
            else:
                all_files.append(cur_path )

    return all_files

f = show_files("/home/zeusee/plate/", [])


if __name__ == '__main__':
    parser = argparse.ArgumentParser()
    parser.add_argument('--weights', nargs='+', type=str, default='runs/train/exp/weights/last.pt', help='model.pt path(s)')
    parser.add_argument('--image', type=str, default='data/images/test.jpg', help='source')  # file/folder, 0 for webcam
    parser.add_argument('--img-size', type=int, default=640, help='inference size (pixels)')
    opt = parser.parse_args()
    print(opt)
    device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
    model = load_model(opt.weights, device)

    for filename in f:
        
        print(filename)
        detect_one(model, filename, device)