HTTP/2 302 date: Thu, 24 Jul 2025 20:52:16 GMT content-type: text/html; charset=utf-8 content-length: 0 vary: X-PJAX, X-PJAX-Container, Turbo-Visit, Turbo-Frame, X-Requested-With,Accept-Encoding, Accept, X-Requested-With location: https://objects.githubusercontent.com/github-production-repository-file-5c1aeb/5108051/10762369?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Credential=AKIAVCODYLSA53PQK4ZA%2F20250724%2Fus-east-1%2Fs3%2Faws4_request&X-Amz-Date=20250724T205216Z&X-Amz-Expires=300&X-Amz-Signature=1393679325a721e48100add5c8adadf9663b229b309597d296b319ac45952558&X-Amz-SignedHeaders=host&response-content-disposition=attachment%3Bfilename%3Dmain.py.txt&response-content-type=text%2Fplain cache-control: no-cache strict-transport-security: max-age=31536000; includeSubdomains; preload x-frame-options: deny x-content-type-options: nosniff x-xss-protection: 0 referrer-policy: no-referrer-when-downgrade content-security-policy: default-src 'none'; base-uri 'self'; child-src github.githubassets.com github.com/assets-cdn/worker/ github.com/assets/ gist.github.com/assets-cdn/worker/; connect-src 'self' uploads.github.com www.githubstatus.com collector.github.com raw.githubusercontent.com api.github.com github-cloud.s3.amazonaws.com github-production-repository-file-5c1aeb.s3.amazonaws.com github-production-upload-manifest-file-7fdce7.s3.amazonaws.com github-production-user-asset-6210df.s3.amazonaws.com *.rel.tunnels.api.visualstudio.com wss://*.rel.tunnels.api.visualstudio.com objects-origin.githubusercontent.com copilot-proxy.githubusercontent.com proxy.individual.githubcopilot.com proxy.business.githubcopilot.com proxy.enterprise.githubcopilot.com *.actions.githubusercontent.com wss://*.actions.githubusercontent.com productionresultssa0.blob.core.windows.net/ productionresultssa1.blob.core.windows.net/ productionresultssa2.blob.core.windows.net/ productionresultssa3.blob.core.windows.net/ productionresultssa4.blob.core.windows.net/ productionresultssa5.blob.core.windows.net/ productionresultssa6.blob.core.windows.net/ productionresultssa7.blob.core.windows.net/ productionresultssa8.blob.core.windows.net/ productionresultssa9.blob.core.windows.net/ productionresultssa10.blob.core.windows.net/ productionresultssa11.blob.core.windows.net/ productionresultssa12.blob.core.windows.net/ productionresultssa13.blob.core.windows.net/ productionresultssa14.blob.core.windows.net/ productionresultssa15.blob.core.windows.net/ productionresultssa16.blob.core.windows.net/ productionresultssa17.blob.core.windows.net/ productionresultssa18.blob.core.windows.net/ productionresultssa19.blob.core.windows.net/ github-production-repository-image-32fea6.s3.amazonaws.com github-production-release-asset-2e65be.s3.amazonaws.com insights.github.com wss://alive.github.com api.githubcopilot.com api.individual.githubcopilot.com api.business.githubcopilot.com api.enterprise.githubcopilot.com; font-src github.githubassets.com; form-action 'self' github.com gist.github.com copilot-workspace.githubnext.com objects-origin.githubusercontent.com; frame-ancestors 'none'; frame-src viewscreen.githubusercontent.com notebooks.githubusercontent.com; img-src 'self' data: blob: github.githubassets.com media.githubusercontent.com camo.githubusercontent.com identicons.github.com avatars.githubusercontent.com private-avatars.githubusercontent.com github-cloud.s3.amazonaws.com objects.githubusercontent.com release-assets.githubusercontent.com secured-user-images.githubusercontent.com/ user-images.githubusercontent.com/ private-user-images.githubusercontent.com opengraph.githubassets.com copilotprodattachments.blob.core.windows.net/github-production-copilot-attachments/ github-production-user-asset-6210df.s3.amazonaws.com customer-stories-feed.github.com spotlights-feed.github.com objects-origin.githubusercontent.com *.githubusercontent.com; manifest-src 'self'; media-src github.com user-images.githubusercontent.com/ secured-user-images.githubusercontent.com/ private-user-images.githubusercontent.com github-production-user-asset-6210df.s3.amazonaws.com gist.github.com; script-src github.githubassets.com; style-src 'unsafe-inline' github.githubassets.com; upgrade-insecure-requests; worker-src github.githubassets.com github.com/assets-cdn/worker/ github.com/assets/ gist.github.com/assets-cdn/worker/ server: github.com set-cookie: _gh_sess=84PIw0OLDJJPY7xcekvf%2BgiKpaRQOgjRBgf1DIxghjfbHmpHmv1Ila2sv9mJxOp5Vx6dMQhJRX8h%2FmayR8vmsDerJkY0rM%2FbGeFO815Q5t2cDJ%2FWOHBfYCSD4Zhyr04V43AxlaWHdicSCUxciYVGxBmcvnRAsAOUlyoPrQlYKnj6f0UldZK3J8iD7nKzr4H5uCusa4llyda61foeywLgy8R6%2BQnAWGhf3%2BN8pUT%2Bo8R9LO%2BBmeBpEF%2BOWM6H7tt0G2BC%2FfVEoblZgAgI7S6M1A%3D%3D--JNHidElcU%2BgYXrRL--npHz7ke6ry7RhwVmx3vcJA%3D%3D; Path=/; HttpOnly; Secure; SameSite=Lax set-cookie: _octo=GH1.1.402456917.1753390336; Path=/; Domain=github.com; Expires=Fri, 24 Jul 2026 20:52:16 GMT; Secure; SameSite=Lax set-cookie: logged_in=no; Path=/; Domain=github.com; Expires=Fri, 24 Jul 2026 20:52:16 GMT; HttpOnly; Secure; SameSite=Lax x-github-request-id: 855E:249F26:6955A:8F39B:68829D00 HTTP/2 200 content-type: text/plain last-modified: Tue, 04 Mar 2025 13:14:24 GMT etag: "0x8DD5B1E7C040B3C" server: Windows-Azure-Blob/1.0 Microsoft-HTTPAPI/2.0 x-ms-request-id: d1b9e916-b01e-007c-0e33-fcb90e000000 x-ms-version: 2025-05-05 x-ms-creation-time: Tue, 04 Mar 2025 13:14:24 GMT x-ms-blob-content-md5: h+SuzUPySGomequBrvCXVQ== x-ms-lease-status: unlocked x-ms-lease-state: available x-ms-blob-type: BlockBlob content-disposition: attachment;filename=main.py.txt x-ms-server-encrypted: true via: 1.1 varnish, 1.1 varnish fastly-restarts: 1 accept-ranges: bytes age: 0 date: Thu, 24 Jul 2025 20:52:18 GMT x-served-by: cache-iad-kiad7000123-IAD, cache-bom-vanm7210086-BOM x-cache: MISS, HIT x-cache-hits: 0, 0 x-timer: S1753390337.890576,VS0,VE335 content-length: 11871 #!/usr/bin/env python """qr.py Usage example: python qr.py -o out.yaml -p qrcodes/detection -H, --help - show help -o, --output - output file (default out.yaml) -p, --path - input dataset path (default qrcodes/detection) -a, --accuracy - input accuracy (default 20 pixels) -alg, --algorithm - input alg (default opencv) --metric - input norm (default l_inf) """ import argparse import glob from enum import Enum import time import numpy as np from numpy import linalg as LA import cv2 as cv class DetectorQR: TypeDetector = Enum('TypeDetector', 'opencv opencv_wechat') def __init__(self): self.detected_corners = np.array([]) self.decoded_info = [] self.detector = None class CvObjDetector(DetectorQR): def __init__(self): super().__init__() self.detector = cv.QRCodeDetector() def detect(self, image, use_alignment=True): _, decoded_info, corners, _ = self.detector.detectAndDecodeMulti(image) if corners is None or len(corners) == 0: return False, np.array([]) self.decoded_info = decoded_info self.detected_corners = corners return True, corners def detect_aruco(self, image): self.detector.detectMultiAruco(image) def decode(self, image, use_alignment=True): if use_alignment: if len(self.decoded_info) == 0: return 0, [], None return True, self.decoded_info, self.detected_corners else: if self.detected_corners.size == 0: return 0, [], None r, decoded_info, straight_qrcode = self.detector.decodeMulti(image, self.detected_corners) self.decoded_info = decoded_info return r, decoded_info, straight_qrcode class CvWechatDetector(DetectorQR): def __init__(self, path_to_model="./"): super().__init__() self.detector = cv.wechat_qrcode_WeChatQRCode(path_to_model + "detect.prototxt", path_to_model + "detect.caffemodel", path_to_model + "sr.prototxt", path_to_model + "sr.caffemodel") def detect(self, image): decoded_info, corners = self.detector.detectAndDecode(image) if len(decoded_info) == 0: return False, np.array([]) corners = np.array(corners).reshape(-1, 4, 2) self.decoded_info = decoded_info self.detected_corners = corners return True, corners def decode(self, image): if len(self.decoded_info) == 0: return 0, [], None return True, self.decoded_info, self.detected_corners def create_instance_qr(type_detector=DetectorQR.TypeDetector.opencv, path_to_model="./"): if type_detector is DetectorQR.TypeDetector.opencv: return CvObjDetector() if type_detector is DetectorQR.TypeDetector.opencv_wechat: return CvWechatDetector(path_to_model) raise TypeError("this type_detector isn't supported") def find_images_path(dir_path): images = glob.glob(dir_path + '/*.jpg') images += glob.glob(dir_path + '/*.png') return images def get_gold_corners(label_path): f = open(label_path, "r") corners = [] for line in f.readlines(): try: f_list = [float(i) for i in line.split(" ")] corners += f_list except ValueError as e: pass return np.array(corners).reshape(-1, 4, 2) # l_1 - https://en.wikipedia.org/wiki/Norm_(mathematics) # l_inf - Chebyshev norm https://en.wikipedia.org/wiki/Chebyshev_distance TypeNorm = Enum('TypeNorm', 'l1 l2 l_inf') def get_norm(gold_corners, corners, type_dist): if type_dist is TypeNorm.l1: return LA.norm((gold_corners - corners).flatten(), 1) if type_dist is TypeNorm.l2: return LA.norm((gold_corners - corners).flatten(), 2) if type_dist is TypeNorm.l_inf: return LA.norm((gold_corners - corners).flatten(), np.inf) raise TypeError("this TypeNorm isn't supported") def get_norm_to_rotate_qr(gold_corner, corners, accuracy, type_dist=TypeNorm.l_inf): corners = corners.reshape(-1, 4, 2) dist = 1e9 for one_corners in corners: dist = min(dist, get_norm(gold_corner, one_corners, type_dist)) for i in range(0, 3): one_corners = np.roll(one_corners, 1, 0) dist = min(dist, get_norm(gold_corner, one_corners, type_dist)) one_corners = np.flip(one_corners, 0) dist = min(dist, get_norm(gold_corner, one_corners, type_dist)) for i in range(0, 3): one_corners = np.roll(one_corners, 1, 0) dist = min(dist, get_norm(gold_corner, one_corners, type_dist)) return dist def read_output(path): fs = cv.FileStorage(path, cv.FILE_STORAGE_READ) root = fs.root() for image in root.keys(): if image.split('_')[0] == "img": image_category = image.split("_")[-2] image_info = root.getNode(image) corners = image_info.getNode("corners").mat() decoded_info = image_info.getNode("decoded_info") if not decoded_info.empty(): for i in range(decoded_info.size()): # print(decoded_info.at(i).string()) pass def main(): # parse command line options parser = argparse.ArgumentParser(description="bench QR code dataset", add_help=False) parser.add_argument("-H", "--help", help="show help", action="store_true", dest="show_help") parser.add_argument("-o", "--output", help="output file", default="out.yaml", action="store", dest="output") parser.add_argument("-p", "--path", help="input dataset path", default="qrcodes/detection", action="store", dest="dataset_path") parser.add_argument("-m", "--model", help="path to opencv_wechat model (detect.prototxt, detect.caffemodel," "sr.prototxt, sr.caffemodel), build opencv+contrib to get model", default="./", action="store", dest="model_path") parser.add_argument("-a", "--accuracy", help="input accuracy", default="20", action="store", dest="accuracy", type=int) parser.add_argument("-alg", "--algorithm", help="QR detect algorithm", default="opencv", action="store", dest="algorithm", choices=['opencv', 'opencv_wechat'], type=str) parser.add_argument("--metric", help="Metric for distance between QR corners", default="l2", action="store", dest="metric", choices=['l1', 'l2', 'l_inf'], type=str) args = parser.parse_args() show_help = args.show_help if show_help: parser.print_help() return output = args.output dataset_path = args.dataset_path model_path = args.model_path accuracy = args.accuracy algorithm = args.algorithm metric = TypeNorm.l_inf if args.metric == "l1": metric = TypeNorm.l1 elif args.metric == "l2": metric = TypeNorm.l2 list_dirs = glob.glob(dataset_path + "/*") fs = cv.FileStorage(output, cv.FILE_STORAGE_WRITE) detect_dict = {} decode_dict = {} fs.write("dataset_path", dataset_path) gl_count = 0 gl_detect = 0 gl_decode = 0 gl_dist = 0 gl_pos_dist = 0 qr = create_instance_qr(DetectorQR.TypeDetector[algorithm], model_path) for dir in list_dirs: imgs_path = find_images_path(dir) qr_count = 0 qr_detect = 0 qr_decode = 0 loc_dist = 0 loc_pos_dist = 0 for img_path in imgs_path: label_path = img_path[:-3] + "txt" gold_corners = get_gold_corners(label_path) qr_count += gold_corners.shape[0] image = cv.imread(img_path, cv.IMREAD_IGNORE_ORIENTATION) ret, corners = qr.detect(image) img_name = img_path[:-4].replace('\\', '_') img_name = "img_" + img_name.replace('/', '_') fs.startWriteStruct(img_name, cv.FILE_NODE_MAP) fs.write("bool", int(ret)) fs.write("gold_corners", gold_corners) fs.write("corners", corners) if ret is True: i = 0 r, decoded_info, straight_qrcode = qr.decode(image) decoded_corners = [] if len(decoded_info) > 0: for info in decoded_info: if info != "": qr_decode += 1 for i in range(corners.shape[0]): decoded_corners.append(corners[i]) decoded_corners = np.array(decoded_corners) fs.write("decoded_info", decoded_info) for one_gold_corners in gold_corners: dist = get_norm_to_rotate_qr(one_gold_corners, corners, accuracy, metric) fs.write("dist_to_gold_corner_" + str(i), dist) if dist <= accuracy: qr_detect += 1 i += 1 gl_dist += dist loc_dist += dist for decode_corner, decoded_info in zip(decoded_corners, decoded_info): if decoded_info != "": dist = get_norm_to_rotate_qr(decode_corner, gold_corners, accuracy, metric) gl_pos_dist += dist loc_pos_dist += dist fs.endWriteStruct() category = (dir.replace('\\', '_')).replace('/', '_').split('_')[-1] detect_dict[category] = {"nums": qr_count, "detected": qr_detect, "detected_prop": qr_detect / max(1, qr_count)} decode_dict[category] = {"nums": qr_count, "decoded": qr_decode, "decoded_prop": qr_decode / max(1, qr_count)} print(dir, qr_detect / max(1, qr_count), qr_decode / max(1, qr_count), qr_count) print("loc_dist", loc_dist / max(1, qr_count), " loc_pos_dist", loc_pos_dist / max(1, qr_decode)) gl_count += qr_count gl_detect += qr_detect gl_decode += qr_decode print(gl_count) print(gl_detect) print(gl_decode) print("gl_dist", gl_dist / max(1, gl_count), "gl_pos_dist", gl_pos_dist / max(1, gl_decode)) print("detect", gl_detect / max(1, gl_count)) print("decode", gl_decode / max(1, gl_count)) detect_dict["total"] = {"nums": gl_count, "detected": gl_detect, "detected_prop": gl_detect / max(1, gl_count)} fs.startWriteStruct("category_detected", cv.FILE_NODE_MAP) for category in detect_dict: fs.startWriteStruct(category, cv.FILE_NODE_MAP) fs.write("nums", detect_dict[category]["nums"]) fs.write("detected", detect_dict[category]["detected"]) fs.write("detected_prop", detect_dict[category]["detected_prop"]) fs.endWriteStruct() fs.endWriteStruct() decode_dict["total"] = {"nums": gl_count, "decoded": gl_decode, "decoded_prop": gl_decode / max(1, gl_count)} fs.startWriteStruct("category_decoded", cv.FILE_NODE_MAP) for category in decode_dict: fs.startWriteStruct(category, cv.FILE_NODE_MAP) fs.write("nums", decode_dict[category]["nums"]) fs.write("decoded", decode_dict[category]["decoded"]) fs.write("decoded_prop", decode_dict[category]["decoded_prop"]) fs.endWriteStruct() fs.endWriteStruct() if __name__ == '__main__': start = time.time() main() print(time.time() - start)