def worker(ip, t, m, h): global times, n, passip if detect(ip, t, h) == True: passip.append(ip) print('√ ' + ip) else: if m == False: print('x ' + ip) times += 1 if times == n: global output print('√ finish ' + '本次扫描了' + str(times) + '个ip,' + 'SNI_IP有' + str(len(passip)) + '个。') if output == 'replace': name = time.strftime('%Y-%m-%d-%H-%M-%S', time.localtime(time.time())) output = 'PassIp ' + name + '.txt' f = open(output, 'w') try: for v in passip: f.writelines(v + '\n') finally: f.close() print('bye,文件已写出到' + output + ',按Enter退出。') input()
def auto(camera, rawCapture, cas_params, stop_event): print("In Auto Detction System for PiCamera...") g.track_flag check_candidates(stop_event) for frame in camera.capture_continuous(rawCapture, format="bgr", use_video_port=True): flag = False raw_img = frame.array # cv2.imshow("Raw", img) # img = preprocess(img) # cv2.imshow("Preprocessed", img) rects, detected_img = detect(raw_img, cas_params) g.img = box(rects, detected_img) # cv2.imshow("Cascaded", img) measure(raw_img, rects) # if there's no rects found, look around # if not rects: # look_around() # Check time elapsed, if over 10 sec, invoke spiral search # if (time.time()-start) > 10: # spiral_search() if g.track_flag: track(g.avg_pos) g.track_flag = False #time.sleep(.1) rawCapture.truncate(0)
def sdetect(): for impath in glob.glob("output/json/*.jpg"): img = cv2.imread(impath) im = cv2.Canny(img, 200, 200) onimg = cv2.imread(impath) oimg = cv2.imread(impath) hsv = cv2.cvtColor(img, cv2.COLOR_BGR2HSV) hue, sens = 60, 40 lowergreen = np.array([hue - sens, 50, 50]) uppergreen = np.array([hue + sens, 255, 255]) mask = cv2.inRange(hsv, lowergreen, uppergreen) img = cv2.bitwise_and(img, img, mask=cv2.bitwise_not(mask)) img = cv2.bitwise_and(img, img, mask=cv2.bitwise_not(im)) frame = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY) ret, threshed = cv2.threshold(frame, 127, 255, cv2.THRESH_TOZERO) img = cv2.bitwise_and(img, img, mask=cv2.bitwise_not(threshed)) gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY) blurred = cv2.GaussianBlur(gray, (5, 5), 0) ret, thresh = cv2.threshold(blurred, 0, 255, cv2.THRESH_TOZERO) _, cnts, heier = cv2.findContours(thresh.copy(), cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE) n = 0 cnt = list() for c in cnts: area = cv2.contourArea(c) if area > 100: cnt.append(c) shape = detect(c) n += 1 ## haar = cv2.CascadeClassifier('E://stage2.xml') ## if haar.detectMultiScale(gray, 1.3, 5): ## shape="person" return shape
def upload_page(): if request.method == 'POST': # check if the post request has the file part if 'file' not in request.files: return render_template('upload.html', msg='No file selected') file = request.files['file'] # if user does not select file, browser also # submit a empty part without filename if file.filename == '': return render_template('upload.html', msg='No file selected') if file and allowed_file(file.filename): file_path = os.path.join(os.getcwd() + UPLOAD_FOLDER, file.filename) file.save(file_path) print(file.filename) # call the OCR function on it extracted_text = detect(file_path) print(extracted_text) # extract the text and display it return render_template('upload.html', msg='Successfully processed', extracted_text=extracted_text, img_src='/static/uploads/' + file.filename) elif request.method == 'GET': return render_template('upload.html')
def worker(ip, t, m, h): global times, n, passip ret = detect(ip, t, h) with lock: if ret: passip.append(ip) printx('√ ' + ip, 1) times += 1 printx()
def run(self): print('[*] LIVE Camera') for stream in detect(): if stream[0] == "Busy Camera": self.cv_img = cv2.imread("../../img/offline.jpg") self.change_pixmap_signal.emit(self.cv_img) break else: self.cv_img = stream[1] self.change_pixmap_signal.emit(self.cv_img) self.detected_label = stream[0] print("DETECTED=", stream[0])
def worker(t, h): global times, passip, ipQueue try: ip = ipQueue.get(timeout=5) except: pass else: r = detect(ip, t, h) times += 1 if r == True: passip.append(ip) printx('√ ' + ip, 1) printx()
def worker(port): while not q.empty(): global times, n, passip, stop ip = q.get_nowait() port = 8118 if port is None else str(port) if detect(ip, timeout, hostname, port) and req_test(ip, port) == True: passip.append(ip) printx('√ ' + ip, 1) times += 1 printx() global output #print ('√ finish ' + 'This time seem'+ str(times) +' ip,'+'SNI_IP '+ str(len(passip)) +' s。') print(times) print(passip)
def ImageRec(self): output_dir, _ = os.path.split(self.file_dir) output_file = detect(source=self.file_dir, output=output_dir) image = cv2.imread(output_file) rows, cols, channels = image.shape bytesPerLine = channels * cols cv2.cvtColor(image, cv2.COLOR_BGR2RGB, image) QImg = QImage(image.data, cols, rows, bytesPerLine, QImage.Format_RGB888) self.ui.lab_home_main_disc.setPixmap( QPixmap.fromImage(QImg).scaled(self.ui.lab_home_main_disc.size(), Qt.KeepAspectRatio, Qt.SmoothTransformation)) ###############################################################################################################################################################
def traffic(): d = driver() d.setStatus(mode="speed") isfirst = True decisions = {1: 'left', 0: 'straight', -1: 'right'} dodetect = 0 while 1: try: img_origin, img = get_img(camera, closed_size) cruise_main(d, img, isfirst) isfirst = False dodetect = (dodetect + 1) % detect_interval if dodetect % detect_interval != 0: continue zebra_conf = detect(img_origin, zebra_threshold, zebra, zebra_area) decision, sign_conf = detect_sign(img_origin, sign_threshold, right, straight, left, sign_area) print('[ Detection ] [ Zebra', zebra_conf, '] [ Sign', sign_conf, ']') if zebra_conf > zebra_conf_threshold: print("[ Zebra ] [ Confidence", zebra_conf, ']') control_open(d, 0, 0, 3) img_origin, img = move_away_from_zebra(d, camera, time_for_zebra, closed_size, zebra_edge, zebra_motorMax) if sign_conf > sign_conf_threshold: print("[ Sign ] [ Confidence", sign_conf, '] [ Decision', decisions[decision], ']') if decision: motor = motor_for_turn steer = decision * steer_for_turn control_open(d, motor, steer, time_for_turn) else: cruise_main(d, img, False) except KeyboardInterrupt: break d.setStatus(motor=0.0, servo=0.0, dist=0x00, mode="stop") d.close() del d
def post(self): data = parser.parse_args() if data['pic'] == "": return {'data': '', 'message': 'No file found', 'status': 'error'} photo = data['pic'] if photo: filename = 'your_image.png' photo.save(os.path.join(UPLOAD_FOLDER, filename)) #data = "test sentense" data = detect('uploads/your_image.png') data = make_sentense_from_raw(data) return {'data': data, 'status': 'success'} return { 'data': '', 'message': 'Something when wrong', 'status': 'error' }
def spider(self): # we create a default resource for # the directory itself self.resources.push(Resource({"name": "index", "path": self.folder})) # the grid is like an index of the files on the file system # and their relationships (hyperlinks) # where to find everything and how to intitialise # the non-static parts of a living document # such as the microservices and REPLs for item in self.resources: # an item probes its exitence - it may no longer exist on the file system item.probe() for file in self.folder: # detect the general kind of file and add it to the resources resource = detect(file) self.resources.append(resource)
def worker (ip,t,m,h): global times ,n ,passip if detect(ip,t,h) == True: passip.append(ip) print ('√ '+ip) else: if m == False: print ('x '+ip) times += 1 if times == n : global output print ('√ finish ' + '本次扫描了'+ str(times) +'个ip,'+'SNI_IP有'+ str(len(passip)) +'个。') if output == 'replace': name = time.strftime('%Y-%m-%d-%H-%M-%S',time.localtime(time.time())) output = 'PassIp '+ name +'.txt' f = open (output,'w') try: for v in passip: f.writelines(v+'\n') finally: f.close() print('bye,文件已写出到'+output+',按Enter退出。') input()
def button2(): choice = usb_or_ip() if choice == "B": video = "http://" + get_ip() + "/video?dummy=param.mjpg" capture1 = cv.VideoCapture(video) success1, frame1 = capture1.read() cv.imwrite(tempimagepath_cam, frame1) cv.imwrite(tempimagepath_detect, frame1[85:450, 200:480]) else: success, frame = capture.read() ref, frame = capture.read() cv.imwrite(tempimagepath_detect, frame[85:450, 200:480]) cv.imwrite(tempimagepath_cam, frame) parser = argparse.ArgumentParser() parser.add_argument('--cfg', type=str, default='data/train/yolov3.cfg', help='cfg file path') parser.add_argument('--data', type=str, default='cz.data', help='coco.data file path') parser.add_argument('--weights', type=str, default='data/yolov3_10000.weights', help='path to weights file') parser.add_argument('--images', type=str, default='data/samples', help='path to images') parser.add_argument('--img-size', type=int, default=416, help='inference size (pixels)') parser.add_argument('--conf-thres', type=float, default=0.5, help='object confidence threshold') parser.add_argument('--nms-thres', type=float, default=0.5, help='iou threshold for non-maximum suppression') parser.add_argument( '--fourcc', type=str, default='mp4v', help='fourcc output video codec (verify ffmpeg support)') parser.add_argument('--output', type=str, default='output', help='specifies the output path for images and videos') opt = parser.parse_args() with torch.no_grad(): label = detect(opt.cfg, opt.data, opt.weights, images=opt.images, img_size=opt.img_size, conf_thres=opt.conf_thres, nms_thres=opt.nms_thres, fourcc=opt.fourcc, output=opt.output)
def main(): d=detect(inputFolder='../data/pilgrim/',outputFolder='../output/pilgrim/') print('Loading books and splitting') text=d.loadNew() books=d.loadCandidates() textChunks=d.splitChunks(text) print('Filtering using Jaccard') reducedBooks=d.filterWithJacard(textChunks,books,threshold=0.25) pickling_on = open('../output/'+'pilgrim/reducedBooks.pickle',"wb") pickle.dump(reducedBooks, pickling_on) # print('Text: ',len(text)) # print('original is',len(books['isaiah'])) # print('reduced isaiah',len(reducedBooks['isaiah'])) # print('textChunks: ',len(textChunks)) print('Syntactic parsing') parseTrees,parsedSentences,parseWithoutTokenTrees=d.parseNewBook(textChunks) pickling_on = open('../output/'+'pilgrim/parseTrees.pickle',"wb") pickle.dump(parseTrees, pickling_on) # print('Parse trees',len(parseTrees)) potentialParseTrees,potentialParsedSentences,potentialParseWithoutTokenTrees=d.parseCandidates(reducedBooks) # print(len(parseTrees)) # print(len(parseTrees['isaiah'])) pickling_on = open('../output/'+'pilgrim/potentialParseTrees.pickle',"wb") pickle.dump(potentialParseTrees, pickling_on) # print('Potential Parse Trees isaiah ',len(potentialParseTrees['isaiah'])) print('Moschitti scoring') syntacticScore,syntacticScoreWithoutTokens=d.syntacticScoring(parseTrees,potentialParseTrees,parseWithoutTokenTrees,potentialParseWithoutTokenTrees) pickling_on = open('../output/'+'pilgrim/allScores.pickle',"wb") pickle.dump(syntacticScore, pickling_on) pickling_on = open('../output/'+'pilgrim/allScores2.pickle',"wb") pickle.dump(syntacticScoreWithoutTokens, pickling_on) print('Semantic scoring') semanticScore=d.semanticScoring(text,reducedBooks) # print('Semantic Score: ',len(semanticScore)) print('Extracting longest subsequence') lcsScore,lcs=d.longestSubsequenceScoring(text,reducedBooks) print('Average scoring') scoreTuples=d.aggregateScoring(syntacticScore,semanticScore,lcsScore,lcs,syntacticScoreWithoutTokens) # print(len(scoreTuples)) pickling_on = open('../output/'+'pilgrim/scoreTuples.pickle',"wb") pickle.dump(scoreTuples, pickling_on) finalTuples,diffTuples=d.finalFiltering(scoreTuples,reducedBooks,0.80) if len(finalTuples)>100: finalTuples=finalTuples[0:100] orderedTuples=d.nounBasedRanking(finalTuples,text,reducedBooks) pickling_on = open('../output/'+'pilgrim/orderedTuples.pickle',"wb") pickle.dump(orderedTuples, pickling_on) print('Final results: \n\n\n') i=1 for t in orderedTuples: print('Pairing: ',i) print('\n') print('New Sentence: ',text[t[0]]) print('\n') print('Reference: \n',reducedBooks[t[1]][t[2]]) print('\n') print('Similar Sentence is from: ',t[1]) print('Syntactic Score: ',t[3]) print('Syntactic Similarity without tokens: ',t[11]) print('Semantic Score: ',t[4]) print('Semantic Score without stopwords: ',t[5]) print('LCS Length: ',t[9]) print('LCS: ',t[10]) print('Jaccard of common nouns: ',t[12]) print('Jaccard of common verbs: ',t[13]) print('Jaccard of common adjectives: ',t[14]) print('Semantic similarity nouns: ',t[6]) print('Semantic similarity verbs: ',t[7]) print('\n\n') i=i+1 d.writeOutput(orderedTuples,text,reducedBooks) print('\n\n Tuples with large difference in syntactic and semantic value: \n\n\n') diffTuples=d.nounBasedRanking(diffTuples,text,reducedBooks) pickling_on = open('../output/'+'pilgrim/diffTuples.pickle',"wb") pickle.dump(diffTuples, pickling_on)
def main(args): #create the main function with input args if (args.test_text): #if input is test, just run test print(args.test_text) detect(args.test_location, args.output_location ) #runs detect program with input and output locations
def job(): camera.capture(IMG_PATH) detect(load_model, infer, 416, IMG_PATH) os.remove(IMG_PATH)
track_flag = False avg_pos = 0. candidates = [] vs = PiVideoStream((win_w, win_h), 64).start() time.sleep(2.0) start_time = time.time() monitor_start_time = 0. while (True): img = vs.read() # cv2.imshow("Raw", img) # img = preprocess(img) # cv2.imshow("Preprocessed", img) rects, img = detect(img, scale_factor, min_neighs, obj_w, obj_h) img = box(rects, img) # cv2.imshow("Cascaded", img) measure(img, rects, candidates) # if there's no rects found, look around # if not rects: # look_around() # Check time elapsed, if over 10 sec, invoke spiral search # if (time.time()-start) > 10: # spiral_search() #if (time.time()-start_time >.1): if True: # if time.time() - start_time > 5: if candidates: avg_pos = mean(candidates)
# move above the target val = 'MOVP ' + str(p_hat[0]) + ' ' + str( p_hat[1]) + ' 0 ' + str(-p_angle[i]) + ' 0 180\n' checkPoint(val) s.sendall(val.encode('ascii')) # move down to reach the target val = 'MOVP ' + str(p_hat[0]) + ' ' + str( p_hat[1]) + ' -190 ' + str(-p_angle[i]) + ' 0 180\n' checkPoint(val) s.sendall(val.encode('ascii')) # close the gripper s.sendall(close_grip.encode('ascii')) face, grabbing, SN = detect(i, s, actual_length_box[i]) inter_pose_register[i] = SN object_size = GetSizeBySN(SN) xs.append(object_size[0]) ys.append(object_size[1]) zs.append(object_size[2]) print("face: {} grabbing {}".format(face, grabbing)) if SN not in [18, 19, 10, 11]: traceRoute(s, i, SN, face, grabbing) # ========================================== # ReCalibrating the centroid of object # with the manipulator val = 'MOVP ' + str(p_hat[0]) + ' ' + str( p_hat[1]) + ' 0 ' + '90 0 180\n' checkPoint(val)
split('.')[0] + '.png') image_d = os.path.join(args['output'], 'detect' + image.split(os.sep)[-1].\ split('.')[0] + '.png') img = cv2.imread(image_e) img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB) img = removeText(img, args['svm']) # Save remove-text-image cv2.imwrite(image_p, cv2.cvtColor(img, cv2.COLOR_RGB2BGR)) # detect alrotirhem only works with gary scale image. img_GRAY = cv2.cvtColor(img, cv2.COLOR_RGB2GRAY) # Get bounding boxes pairs = detect(img_GRAY) # Using matplot library to display image and detected copy # and paste area. if args['display']: fig, ax = plt.subplots(ncols=1, nrows=1, figsize=(6, 6)) ax.imshow(img) # Draw rectangles in image. for pair_list in pairs: for pair in pair_list: # random.random will generate a number between 0 and 1. color = (random.random(), random.random(), random.random()) for x, y, w, h in pair:
# ratings, usermap = load_itunes(USE_PRODUCTS) breakpoint() data = pd.read_csv('./data/amazon/amazon_network.csv') gmm_analysis(data) dataname = 'amazon' ratings, usermap = load_flipkart(USE_PRODUCTS) (rating_arr, iat_arr, ids) = process_data(ratings, dataname, USE_PRODUCTS) (rating_arr, iat_arr) = (np.array(rating_arr), np.array(iat_arr)) # pickle.dump((rating_arr, iat_arr, ids), open('../data/%s/%s_bucketed.pickle' % (dataname, keyword), 'wb')) # (rating_arr, iat_arr, ids) = pickle.load(open('../data/%s/%s_bucketed.pickle' % (dataname, keyword), 'rb')) (rating_arr, iat_arr) = (rating_arr[0:5000], iat_arr[0:5000]) # Detect suspicious users given matrices containing ratings and inter-arrival times. USE_TIMES is a boolean for whether the inter-arrival times should be used. The last parameter is the number of clusters to use. suspn = detect(rating_arr, iat_arr, USE_TIMES, 2) # OUTPUT RESULTS TO FILE: it considers the top (NUM_TO_OUTPUT) most suspicious users and stores their user ids, scores, ratings and IATs in separate files. NUM_TO_OUTPUT = 500 # number of suspicious users to output to file susp_sorted = np.array([ (x[0]) for x in sorted(enumerate(suspn), key=itemgetter(1), reverse=True) ]) most_susp = susp_sorted[range(1000)] with open('./output/%s/top%d%s_ids.txt' % (dataname, NUM_TO_OUTPUT, keyword), 'w') as outfile: with open( './output/%s/top%d%s_scores.txt' % (dataname, NUM_TO_OUTPUT, keyword), 'w') as out_scores: with open( './output/%s/top%d%s_ratings.txt' % (dataname, NUM_TO_OUTPUT, keyword), 'w') as out_rating:
import cv2 from detect import * class eyes(): def __init__(self, img1): self.img1 = img1 self.main = main def eye(self): image = cv2.imread(self.img1) ey = cv2.CascadeClassifier('classifiers/haarcascade_eye.xml') imgray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY) faces = ey.detectMultiScale(imgray, 1.3, 5) for (ex, ey, ew, eh) in faces: eye_image = cv2.rectangle(image, (ex, ey), (ex + ew, ey + eh), (255, 0, 0), 2) return eye_image if __name__ == "__main__": e = eyes(detect('vasanth.jpg').detectface()) cv2.imshow('image', e.eye()) cv2.waitKey(0) cv2.destryAllwindows()
def main(): # Creating an object to detect sentence level allusions d=detect(inputFolder='../data/n1-lim/',outputFolder='../output/n1-lim-sent/',cores=30,language='de') # loading the data print('Loading books and splitting') text=d.loadNew() books=d.loadCandidates() textChunks=d.splitChunks(text) # d.extendStopwords(text) # processing using spacy print('spacy') spacyTextChunks,spacyBooks,spacyText=d.spacyExtract(textChunks,books) # filtering using jaccard print('Filtering using Jaccard') reducedSpacyBooks,reducedSentences=d.filterWithJacard(spacyTextChunks,spacyBooks,threshold=0.05) #filtering the spacy data structure reducedBooks=d.filterOriginalBooks(reducedSentences,books) #filtering the original data structure pickling_on = open('../output/'+'n1-lim-sent/reducedBooks.pickle',"wb") pickle.dump(reducedBooks, pickling_on) # Syntactic parsing of the new text print('Syntactic parsing') parseTrees,parsedSentences,parseWithoutTokenTrees=d.parseNewBook(textChunks) pickling_on = open('../output/'+'n1-lim-sent/parseTrees.pickle',"wb") pickle.dump(parseTrees, pickling_on) # Syntactic parsing of the potential candidates potentialParseTrees,potentialParsedSentences,potentialParseWithoutTokenTrees=d.parseCandidates(reducedBooks) pickling_on = open('../output/'+'n1-lim-sent/potentialParseTrees.pickle',"wb") pickle.dump(potentialParseTrees, pickling_on) # Syntactic scoring using the moschitti score print('Moschitti scorings') syntacticScore,syntacticScoreWithoutTokens=d.syntacticScoring(parseTrees,potentialParseTrees,parseWithoutTokenTrees,potentialParseWithoutTokenTrees) pickling_on = open('../output/'+'n1-lim-sent/allScores.pickle',"wb") pickle.dump(syntacticScore, pickling_on) # Semantic scoring using word2vec print('Semantic scoring') semanticScore=d.semanticScoring(spacyText,reducedSpacyBooks,monolingual=True,lang1='english',lang2='english') # Extracting the longest common subsequence print('Extracting longest subsequence') lcsScore,lcs=d.longestSubsequenceScoring(text,reducedBooks) # Aggregating the syntactic and semantic scores print('Average scoring') scoreTuples=d.aggregateScoring(syntacticScore,semanticScore,lcsScore,lcs,syntacticScoreWithoutTokens) pickling_on = open('../output/'+'n1-lim-sent/scoreTuples.pickle',"wb") pickle.dump(scoreTuples, pickling_on) # Extracting a limited number of sentence pairs finalTuples,diffTuples=d.finalFiltering(scoreTuples,reducedBooks,0.79) if len(finalTuples)>100: finalTuples=finalTuples[0:100] # Sorting the extracted tuples using Noun based ranking orderedTuples=d.nounBasedRanking(finalTuples,spacyText,reducedSpacyBooks) pickling_on = open('../output/'+'n1-lim-sent/orderedTuples.pickle',"wb") pickle.dump(orderedTuples, pickling_on) # Printing final results on the terminal print('Final results: \n\n\n') i=1 for t in orderedTuples: print('Pairing: ',i) print('\n') print('New Sentence: ',text[t[0]]) print('\n') print('Reference: \n',reducedBooks[t[1]][t[2]]) print('\n') print('Similar Sentence is from: ',t[1]) print('Syntactic Score: ',t[3]) print('Syntactic Similarity without tokens: ',t[11]) print('Semantic Score: ',t[4]) print('Semantic Score without stopwords: ',t[5]) print('LCS Length: ',t[9]) print('LCS: ',t[10]) print('Jaccard of common nouns: ',t[13]) print('Jaccard of common verbs: ',t[14]) print('Jaccard of common adjectives: ',t[15]) print('Semantic similarity nouns: ',t[6]) print('Semantic similarity verbs: ',t[7]) print('\n\n') i=i+1 # Writing the output into a file d.writeOutput(orderedTuples,text,reducedBooks) # Sorting the tuples which had high differences diffTuples=d.nounBasedRanking(diffTuples,spacyText,reducedSpacyBooks) pickling_on = open('../output/'+'n1-lim-sent/diffTuples.pickle',"wb") pickle.dump(diffTuples, pickling_on)