CabConModding
Facebook
Twitter
youtube
Discord
Contact us
RSS
Menu
CabConModding
Home
New
Top
Premium
Rules
FAQ - Frequently Asked Questions
Games
Fornite
Call of Duty: Black Ops 3
Clash of Clans
Grand Theft Auto 5
Apex Legends
Assassin’s Creed Origins
Forums
Premium
Latest posts
What's new
Latest posts
New profile posts
Latest activity
Members
Current visitors
New profile posts
Log in
Register
What's new
Premium
Latest posts
Menu
Log in
Register
Navigation
Install the app
Install
More options
Dark Theme
Contact us
Close Menu
Join the Fortnite Facebook Group!
Join our facebook group now and discuss, request and browse the latest Fortnite Accounts, Hacks, Mods and Cheats
Forums
Gaming
Fortnite
Fortnite Cheats, Hacks and Mods
Neural Network Python hack need assistance
JavaScript is disabled. For a better experience, please enable JavaScript in your browser before proceeding.
You are using an out of date browser. It may not display this or other websites correctly.
You should upgrade or use an
alternative browser
.
Reply to thread
Message
<blockquote data-quote="tel1014" data-source="post: 36722" data-attributes="member: 217129"><p> <ol> <li data-xf-list-type="ol">So this was on another site and I was trying to set this up. The OP said that the aimbot kept locking onto his character and he couldnt fix it. I decided to just remove the aimbot all together and only use the glow and i was in the middle of installing everything when i realized that 1. import cv2 is a library which is exclusive to python 2.7 and 2. the code is in python 2.7 format(you can tell by the fact that there is no parenthesis around the variables). Now i would just go and install tensorflow, however tensorflow is no longer supported for python 2.7 and is only python 3.5 and 3.6. If anyone can either find a version of tensorflow for python 2.7, or cv2 for python 3.5(in which case i will revise the code to be updated to python 3) then this will be a undetectable cheat as all it does is record the frame screens and find people</li> </ol><p>also this is not 100% accurate so any improvements to the code will be extremely helpful.</p><p>Happy hacking!</p><ol> <li data-xf-list-type="ol"><strong># USAGE</strong></li> <li data-xf-list-type="ol"><strong># python real_time_object_detection.py --prototxt MobileNetSSD_deploy.prototxt.txt --model MobileNetSSD_deploy.caffemodel</strong></li> <li data-xf-list-type="ol"><strong># import the necessary packages</strong></li> <li data-xf-list-type="ol"><strong>import win32api</strong></li> <li data-xf-list-type="ol"><strong>import keyboard as keyboard</strong></li> <li data-xf-list-type="ol"><strong>import pygame as pygame</strong></li> <li data-xf-list-type="ol"><strong>import pythoncom</strong></li> <li data-xf-list-type="ol"><strong>import win32con</strong></li> <li data-xf-list-type="ol"><strong>from PIL import ImageGrab</strong></li> <li data-xf-list-type="ol"><strong>from imutils.video import VideoStream</strong></li> <li data-xf-list-type="ol"><strong>from imutils.video import FPS</strong></li> <li data-xf-list-type="ol"><strong>import numpy as np</strong></li> <li data-xf-list-type="ol"><strong>import argparse</strong></li> <li data-xf-list-type="ol"><strong>import imutils</strong></li> <li data-xf-list-type="ol"><strong>import time</strong></li> <li data-xf-list-type="ol"><strong>import cv2</strong></li> <li data-xf-list-type="ol"><strong>import pyautogui</strong></li> <li data-xf-list-type="ol"><strong># construct the argument parse and parse the arguments</strong></li> <li data-xf-list-type="ol"><strong>from keyboard._mouse_event import RIGHT</strong></li> <li data-xf-list-type="ol"><strong>ap = argparse.ArgumentParser()</strong></li> <li data-xf-list-type="ol"><strong>ap.add_argument("-p", "--prototxt", required=False,</strong></li> <li data-xf-list-type="ol"><strong> help="path to Caffe 'deploy' prototxt file")</strong></li> <li data-xf-list-type="ol"><strong>ap.add_argument("-m", "--model", required=False,</strong></li> <li data-xf-list-type="ol"><strong> help="path to Caffe pre-trained model")</strong></li> <li data-xf-list-type="ol"><strong>ap.add_argument("-c", "--confidence", type=float, default=0.6,</strong></li> <li data-xf-list-type="ol"><strong> help="minimum probability to filter weak detections")</strong></li> <li data-xf-list-type="ol"><strong>args = vars(ap.parse_args())</strong></li> <li data-xf-list-type="ol"><strong>prott1 = 'C:\Users\Saehi\PycharmProjects/testing\MobileNetSSD_deploy.prototxt.txt'</strong></li> <li data-xf-list-type="ol"><strong>prott2 = 'C:\Users\Saehi\PycharmProjects/testing\MobileNetSSD_deploy.caffemodel'</strong></li> <li data-xf-list-type="ol"><strong># initialize the list of class labels MobileNet SSD was trained to</strong></li> <li data-xf-list-type="ol"><strong># detect, then generate a set of bounding box colors for each class</strong></li> <li data-xf-list-type="ol"><strong>CLASSES = ["background", "aeroplane", "bicycle", "bird", "boat",</strong></li> <li data-xf-list-type="ol"><strong> "bottle", "bus", "car", "cat", "chair", "cow", "diningtable",</strong></li> <li data-xf-list-type="ol"><strong> "dog", "horse", "motorbike", "person", "pottedplant", "sheep",</strong></li> <li data-xf-list-type="ol"><strong> "sofa", "train", "tvmonitor"]</strong></li> <li data-xf-list-type="ol"><strong>COLORS = np.random.uniform(0, 255, size=(len(CLASSES), 3))</strong></li> <li data-xf-list-type="ol"><strong># load our serialized model from disk</strong></li> <li data-xf-list-type="ol"><strong>print("[INFO] loading model...")</strong></li> <li data-xf-list-type="ol"><strong>net = cv2.dnn.readNetFromCaffe(prott1, prott2)</strong></li> <li data-xf-list-type="ol"><strong># initialize the video stream, allow the cammera sensor to warmup,</strong></li> <li data-xf-list-type="ol"><strong># and initialize the FPS counter</strong></li> <li data-xf-list-type="ol"><strong>print("[INFO] starting video stream...")</strong></li> <li data-xf-list-type="ol"><strong>#vs = VideoStream(src=0).start()</strong></li> <li data-xf-list-type="ol"><strong>#time.sleep(2.0)</strong></li> <li data-xf-list-type="ol"><strong>#fps = FPS().start()</strong></li> <li data-xf-list-type="ol"><strong># loop over the frames from the video stream</strong></li> <li data-xf-list-type="ol"><strong>HSX = 100;</strong></li> <li data-xf-list-type="ol"><strong>LSX = 1000;</strong></li> <li data-xf-list-type="ol"><strong>HSY = 100;</strong></li> <li data-xf-list-type="ol"><strong>LSY = 1000;</strong></li> <li data-xf-list-type="ol"><strong>HEX = 100;</strong></li> <li data-xf-list-type="ol"><strong>LEX = 1000;</strong></li> <li data-xf-list-type="ol"><strong>HEY = 100;</strong></li> <li data-xf-list-type="ol"><strong>LEY = 1000;</strong></li> <li data-xf-list-type="ol"><strong>while True:</strong></li> <li data-xf-list-type="ol"><strong> # grab the frame from the threaded video stream and resize it</strong></li> <li data-xf-list-type="ol"><strong> # to have a maximum width of 400 pixels</strong></li> <li data-xf-list-type="ol"><strong> frame = np.array(ImageGrab.grab(bbox=(0, 40, 1820, 1240)))</strong></li> <li data-xf-list-type="ol"><strong> # frame = imutils.resize(frame, width=400)</strong></li> <li data-xf-list-type="ol"><strong> # grab the frame dimensions and convert it to a blob</strong></li> <li data-xf-list-type="ol"><strong> (h, w) = frame.shape[:2]</strong></li> <li data-xf-list-type="ol"><strong> blob = cv2.dnn.blobFromImage(cv2.resize(frame, (300, 300)),</strong></li> <li data-xf-list-type="ol"><strong> 0.007843, (300, 300), 127.5)</strong></li> <li data-xf-list-type="ol"><strong> # pass the blob through the network and obtain the detections and</strong></li> <li data-xf-list-type="ol"><strong> # predictions</strong></li> <li data-xf-list-type="ol"><strong> net.setInput(blob)</strong></li> <li data-xf-list-type="ol"><strong> detections = net.forward()</strong></li> <li data-xf-list-type="ol"><strong> # loop over the detections</strong></li> <li data-xf-list-type="ol"><strong> for i in np.arange(0, detections.shape[2]):</strong></li> <li data-xf-list-type="ol"><strong> # extract the confidence (i.e., probability) associated with</strong></li> <li data-xf-list-type="ol"><strong> # the prediction</strong></li> <li data-xf-list-type="ol"><strong> confidence = detections[0, 0, i, 2]</strong></li> <li data-xf-list-type="ol"><strong> # filter out weak detections by ensuring the `confidence` is</strong></li> <li data-xf-list-type="ol"><strong> # greater than the minimum confidence</strong></li> <li data-xf-list-type="ol"><strong> if confidence > args["confidence"]:</strong></li> <li data-xf-list-type="ol"><strong> # extract the index of the class label from the</strong></li> <li data-xf-list-type="ol"><strong> # `detections`, then compute the (x, y)-coordinates of</strong></li> <li data-xf-list-type="ol"><strong> # the bounding box for the object</strong></li> <li data-xf-list-type="ol"><strong> idx = int(detections[0, 0, i, 1])</strong></li> <li data-xf-list-type="ol"><strong> box = detections[0, 0, i, 3:7] * np.array([w, h, w, h])</strong></li> <li data-xf-list-type="ol"><strong> (startX, startY, endX, endY) = box.astype("int")</strong></li> <li data-xf-list-type="ol"><strong> # draw the prediction on the frame</strong></li> <li data-xf-list-type="ol"><strong> label = "{}: {:.2f}%".format(CLASSES[idx],</strong></li> <li data-xf-list-type="ol"><strong> confidence * 100)</strong></li> <li data-xf-list-type="ol"><strong> cv2.rectangle(frame, (startX, startY), (endX, endY),</strong></li> <li data-xf-list-type="ol"><strong> COLORS[idx], 2)</strong></li> <li data-xf-list-type="ol"><strong> y = startY - 15 if startY - 15 > 15 else startY + 15</strong></li> <li data-xf-list-type="ol"><strong> cv2.putText(frame, label, (startX, y),</strong></li> <li data-xf-list-type="ol"><strong> cv2.FONT_HERSHEY_SIMPLEX, 0.5, COLORS[idx], 2)</strong></li> <li data-xf-list-type="ol"><strong> if 'person' in label:</strong></li> <li data-xf-list-type="ol"><strong> pygame.init()</strong></li> <li data-xf-list-type="ol"><strong> pygame.event.get()</strong></li> <li data-xf-list-type="ol"><strong> if pygame.mouse.get_pressed():</strong></li> <li data-xf-list-type="ol"><strong> print 'pressing'</strong></li> <li data-xf-list-type="ol"><strong> #tried to detect my character's offset and add the best way to exclude it, failed most tests.</strong></li> <li data-xf-list-type="ol"><strong> if startX > 369 & startX < 1402 & startY > -1 & startY < 725 & endX > 339 & endX < 1805 & endY > 806 & endY < 1017:</strong></li> <li data-xf-list-type="ol"><strong> print 'found myself'</strong></li> <li data-xf-list-type="ol"><strong> else:</strong></li> <li data-xf-list-type="ol"><strong> #print 'found somebody else'</strong></li> <li data-xf-list-type="ol"><strong> nosum = int(round(startX * 1)) + int(round(startX * 0.06))</strong></li> <li data-xf-list-type="ol"><strong> nosum2 = int(round(y * 1)) + int(round(y * 0.7))</strong></li> <li data-xf-list-type="ol"><strong> halfX = (endX - startX) / 2</strong></li> <li data-xf-list-type="ol"><strong> halfY = (endY - startY) / 2</strong></li> <li data-xf-list-type="ol"><strong> finalX = startX + halfX</strong></li> <li data-xf-list-type="ol"><strong> finalY = startY + halfY</strong></li> <li data-xf-list-type="ol"><strong> pyautogui.moveTo(finalX, finalY)</strong></li> <li data-xf-list-type="ol"><strong> #win32api.SetCursorPos((finalX, finalY))</strong></li> <li data-xf-list-type="ol"><strong> win32api.mouse_event(win32con.MOUSEEVENTF_LEFTDOWN, finalX, finalY, 0, 0)</strong></li> <li data-xf-list-type="ol"><strong> win32api.mouse_event(win32con.MOUSEEVENTF_LEFTUP, finalX, finalY, 0, 0)</strong></li> <li data-xf-list-type="ol"><strong> #print 'Pressed L'</strong></li> <li data-xf-list-type="ol"><strong> if 'HSX' not in locals():</strong></li> <li data-xf-list-type="ol"><strong> HSX = startX</strong></li> <li data-xf-list-type="ol"><strong> if 'LSX' not in locals():</strong></li> <li data-xf-list-type="ol"><strong> LSX = startX</strong></li> <li data-xf-list-type="ol"><strong> if 'HSY' not in locals():</strong></li> <li data-xf-list-type="ol"><strong> HSY = startY</strong></li> <li data-xf-list-type="ol"><strong> if 'LSY' not in locals():</strong></li> <li data-xf-list-type="ol"><strong> LSY = startY</strong></li> <li data-xf-list-type="ol"><strong> if 'HEX' not in locals():</strong></li> <li data-xf-list-type="ol"><strong> HEX = endX</strong></li> <li data-xf-list-type="ol"><strong> if 'LEX' not in locals():</strong></li> <li data-xf-list-type="ol"><strong> LEX = endX</strong></li> <li data-xf-list-type="ol"><strong> if 'HEY' not in locals():</strong></li> <li data-xf-list-type="ol"><strong> HEY = endY</strong></li> <li data-xf-list-type="ol"><strong> if 'LEY' not in locals():</strong></li> <li data-xf-list-type="ol"><strong> LEY = endY</strong></li> <li data-xf-list-type="ol"><strong> if startX > HSX:</strong></li> <li data-xf-list-type="ol"><strong> HSX = startX</strong></li> <li data-xf-list-type="ol"><strong> if startX < LSX:</strong></li> <li data-xf-list-type="ol"><strong> LSX = startX</strong></li> <li data-xf-list-type="ol"><strong> if startY > HSY:</strong></li> <li data-xf-list-type="ol"><strong> HSY = startY</strong></li> <li data-xf-list-type="ol"><strong> if startY < LSY:</strong></li> <li data-xf-list-type="ol"><strong> LSY = startY</strong></li> <li data-xf-list-type="ol"><strong> if endX > HEX:</strong></li> <li data-xf-list-type="ol"><strong> HEX = endX</strong></li> <li data-xf-list-type="ol"><strong> if endX < LEX:</strong></li> <li data-xf-list-type="ol"><strong> LEX = endX</strong></li> <li data-xf-list-type="ol"><strong> if endY > HEY:</strong></li> <li data-xf-list-type="ol"><strong> HEY = endY</strong></li> <li data-xf-list-type="ol"><strong> if endY < LEY:</strong></li> <li data-xf-list-type="ol"><strong> LEY = endY</strong></li> <li data-xf-list-type="ol"><strong> print 'HStartX: ' + str(HSX)</strong></li> <li data-xf-list-type="ol"><strong> print 'LStartX: ' + str(LSX)</strong></li> <li data-xf-list-type="ol"><strong> print 'HStartY: ' + str(HSY)</strong></li> <li data-xf-list-type="ol"><strong> print 'LStartY: ' + str(LSY)</strong></li> <li data-xf-list-type="ol"><strong> print 'HendX: ' + str(HEX)</strong></li> <li data-xf-list-type="ol"><strong> print 'LendX: ' + str(LEX)</strong></li> <li data-xf-list-type="ol"><strong> print 'HendY: ' + str(HEY)</strong></li> <li data-xf-list-type="ol"><strong> print 'LendY: ' + str(LEY)</strong></li> <li data-xf-list-type="ol"><strong> #print args["confidence"]</strong></li> <li data-xf-list-type="ol"><strong># click(10,10)</strong></li> <li data-xf-list-type="ol"><strong> # show the output frame</strong></li> <li data-xf-list-type="ol"><strong> cv2.imshow("Frame", frame)</strong></li> <li data-xf-list-type="ol"><strong> key = cv2.waitKey(1) & 0xFF</strong></li> <li data-xf-list-type="ol"><strong> # if the `q` key was pressed, break from the loop</strong></li> <li data-xf-list-type="ol"><strong> if key == ord("q"):</strong></li> <li data-xf-list-type="ol"><strong> break</strong></li> <li data-xf-list-type="ol"><strong> # update the FPS counter</strong></li> <li data-xf-list-type="ol"><strong># stop the timer and display FPS information</strong></li> <li data-xf-list-type="ol"><strong># do a bit of cleanup</strong></li> <li data-xf-list-type="ol"><strong>cv2.destroyAllWindows()</strong></li> </ol></blockquote><p></p>
[QUOTE="tel1014, post: 36722, member: 217129"] [LIST=1] [*]So this was on another site and I was trying to set this up. The OP said that the aimbot kept locking onto his character and he couldnt fix it. I decided to just remove the aimbot all together and only use the glow and i was in the middle of installing everything when i realized that 1. import cv2 is a library which is exclusive to python 2.7 and 2. the code is in python 2.7 format(you can tell by the fact that there is no parenthesis around the variables). Now i would just go and install tensorflow, however tensorflow is no longer supported for python 2.7 and is only python 3.5 and 3.6. If anyone can either find a version of tensorflow for python 2.7, or cv2 for python 3.5(in which case i will revise the code to be updated to python 3) then this will be a undetectable cheat as all it does is record the frame screens and find people [/LIST] also this is not 100% accurate so any improvements to the code will be extremely helpful. Happy hacking! [LIST=1] [*][B][/B] [*][B][/B] [*][B][/B] [*][B][/B] [*][B][/B] [*][B]# USAGE[/B] [*][B]# python real_time_object_detection.py --prototxt MobileNetSSD_deploy.prototxt.txt --model MobileNetSSD_deploy.caffemodel[/B] [*][B]# import the necessary packages[/B] [*][B]import win32api[/B] [*][B]import keyboard as keyboard[/B] [*][B]import pygame as pygame[/B] [*][B]import pythoncom[/B] [*][B]import win32con[/B] [*][B]from PIL import ImageGrab[/B] [*][B]from imutils.video import VideoStream[/B] [*][B]from imutils.video import FPS[/B] [*][B]import numpy as np[/B] [*][B]import argparse[/B] [*][B]import imutils[/B] [*][B]import time[/B] [*][B]import cv2[/B] [*][B]import pyautogui[/B] [*][B]# construct the argument parse and parse the arguments[/B] [*][B]from keyboard._mouse_event import RIGHT[/B] [*][B]ap = argparse.ArgumentParser()[/B] [*][B]ap.add_argument("-p", "--prototxt", required=False,[/B] [*][B] help="path to Caffe 'deploy' prototxt file")[/B] [*][B]ap.add_argument("-m", "--model", required=False,[/B] [*][B] help="path to Caffe pre-trained model")[/B] [*][B]ap.add_argument("-c", "--confidence", type=float, default=0.6,[/B] [*][B] help="minimum probability to filter weak detections")[/B] [*][B]args = vars(ap.parse_args())[/B] [*][B]prott1 = 'C:\Users\Saehi\PycharmProjects/testing\MobileNetSSD_deploy.prototxt.txt'[/B] [*][B]prott2 = 'C:\Users\Saehi\PycharmProjects/testing\MobileNetSSD_deploy.caffemodel'[/B] [*][B]# initialize the list of class labels MobileNet SSD was trained to[/B] [*][B]# detect, then generate a set of bounding box colors for each class[/B] [*][B]CLASSES = ["background", "aeroplane", "bicycle", "bird", "boat",[/B] [*][B] "bottle", "bus", "car", "cat", "chair", "cow", "diningtable",[/B] [*][B] "dog", "horse", "motorbike", "person", "pottedplant", "sheep",[/B] [*][B] "sofa", "train", "tvmonitor"][/B] [*][B]COLORS = np.random.uniform(0, 255, size=(len(CLASSES), 3))[/B] [*][B]# load our serialized model from disk[/B] [*][B]print("[INFO] loading model...")[/B] [*][B]net = cv2.dnn.readNetFromCaffe(prott1, prott2)[/B] [*][B]# initialize the video stream, allow the cammera sensor to warmup,[/B] [*][B]# and initialize the FPS counter[/B] [*][B]print("[INFO] starting video stream...")[/B] [*][B]#vs = VideoStream(src=0).start()[/B] [*][B]#time.sleep(2.0)[/B] [*][B]#fps = FPS().start()[/B] [*][B]# loop over the frames from the video stream[/B] [*][B]HSX = 100;[/B] [*][B]LSX = 1000;[/B] [*][B]HSY = 100;[/B] [*][B]LSY = 1000;[/B] [*][B]HEX = 100;[/B] [*][B]LEX = 1000;[/B] [*][B]HEY = 100;[/B] [*][B]LEY = 1000;[/B] [*][B]while True:[/B] [*][B] # grab the frame from the threaded video stream and resize it[/B] [*][B] # to have a maximum width of 400 pixels[/B] [*][B] frame = np.array(ImageGrab.grab(bbox=(0, 40, 1820, 1240)))[/B] [*][B] # frame = imutils.resize(frame, width=400)[/B] [*][B] # grab the frame dimensions and convert it to a blob[/B] [*][B] (h, w) = frame.shape[:2][/B] [*][B] blob = cv2.dnn.blobFromImage(cv2.resize(frame, (300, 300)),[/B] [*][B] 0.007843, (300, 300), 127.5)[/B] [*][B] # pass the blob through the network and obtain the detections and[/B] [*][B] # predictions[/B] [*][B] net.setInput(blob)[/B] [*][B] detections = net.forward()[/B] [*][B] # loop over the detections[/B] [*][B] for i in np.arange(0, detections.shape[2]):[/B] [*][B] # extract the confidence (i.e., probability) associated with[/B] [*][B] # the prediction[/B] [*][B] confidence = detections[0, 0, i, 2][/B] [*][B] # filter out weak detections by ensuring the `confidence` is[/B] [*][B] # greater than the minimum confidence[/B] [*][B] if confidence > args["confidence"]:[/B] [*][B] # extract the index of the class label from the[/B] [*][B] # `detections`, then compute the (x, y)-coordinates of[/B] [*][B] # the bounding box for the object[/B] [*][B] idx = int(detections[0, 0, i, 1])[/B] [*][B] box = detections[0, 0, i, 3:7] * np.array([w, h, w, h])[/B] [*][B] (startX, startY, endX, endY) = box.astype("int")[/B] [*][B] # draw the prediction on the frame[/B] [*][B] label = "{}: {:.2f}%".format(CLASSES[idx],[/B] [*][B] confidence * 100)[/B] [*][B] cv2.rectangle(frame, (startX, startY), (endX, endY),[/B] [*][B] COLORS[idx], 2)[/B] [*][B] y = startY - 15 if startY - 15 > 15 else startY + 15[/B] [*][B] cv2.putText(frame, label, (startX, y),[/B] [*][B] cv2.FONT_HERSHEY_SIMPLEX, 0.5, COLORS[idx], 2)[/B] [*][B] if 'person' in label:[/B] [*][B] pygame.init()[/B] [*][B] pygame.event.get()[/B] [*][B] if pygame.mouse.get_pressed():[/B] [*][B] print 'pressing'[/B] [*][B] #tried to detect my character's offset and add the best way to exclude it, failed most tests.[/B] [*][B] if startX > 369 & startX < 1402 & startY > -1 & startY < 725 & endX > 339 & endX < 1805 & endY > 806 & endY < 1017:[/B] [*][B] print 'found myself'[/B] [*][B] else:[/B] [*][B] #print 'found somebody else'[/B] [*][B] nosum = int(round(startX * 1)) + int(round(startX * 0.06))[/B] [*][B] nosum2 = int(round(y * 1)) + int(round(y * 0.7))[/B] [*][B] halfX = (endX - startX) / 2[/B] [*][B] halfY = (endY - startY) / 2[/B] [*][B] finalX = startX + halfX[/B] [*][B] finalY = startY + halfY[/B] [*][B] pyautogui.moveTo(finalX, finalY)[/B] [*][B] #win32api.SetCursorPos((finalX, finalY))[/B] [*][B] win32api.mouse_event(win32con.MOUSEEVENTF_LEFTDOWN, finalX, finalY, 0, 0)[/B] [*][B] win32api.mouse_event(win32con.MOUSEEVENTF_LEFTUP, finalX, finalY, 0, 0)[/B] [*][B] #print 'Pressed L'[/B] [*][B] if 'HSX' not in locals():[/B] [*][B] HSX = startX[/B] [*][B] if 'LSX' not in locals():[/B] [*][B] LSX = startX[/B] [*][B] if 'HSY' not in locals():[/B] [*][B] HSY = startY[/B] [*][B] if 'LSY' not in locals():[/B] [*][B] LSY = startY[/B] [*][B] if 'HEX' not in locals():[/B] [*][B] HEX = endX[/B] [*][B] if 'LEX' not in locals():[/B] [*][B] LEX = endX[/B] [*][B] if 'HEY' not in locals():[/B] [*][B] HEY = endY[/B] [*][B] if 'LEY' not in locals():[/B] [*][B] LEY = endY[/B] [*][B] if startX > HSX:[/B] [*][B] HSX = startX[/B] [*][B] if startX < LSX:[/B] [*][B] LSX = startX[/B] [*][B] if startY > HSY:[/B] [*][B] HSY = startY[/B] [*][B] if startY < LSY:[/B] [*][B] LSY = startY[/B] [*][B] if endX > HEX:[/B] [*][B] HEX = endX[/B] [*][B] if endX < LEX:[/B] [*][B] LEX = endX[/B] [*][B] if endY > HEY:[/B] [*][B] HEY = endY[/B] [*][B] if endY < LEY:[/B] [*][B] LEY = endY[/B] [*][B] print 'HStartX: ' + str(HSX)[/B] [*][B] print 'LStartX: ' + str(LSX)[/B] [*][B] print 'HStartY: ' + str(HSY)[/B] [*][B] print 'LStartY: ' + str(LSY)[/B] [*][B] print 'HendX: ' + str(HEX)[/B] [*][B] print 'LendX: ' + str(LEX)[/B] [*][B] print 'HendY: ' + str(HEY)[/B] [*][B] print 'LendY: ' + str(LEY)[/B] [*][B] #print args["confidence"][/B] [*][B]# click(10,10)[/B] [*][B] # show the output frame[/B] [*][B] cv2.imshow("Frame", frame)[/B] [*][B] key = cv2.waitKey(1) & 0xFF[/B] [*][B] # if the `q` key was pressed, break from the loop[/B] [*][B] if key == ord("q"):[/B] [*][B] break[/B] [*][B] # update the FPS counter[/B] [*][B]# stop the timer and display FPS information[/B] [*][B]# do a bit of cleanup[/B] [*][B]cv2.destroyAllWindows()[/B] [/LIST] [/QUOTE]
Verification
Post reply
Forums
Gaming
Fortnite
Fortnite Cheats, Hacks and Mods
Neural Network Python hack need assistance
CabConModding is now on facebook! Check the latest Updates, the Site Status and much more now!
This site uses cookies to help personalise content, tailor your experience and to keep you logged in if you register.
By continuing to use this site, you are consenting to our use of cookies.
Accept
Learn more…
Top