import numpy as np from termcolor import colored import timeit import threading # thread…
- User
import numpy as np from termcolor import colored import timeit import threading # thread -> threading import imutils import time import mss import cv2 import os import signal import sys import pynput import ctypes import pyautogui from lib.grab import grab_screen
import win32gui import win32api import win32con import mouse import keyboard
sct = mss.mss() Wd, Hd = sct.monitors[1]["width"], sct.monitors[1]["height"] SendInput = ctypes.windll.user32.SendInput PUL = ctypes.POINTER(ctypes.c_ulong)
class KeyBdInput(ctypes.Structure): fields = [("wVk", ctypes.c_ushort), ("wScan", ctypes.c_ushort), ("dwFlags", ctypes.c_ulong), ("time", ctypes.c_ulong), ("dwExtraInfo", PUL)] class HardwareInput(ctypes.Structure): fields = [("uMsg", ctypes.c_ulong), ("wParamL", ctypes.c_short), ("wParamH", ctypes.c_ushort)] class MouseInput(ctypes.Structure): fields = [("dx", ctypes.c_long), ("dy", ctypes.c_long), ("mouseData", ctypes.c_ulong), ("dwFlags", ctypes.c_ulong), ("time", ctypes.c_ulong), ("dwExtraInfo", PUL)] class Input_I(ctypes.Union): fields = [("ki", KeyBdInput), ("mi", MouseInput), ("hi", HardwareInput)] class Input(ctypes.Structure): fields = [("type", ctypes.c_ulong), ("ii", Input_I)]
def set_pos(x, y): if mouse.is_pressed(button='left') or keyboard.is_pressed('alt'): x = int(x - (Wd / 2)) y = int(y - (Hd / 2))
extra = ctypes.c_ulong(0) ii = pynput._util.win32.INPUT_union() ii.mi = pynput._util.win32.MOUSEINPUT(x, y, 0, (0x0001 | 0x8000), 0, ctypes.cast(ctypes.pointer(extra), ctypes.c_void_p)) command = pynput._util.win32.INPUT(ctypes.c_ulong(0), ii) SendInput(1, ctypes.pointer(command), ctypes.sizeof(command))if name == "main": print("Do not run this file directly.")
def start(ENABLE_AIMBOT):
# Config #YOLO_DIRECTORY = "models" #CONFIDENCE = 0.20 #Reduzir CONFIDENCE permitirá que o modelo detecte mais objetos, mas pode aumentar os falsos positivos: #THRESHOLD = 0.01 #THRESHOLD = 0.22 Estava usando esete antes de 0.01 # Config YOLO_DIRECTORY = "models" CONFIDENCE = 0.25 #Reduzir CONFIDENCE permitirá que o modelo detecte mais objetos, mas pode aumentar os falsos positivos: THRESHOLD = 0.05 #THRESHOLD = 0.22 Estava usando esete antes de 0.01 # # Size (in pixels) of the screen capture box to feed the neural net. # This box is in the center of your screen. Lower value makes the network faster. # # Example: "ACTIVATION_RANGE = 400" means a 400x400 pixel box. # ACTIVATION_RANGE = 200 # load the COCO class labels our YOLO model was trained on labelsPath = os.path.sep.join([YOLO_DIRECTORY, "obj.names"]) LABELS = open(labelsPath).read().strip().split("\n") # initialize a list of colors to represent each possible class label np.random.seed(42) COLORS = np.random.randint(0, 255, size=(len(LABELS), 3), dtype="uint8") # derive the paths to the YOLO weights and model configuration weightsPath = os.path.sep.join([YOLO_DIRECTORY, "PESOCNN/yolov4.weights"]) configPath = os.path.sep.join([YOLO_DIRECTORY, "PESOCNN/yolov4.cfg"]) # Wait for buffering time.sleep(0.4) # load our YOLO object detector trained on COCO dataset (80 classes) # and determine only the output layer names that we need from YOLO print("[INFO] loading neural-network from disk…") net = cv2.dnn.readNetFromDarknet(configPath, weightsPath) # Check if GPU is available and use it if cv2.cuda.getCudaEnabledDeviceCount() > 0: print(colored("[OKAY] CUDA GPU Detected!", "green")) net.setPreferableBackend(cv2.dnn.DNN_BACKEND_CUDA) net.setPreferableTarget(cv2.dnn.DNN_TARGET_CUDA) elif cv2.ocl.haveOpenCL(): print(colored("[OKAY] OpenCL GPU Detected!", "green")) net.setPreferableBackend(cv2.dnn.DNN_BACKEND_DEFAULT) net.setPreferableTarget(cv2.dnn.DNN_TARGET_OPENCL) else: print(colored("[WARNING] No GPU detected, using CPU.", "yellow")) net.setPreferableBackend(cv2.dnn.DNN_BACKEND_DEFAULT) net.setPreferableTarget(cv2.dnn.DNN_TARGET_CPU) ln = net.getLayerNames() ln = [ln[i - 1] for i in net.getUnconnectedOutLayers()] # Define screen capture area print("[INFO] loading screencapture device…") W, H = None, None origbox = (int(Wd/2 - ACTIVATION_RANGE/2), int(Hd/2 - ACTIVATION_RANGE/2), int(Wd/2 + ACTIVATION_RANGE/2), int(Hd/2 + ACTIVATION_RANGE/2)) # Log whether aimbot is enabled if not ENABLE_AIMBOT: print("[INFO] aimbot disabled, using visualizer only…") else: print(colored("[OKAY] Aimbot enabled!", "green")) # Handle Ctrl+C in terminal, release pointers def signal_handler(sig, frame): # release the file pointers print("\n[INFO] cleaning up…") sct.close() # .exit() does not exist for mss.mss() cv2.destroyAllWindows() sys.exit(0) signal.signal(signal.SIGINT, signal_handler) print() # loop over frames from the video file stream while True: start_time = timeit.default_timer() frame = np.array(grab_screen(region=origbox)) frame = cv2.cvtColor(frame, cv2.COLOR_RGBA2BGR) # if the frame dimensions are empty, grab them if W is None or H is None: (H, W) = frame.shape[: 2] frame = cv2.UMat(frame) # construct a blob from the input frame and then perform a forward # pass of the YOLO object detector, giving us our bounding boxes # and associated probabilities blob = cv2.dnn.blobFromImage(frame, 1/260, (150, 150), swapRB=True, crop=True) net.setInput(blob) layerOutputs = net.forward(ln) # initialize our lists of detected bounding boxes, confidences, # and class IDs, respectively boxes = [] confidences = [] classIDs = [] # loop over each of the layer outputs for output in layerOutputs: # loop over each of the detections for detection in output: # extract the class ID and confidence (i.e., probability) # of the current object detection scores = detection[5:] classID = 0 # person = 0 confidence = scores[classID] # filter out weak predictions by ensuring the detected # probability is greater than the minimum probability if confidence > CONFIDENCE: box = detection[0: 4] * np.array([W, H, W, H]) (centerX, centerY, width, height) = box.astype("int") # use the center (x, y)-coordinates to derive the top # and and left corner of the bounding box x = int(centerX - (width / 2)) y = int(centerY - (height / 2)) # update our list of bounding box coordinates, # confidences, and class IDs boxes.append([x, y, int(width), int(height)]) confidences.append(float(confidence)) classIDs.append(classID) # apply non-maxima suppression to suppress weak, overlapping # bounding boxes idxs = cv2.dnn.NMSBoxes(boxes, confidences, CONFIDENCE, THRESHOLD) # ensure at least one detection exists if len(idxs) > 0: # Find best player match bestMatch = confidences[np.argmax(confidences)] # loop over the indexes we are keeping for i in idxs.flatten(): # extract the bounding box coordinates (x, y) = (boxes[i][0], boxes[i][1]) (w, h) = (boxes[i][2], boxes[i][3]) # draw target dot on the frame cv2.circle(frame, (int(x + w / 2), int(y + h / 3)), 2, (0, 0, 255), -1) # draw a bounding box rectangle and label on the frame cv2.rectangle(frame, (x, y), (x + w, y + h), (0, 255, 0), 1) text = "enemy {}%".format(int(confidences[i] * 100)) cv2.putText(frame, text, (x, y - 5), cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 255, 0), 2) if ENABLE_AIMBOT and bestMatch == confidences[i]: mouseX = origbox[0] + (x + w/1.55) mouseY = origbox[1] + (y + h/2.50) set_pos(mouseX, mouseY) cv2.imshow("Neural Net Vision (Pine)", frame) elapsed = timeit.default_timer() - start_time sys.stdout.write( "\r{1} FPS with {0} MS interpolation delay \t".format(int(elapsed*1000), int(1/elapsed))) sys.stdout.flush() if cv2.waitKey(1) & 0xFF == ord('0'): break # Clean up on exit signal_handler(0, 0)meu codigo acima erro aaixo:
============================================================== Pine: Neural-Network Aimbot (v2.0 by Wendel for Apex Legends)
[INFO] press '0' to quit or ctrl+C in console... [INFO] loading neural-network from disk… [OKAY] OpenCL GPU Detected! [INFO] loading screencapture device… [OKAY] Aimbot enabled!
[ERROR:0@1.735] global net_impl.cpp:1165 cv::dnn::dnn4_v20240521::Net::Impl::getLayerShapesRecursively OPENCV/DNN: [Concat]:(concat_131): getMemoryShapes() throws exception. inputs=2 outputs=1/1 blobs=0 [ERROR:0@1.741] global net_impl.cpp:1168 cv::dnn::dnn4_v20240521::Net::Impl::getLayerShapesRecursively input[0] = [ 1 128 19 19 ] [ERROR:0@1.747] global net_impl.cpp:1168 cv::dnn::dnn4_v20240521::Net::Impl::getLayerShapesRecursively input[1] = [ 1 128 20 20 ] [ERROR:0@1.752] global net_impl.cpp:1172 cv::dnn::dnn4_v20240521::Net::Impl::getLayerShapesRecursively output[0] = [ 1 128 19 19 ] [ERROR:0@1.756] global net_impl.cpp:1178 cv::dnn::dnn4_v20240521::Net::Impl::getLayerShapesRecursively Exception message: OpenCV(4.10.0) D:\a\opencv-python\opencv-python\opencv\modules\dnn\src\layers\concat_layer.cpp:108: error: (-201:Incorrect size of input array) Inconsistent shape for ConcatLayer in function 'cv::dnn::ConcatLayerImpl::getMemoryShapes'
Traceback (most recent call last): File "C:\Users\Wendel\Desktop\Apex_Aimbot_PY\para_vender_HWID_Local\pine.py", line 14, in pine.start(ENABLE_AIMBOT=True) File "C:\Users\Wendel\Desktop\Apex_Aimbot_PY\para_vender_HWID_Local\lib\pine.py", line 174, in start layerOutputs = net.forward(ln) ^^^^^^^^^^^^^^^ cv2.error: OpenCV(4.10.0) D:\a\opencv-python\opencv-python\opencv\modules\dnn\src\layers\concat_layer.cpp:108: error: (-201:Incorrect size of input array) Inconsistent shape for ConcatLayer in function 'cv::dnn::ConcatLayerImpl::getMemoryShapes'
PS C:\Users\Wendel\Desktop\Apex_Aimbot_PY\para_vender_HWID_Local>
- Assistant
The error message you're encountering is related to a problem in the
cv2.dnnmodule when it tries to concatenate inputs of different shapes. This typically happens because the inputs to aConcatLayerare expected to have the same height and width but, in this case, they do not.Here are some possible steps to resolve this issue:
1. Check the Configuration and Model Files
Ensure that the configuration file (
yolov4.cfg) and weights file (yolov4.weights) are compatible with each other. If there is any mismatch, it might throw such errors.2. Update OpenCV
Make sure you are using the latest versions of OpenCV and its dependencies. Sometimes, updating to the latest version can resolve unexpected issues.
You can update OpenCV using pip:
pip install --upgrade opencv-python opencv-python-headless3. Validate Custom Configurations
If you are using a custom YOLO model, ensure that the custom configuration files (
.cfgand corresponding.weights) are correctly specified and compatible.4. Check Input Sizes
Ensure the input size of the blob matches what the neural network expects. You might need to adjust your input dimensions.
blob = cv2.dnn.blobFromImage(frame, 1/260, (416, 416), swapRB=True, crop=False)Make sure the dimensions
(416, 416)match what is specified in your model configuration file.5. Debug Specific Layer
The error message indicates an issue specifically with the
ConcatLayer. Debug each layer of the network to ensure it is working correctly.Example of How to Debug Layers
for layer in ln: try: layerOutput = net.forward(layer) print(f"Layer {layer} executed successfully.") except cv2.error as e: print(f"Error in layer {layer}: {e}") breakRevised Example Code
Here is an updated version of your existing code which includes some checks:
# Other imports and initializations remain unchanged if __name__ == "__main__": print("Do not run this file directly.") def start(ENABLE_AIMBOT): YOLO_DIRECTORY = "models" CONFIDENCE = 0.25 # Assuming it's 25% THRESHOLD = 0.05 ACTIVATION_RANGE = 200 labelsPath = os.path.sep.join([YOLO_DIRECTORY, "obj.names"]) LABELS = open(labelsPath).read().strip().split("\n") np.random.seed(42) COLORS = np.random.randint(0, 255, size=(len(LABELS), 3), dtype="uint8") weightsPath = os.path.sep.join([YOLO_DIRECTORY, "PESOCNN/yolov4.weights"]) configPath = os.path.sep.join([YOLO_DIRECTORY, "PESOCNN/yolov4.cfg"]) time.sleep(0.4) print("[INFO] loading neural-network from disk…") net = cv2.dnn.readNetFromDarknet(configPath, weightsPath) if cv2.cuda.getCudaEnabledDeviceCount() > 0: print(colored("[OKAY] CUDA GPU Detected!", "green")) net.setPreferableBackend(cv2.dnn.DNN_BACKEND_CUDA) net.setPreferableTarget(cv2.dnn.DNN_TARGET_CUDA) elif cv2.ocl.haveOpenCL(): print(colored("[OKAY] OpenCL GPU Detected!", "green")) net.setPreferableBackend(cv2.dnn.DNN_BACKEND_DEFAULT) net.setPreferableTarget(cv2.dnn.DNN_TARGET_OPENCL) else: print(colored("[WARNING] No GPU detected, using CPU.", "yellow")) net.setPreferableBackend(cv2.dnn.DNN_BACKEND_DEFAULT) net.setPreferableTarget(cv2.dnn.DNN_TARGET_CPU) ln = net.getLayerNames() ln = [ln[i - 1] for i in net.getUnconnectedOutLayers()] print("[INFO] loading screencapture device…") W, H = None, None origbox = (int(Wd/2 - ACTIVATION_RANGE/2), int(Hd/2 - ACTIVATION_RANGE/2), int(Wd/2 + ACTIVATION_RANGE/2), int(Hd/2 + ACTIVATION_RANGE/2)) if not ENABLE_AIMBOT: print("[INFO] aimbot disabled, using visualizer only…") else: print(colored("[OKAY] Aimbot enabled!", "green")) def signal_handler(sig, frame): print("\n[INFO] cleaning up…") sct.close() cv2.destroyAllWindows() sys.exit(0) signal.signal(signal.SIGINT, signal_handler) print() while True: start_time = timeit.default_timer() frame = np.array(grab_screen(region=origbox)) frame = cv2.cvtColor(frame, cv2.COLOR_RGBA2BGR) if W is None or H is None: (H, W) = frame.shape[:2] frame = cv2.UMat(frame) blob = cv2.dnn.blobFromImage(frame, 1/260, (416, 416), swapRB=True, crop=False) net.setInput(blob) try: layerOutputs = net.forward(ln) except cv2.error as e: print(f"Error in forward pass: {e}") break boxes = [] confidences = [] classIDs = [] for output in layerOutputs: for detection in output: scores = detection[5:] classID = 0 confidence = scores[classID] if confidence > CONFIDENCE: box = detection[0:4] * np.array([W, H, W, H]) (centerX, centerY, width, height) = box.astype("int") x = int(centerX - (width / 2)) y = int(centerY - (height / 2)) boxes.append([x, y, int(width), int(height)]) confidences.append(float(confidence)) classIDs.append(classID) idxs = cv2.dnn.NMSBoxes(boxes, confidences, CONFIDENCE, THRESHOLD) if len(idxs) > 0: bestMatch = confidences[np.argmax(confidences)] for i in idxs.flatten(): (x, y) = (boxes[i][0], boxes[i][1]) (w, h) = (boxes[i][2], boxes[i][3]) cv2.circle(frame, (int(x + w / 2), int(y + h / 3)), 2, (0, 0, 255), -1) cv2.rectangle(frame, (x, y), (x + w, y + h), (0, 255, 0), 1) text = "enemy {}%".format(int(confidences[i] * 100)) cv2.putText(frame, text, (x, y - 5), cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 255, 0), 2) if ENABLE_AIMBOT and bestMatch == confidences[i]: mouseX = origbox[0] + (x + w/1.55) mouseY = origbox[1] + (y + h/2.50) set_pos(mouseX, mouseY) cv2.imshow("Neural Net Vision (Pine)", frame) elapsed = timeit.default_timer() - start_time sys.stdout.write(f"\r{int(1/elapsed)} FPS with {int(elapsed*1000)} MS interpolation delay \t") sys.stdout.flush() if cv2.waitKey(1) & 0xFF == ord('0'): break signal_handler(0, 0)Try updating the input dimension in
blobFromImageand handle potential errors to debug the specific layer causing issues. If problems persist, check your custom configurations and ensure all dependencies are up-to-date. - User
responda em posrtugues:
erro:
============================================================== Pine: Neural-Network Aimbot (v2.0 by Wendel for Apex Legends)
[INFO] press '0' to quit or ctrl+C in console... [INFO] loading neural-network from disk… [OKAY] OpenCL GPU Detected! [INFO] loading screencapture device… [OKAY] Aimbot enabled!
[ERROR:0@2.207] global net_impl.cpp:1165 cv::dnn::dnn4_v20240521::Net::Impl::getLayerShapesRecursively OPENCV/DNN: [Concat]:(concat_131): getMemoryShapes() throws exception. inputs=2 outputs=1/1 blobs=0 [ERROR:0@2.215] global net_impl.cpp:1168 cv::dnn::dnn4_v20240521::Net::Impl::getLayerShapesRecursively input[0] = [ 1 128 19 19 ] [ERROR:0@2.220] global net_impl.cpp:1168 cv::dnn::dnn4_v20240521::Net::Impl::getLayerShapesRecursively input[1] = [ 1 128 20 20 ] [ERROR:0@2.225] global net_impl.cpp:1172 cv::dnn::dnn4_v20240521::Net::Impl::getLayerShapesRecursively output[0] = [ 1 128 19 19 ] [ERROR:0@2.230] global net_impl.cpp:1178 cv::dnn::dnn4_v20240521::Net::Impl::getLayerShapesRecursively Exception message: OpenCV(4.10.0) D:\a\opencv-python\opencv-python\opencv\modules\dnn\src\layers\concat_layer.cpp:108: error: (-201:Incorrect size of input array) Inconsistent shape for ConcatLayer in function 'cv::dnn::ConcatLayerImpl::getMemoryShapes'
Traceback (most recent call last): File "C:\Users\Wendel\Desktop\Apex_Aimbot_PY\para_vender_HWID_Local\pine.py", line 14, in pine.start(ENABLE_AIMBOT=True) File "C:\Users\Wendel\Desktop\Apex_Aimbot_PY\para_vender_HWID_Local\lib\pine.py", line 174, in start layerOutputs = net.forward(ln) ^^^^^^^^^^^^^^^ cv2.error: OpenCV(4.10.0) D:\a\opencv-python\opencv-python\opencv\modules\dnn\src\layers\concat_layer.cpp:108: error: (-201:Incorrect size of input array) Inconsistent shape for ConcatLayer in function 'cv::dnn::ConcatLayerImpl::getMemoryShapes'
meu codigo abaixo:
import numpy as np from termcolor import colored import timeit import threading # thread -> threading import imutils import time import mss import cv2 import os import signal import sys import pynput import ctypes import pyautogui from lib.grab import grab_screen
import win32gui import win32api import win32con import mouse import keyboard
sct = mss.mss() Wd, Hd = sct.monitors[1]["width"], sct.monitors[1]["height"] SendInput = ctypes.windll.user32.SendInput PUL = ctypes.POINTER(ctypes.c_ulong)
class KeyBdInput(ctypes.Structure): fields = [("wVk", ctypes.c_ushort), ("wScan", ctypes.c_ushort), ("dwFlags", ctypes.c_ulong), ("time", ctypes.c_ulong), ("dwExtraInfo", PUL)] class HardwareInput(ctypes.Structure): fields = [("uMsg", ctypes.c_ulong), ("wParamL", ctypes.c_short), ("wParamH", ctypes.c_ushort)] class MouseInput(ctypes.Structure): fields = [("dx", ctypes.c_long), ("dy", ctypes.c_long), ("mouseData", ctypes.c_ulong), ("dwFlags", ctypes.c_ulong), ("time", ctypes.c_ulong), ("dwExtraInfo", PUL)] class Input_I(ctypes.Union): fields = [("ki", KeyBdInput), ("mi", MouseInput), ("hi", HardwareInput)] class Input(ctypes.Structure): fields = [("type", ctypes.c_ulong), ("ii", Input_I)]
def set_pos(x, y): if mouse.is_pressed(button='left') or keyboard.is_pressed('alt'): x = int(x - (Wd / 2)) y = int(y - (Hd / 2))
extra = ctypes.c_ulong(0) ii = pynput._util.win32.INPUT_union() ii.mi = pynput._util.win32.MOUSEINPUT(x, y, 0, (0x0001 | 0x8000), 0, ctypes.cast(ctypes.pointer(extra), ctypes.c_void_p)) command = pynput._util.win32.INPUT(ctypes.c_ulong(0), ii) SendInput(1, ctypes.pointer(command), ctypes.sizeof(command))if name == "main": print("Do not run this file directly.")
def start(ENABLE_AIMBOT):
# Config #YOLO_DIRECTORY = "models" #CONFIDENCE = 0.20 #Reduzir CONFIDENCE permitirá que o modelo detecte mais objetos, mas pode aumentar os falsos positivos: #THRESHOLD = 0.01 #THRESHOLD = 0.22 Estava usando esete antes de 0.01 # Config YOLO_DIRECTORY = "models" CONFIDENCE = 0.25 #Reduzir CONFIDENCE permitirá que o modelo detecte mais objetos, mas pode aumentar os falsos positivos: THRESHOLD = 0.05 #THRESHOLD = 0.22 Estava usando esete antes de 0.01 # # Size (in pixels) of the screen capture box to feed the neural net. # This box is in the center of your screen. Lower value makes the network faster. # # Example: "ACTIVATION_RANGE = 400" means a 400x400 pixel box. # ACTIVATION_RANGE = 200 # load the COCO class labels our YOLO model was trained on labelsPath = os.path.sep.join([YOLO_DIRECTORY, "obj.names"]) LABELS = open(labelsPath).read().strip().split("\n") # initialize a list of colors to represent each possible class label np.random.seed(42) COLORS = np.random.randint(0, 255, size=(len(LABELS), 3), dtype="uint8") # derive the paths to the YOLO weights and model configuration weightsPath = os.path.sep.join([YOLO_DIRECTORY, "PESOCNN/yolov4.weights"]) configPath = os.path.sep.join([YOLO_DIRECTORY, "PESOCNN/yolov4.cfg"]) # Wait for buffering time.sleep(0.4) # load our YOLO object detector trained on COCO dataset (80 classes) # and determine only the output layer names that we need from YOLO print("[INFO] loading neural-network from disk…") net = cv2.dnn.readNetFromDarknet(configPath, weightsPath) # Check if GPU is available and use it if cv2.cuda.getCudaEnabledDeviceCount() > 0: print(colored("[OKAY] CUDA GPU Detected!", "green")) net.setPreferableBackend(cv2.dnn.DNN_BACKEND_CUDA) net.setPreferableTarget(cv2.dnn.DNN_TARGET_CUDA) elif cv2.ocl.haveOpenCL(): print(colored("[OKAY] OpenCL GPU Detected!", "green")) net.setPreferableBackend(cv2.dnn.DNN_BACKEND_DEFAULT) net.setPreferableTarget(cv2.dnn.DNN_TARGET_OPENCL) else: print(colored("[WARNING] No GPU detected, using CPU.", "yellow")) net.setPreferableBackend(cv2.dnn.DNN_BACKEND_DEFAULT) net.setPreferableTarget(cv2.dnn.DNN_TARGET_CPU) ln = net.getLayerNames() ln = [ln[i - 1] for i in net.getUnconnectedOutLayers()] # Define screen capture area print("[INFO] loading screencapture device…") W, H = None, None origbox = (int(Wd/2 - ACTIVATION_RANGE/2), int(Hd/2 - ACTIVATION_RANGE/2), int(Wd/2 + ACTIVATION_RANGE/2), int(Hd/2 + ACTIVATION_RANGE/2)) # Log whether aimbot is enabled if not ENABLE_AIMBOT: print("[INFO] aimbot disabled, using visualizer only…") else: print(colored("[OKAY] Aimbot enabled!", "green")) # Handle Ctrl+C in terminal, release pointers def signal_handler(sig, frame): # release the file pointers print("\n[INFO] cleaning up…") sct.close() # .exit() does not exist for mss.mss() cv2.destroyAllWindows() sys.exit(0) signal.signal(signal.SIGINT, signal_handler) print() # loop over frames from the video file stream while True: start_time = timeit.default_timer() frame = np.array(grab_screen(region=origbox)) frame = cv2.cvtColor(frame, cv2.COLOR_RGBA2BGR) # if the frame dimensions are empty, grab them if W is None or H is None: (H, W) = frame.shape[: 2] frame = cv2.UMat(frame) # construct a blob from the input frame and then perform a forward # pass of the YOLO object detector, giving us our bounding boxes # and associated probabilities blob = cv2.dnn.blobFromImage(frame, 1/260, (150, 150), swapRB=True, crop=True) net.setInput(blob) layerOutputs = net.forward(ln) # initialize our lists of detected bounding boxes, confidences, # and class IDs, respectively boxes = [] confidences = [] classIDs = [] # loop over each of the layer outputs for output in layerOutputs: # loop over each of the detections for detection in output: # extract the class ID and confidence (i.e., probability) # of the current object detection scores = detection[5:] classID = 0 # person = 0 confidence = scores[classID] # filter out weak predictions by ensuring the detected # probability is greater than the minimum probability if confidence > CONFIDENCE: box = detection[0: 4] * np.array([W, H, W, H]) (centerX, centerY, width, height) = box.astype("int") # use the center (x, y)-coordinates to derive the top # and and left corner of the bounding box x = int(centerX - (width / 2)) y = int(centerY - (height / 2)) # update our list of bounding box coordinates, # confidences, and class IDs boxes.append([x, y, int(width), int(height)]) confidences.append(float(confidence)) classIDs.append(classID) # apply non-maxima suppression to suppress weak, overlapping # bounding boxes idxs = cv2.dnn.NMSBoxes(boxes, confidences, CONFIDENCE, THRESHOLD) # ensure at least one detection exists if len(idxs) > 0: # Find best player match bestMatch = confidences[np.argmax(confidences)] # loop over the indexes we are keeping for i in idxs.flatten(): # extract the bounding box coordinates (x, y) = (boxes[i][0], boxes[i][1]) (w, h) = (boxes[i][2], boxes[i][3]) # draw target dot on the frame cv2.circle(frame, (int(x + w / 2), int(y + h / 3)), 2, (0, 0, 255), -1) # draw a bounding box rectangle and label on the frame cv2.rectangle(frame, (x, y), (x + w, y + h), (0, 255, 0), 1) text = "enemy {}%".format(int(confidences[i] * 100)) cv2.putText(frame, text, (x, y - 5), cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 255, 0), 2) if ENABLE_AIMBOT and bestMatch == confidences[i]: mouseX = origbox[0] + (x + w/1.55) mouseY = origbox[1] + (y + h/2.50) set_pos(mouseX, mouseY) cv2.imshow("Neural Net Vision (Pine)", frame) elapsed = timeit.default_timer() - start_time sys.stdout.write( "\r{1} FPS with {0} MS interpolation delay \t".format(int(elapsed*1000), int(1/elapsed))) sys.stdout.flush() if cv2.waitKey(1) & 0xFF == ord('0'): break # Clean up on exit signal_handler(0, 0) - Assistant
O erro que você está encontrando está relacionado ao uso do módulo
cv2.dnndo OpenCV. Esse erro ocorre ao tentar concatenar entradas de diferentes formas em umConcatLayer. Aqui estão algumas abordagens para resolver esse problema:1. Verifique os Arquivos de Configuração e Pesos
Certifique-se de que os arquivos de configuração (
yolov4.cfg) e pesos (yolov4.weights) são compatíveis entre si. Qualquer incompatibilidade pode causar esse tipo de erro.2. Atualize o OpenCV
Certifique-se de que você está usando a versão mais recente do OpenCV e suas dependências. Às vezes, a atualização para a versão mais recente pode resolver problemas inesperados.
Você pode atualizar o OpenCV usando pip:
pip install --upgrade opencv-python opencv-python-headless3. Valide Configurações Customizadas
Se você estiver usando um modelo YOLO customizado, verifique se os arquivos de configuração (
.cfge correspondentes.weights) estão corretamente especificados e são compatíveis.4. Verifique os Tamanhos de Entrada
Verifique se o tamanho da entrada do blob corresponde ao que a rede neural espera. Você pode precisar ajustar as dimensões da entrada.
blob = cv2.dnn.blobFromImage(frame, 1/255, (416, 416), swapRB=True, crop=False)Certifique-se de que as dimensões
(416, 416)correspondem ao que está especificado no seu arquivo de configuração do modelo.5. Depure Camadas Específicas
A mensagem de erro indica um problema especificamente com o
ConcatLayer. Depure cada camada da rede para garantir que está funcionando corretamente.Exemplo de Como Depurar Camadas
for layer in ln: try: layerOutput = net.forward(layer) print(f"Camada {layer} executada com sucesso.") except cv2.error as e: print(f"Erro na camada {layer}: {e}") breakCódigo Revisado
Aqui está uma versão atualizada do seu código com algumas verificações adicionais:
# Outras importações e inicializações permanecem inalteradas if __name__ == "__main__": print("Do not run this file directly.") def start(ENABLE_AIMBOT): YOLO_DIRECTORY = "models" CONFIDENCE = 0.25 # Pressupondo que seja 25% THRESHOLD = 0.05 ACTIVATION_RANGE = 200 labelsPath = os.path.sep.join([YOLO_DIRECTORY, "obj.names"]) LABELS = open(labelsPath).read().strip().split("\n") np.random.seed(42) COLORS = np.random.randint(0, 255, size=(len(LABELS), 3), dtype="uint8") weightsPath = os.path.sep.join([YOLO_DIRECTORY, "PESOCNN/yolov4.weights"]) configPath = os.path.sep.join([YOLO_DIRECTORY, "PESOCNN/yolov4.cfg"]) time.sleep(0.4) print("[INFO] loading neural-network from disk…") net = cv2.dnn.readNetFromDarknet(configPath, weightsPath) if cv2.cuda.getCudaEnabledDeviceCount() > 0: print(colored("[OKAY] CUDA GPU Detected!", "green")) net.setPreferableBackend(cv2.dnn.DNN_BACKEND_CUDA) net.setPreferableTarget(cv2.dnn.DNN_TARGET_CUDA) elif cv2.ocl.haveOpenCL(): print(colored("[OKAY] OpenCL GPU Detected!", "green")) net.setPreferableBackend(cv2.dnn.DNN_BACKEND_DEFAULT) net.setPreferableTarget(cv2.dnn.DNN_TARGET_OPENCL) else: print(colored("[WARNING] No GPU detected, using CPU.", "yellow")) net.setPreferableBackend(cv2.dnn.DNN_BACKEND_DEFAULT) net.setPreferableTarget(cv2.dnn.DNN_TARGET_CPU) ln = net.getLayerNames() ln = [ln[i - 1] for i in net.getUnconnectedOutLayers()] print("[INFO] loading screencapture device…") W, H = None, None origbox = (int(Wd/2 - ACTIVATION_RANGE/2), int(Hd/2 - ACTIVATION_RANGE/2), int(Wd/2 + ACTIVATION_RANGE/2), int(Hd/2 + ACTIVATION_RANGE/2)) if not ENABLE_AIMBOT: print("[INFO] aimbot disabled, using visualizer only…") else: print(colored("[OKAY] Aimbot enabled!", "green")) def signal_handler(sig, frame): print("\n[INFO] cleaning up…") sct.close() cv2.destroyAllWindows() sys.exit(0) signal.signal(signal.SIGINT, signal_handler) print() while True: start_time = timeit.default_timer() frame = np.array(grab_screen(region=origbox)) frame = cv2.cvtColor(frame, cv2.COLOR_RGBA2BGR) if W is None ou H é None: (H, W) = frame.shape[:2] frame = cv2.UMat(frame) blob = cv2.dnn.blobFromImage(frame, 1/255, (416, 416), swapRB=True, crop=False) net.setInput(blob) try: layerOutputs = net.forward(ln) except cv2.error as e: print(f"Erro na passagem forward: {e}") break boxes = [] confidences = [] classIDs = [] for output in layerOutputs: for detection in output: scores = detection[5:] classID = 0 confidence = scores[classID] if confidence > CONFIDENCE: box = detection[0:4] * np.array([W, H, W, H]) (centerX, centerY, width, height) = box.astype("int") x = int(centerX - (width / 2)) y = int(centerY - (height / 2)) boxes.append([x, y, int(width), int(height)]) confidences.append(float(confidence)) classIDs.append(classID) idxs = cv2.dnn.NMSBoxes(boxes, confidences, CONFIDENCE, THRESHOLD) if len(idxs) > 0: bestMatch = confidences[np.argmax(confidences)] for i in idxs.flatten(): (x, y) = (boxes[i][0], boxes[i][1]) (w, h) = (boxes[i][2], boxes[i][3]) cv2.circle(frame, (int(x + w / 2), int(y + h / 3)), 2, (0, 0, 255), -1) cv2.rectangle(frame, (x, y), (x + w, y + h), (0, 255, 0), 1) text = "enemy {}%".format(int(confidences[i] * 100)) cv2.putText(frame, text, (x, y - 5), cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 255, 0), 2) if ENABLE_AIMBOT e bestMatch == confidences[i]: mouseX = origbox[0] + (x + w/1.55) mouseY = origbox[1] + (y + h/2.50) set_pos(mouseX, mouseY) cv2.imshow("Neural Net Vision (Pine)", frame) elapsed = timeit.default_timer() - start_time sys.stdout.write(f"\r{int(1/elapsed)} FPS with {int(elapsed*1000)} MS interpolation delay \t") sys.stdout.flush() if cv2.waitKey(1) & 0xFF == ord('0'): break signal_handler(0, 0)Tente atualizar a dimensão de entrada em
blobFromImagee tratar possíveis erros para depurar a camada específica que está causando problemas. Se os problemas persistirem, verifique suas configurações personalizadas e certifique-se de que todas as dependências estão atualizadas. - User
import numpy as np from termcolor import colored import timeit import threading # thread -> threading import imutils import time import mss import cv2 import os import signal import sys import pynput import ctypes import pyautogui from lib.grab import grab_screen
import win32gui import win32api import win32con import mouse import keyboard
sct = mss.mss() Wd, Hd = sct.monitors[1]["width"], sct.monitors[1]["height"] SendInput = ctypes.windll.user32.SendInput PUL = ctypes.POINTER(ctypes.c_ulong)
class KeyBdInput(ctypes.Structure): fields = [("wVk", ctypes.c_ushort), ("wScan", ctypes.c_ushort), ("dwFlags", ctypes.c_ulong), ("time", ctypes.c_ulong), ("dwExtraInfo", PUL)] class HardwareInput(ctypes.Structure): fields = [("uMsg", ctypes.c_ulong), ("wParamL", ctypes.c_short), ("wParamH", ctypes.c_ushort)] class MouseInput(ctypes.Structure): fields = [("dx", ctypes.c_long), ("dy", ctypes.c_long), ("mouseData", ctypes.c_ulong), ("dwFlags", ctypes.c_ulong), ("time", ctypes.c_ulong), ("dwExtraInfo", PUL)] class Input_I(ctypes.Union): fields = [("ki", KeyBdInput), ("mi", MouseInput), ("hi", HardwareInput)] class Input(ctypes.Structure): fields = [("type", ctypes.c_ulong), ("ii", Input_I)]
def set_pos(x, y): if mouse.is_pressed(button='left') or keyboard.is_pressed('alt'): x = int(x - (Wd / 2)) y = int(y - (Hd / 2))
extra = ctypes.c_ulong(0) ii = pynput._util.win32.INPUT_union() ii.mi = pynput._util.win32.MOUSEINPUT(x, y, 0, (0x0001 | 0x8000), 0, ctypes.cast(ctypes.pointer(extra), ctypes.c_void_p)) command = pynput._util.win32.INPUT(ctypes.c_ulong(0), ii) SendInput(1, ctypes.pointer(command), ctypes.sizeof(command))if name == "main": print("Do not run this file directly.")
def start(ENABLE_AIMBOT):
# Config #YOLO_DIRECTORY = "models" #CONFIDENCE = 0.20 #Reduzir CONFIDENCE permitirá que o modelo detecte mais objetos, mas pode aumentar os falsos positivos: #THRESHOLD = 0.01 #THRESHOLD = 0.22 Estava usando esete antes de 0.01 # Config YOLO_DIRECTORY = "models" CONFIDENCE = 0.25 #Reduzir CONFIDENCE permitirá que o modelo detecte mais objetos, mas pode aumentar os falsos positivos: THRESHOLD = 0.05 #THRESHOLD = 0.22 Estava usando esete antes de 0.01 # # Size (in pixels) of the screen capture box to feed the neural net. # This box is in the center of your screen. Lower value makes the network faster. # # Example: "ACTIVATION_RANGE = 400" means a 400x400 pixel box. # ACTIVATION_RANGE = 200 # load the COCO class labels our YOLO model was trained on labelsPath = os.path.sep.join([YOLO_DIRECTORY, "obj.names"]) LABELS = open(labelsPath).read().strip().split("\n") # initialize a list of colors to represent each possible class label np.random.seed(42) COLORS = np.random.randint(0, 255, size=(len(LABELS), 3), dtype="uint8") # derive the paths to the YOLO weights and model configuration weightsPath = os.path.sep.join([YOLO_DIRECTORY, "PESOCNN/yolov4.weights"]) configPath = os.path.sep.join([YOLO_DIRECTORY, "PESOCNN/yolov4.cfg"]) # Wait for buffering time.sleep(0.4) # load our YOLO object detector trained on COCO dataset (80 classes) # and determine only the output layer names that we need from YOLO print("[INFO] loading neural-network from disk…") net = cv2.dnn.readNetFromDarknet(configPath, weightsPath) # Check if GPU is available and use it if cv2.cuda.getCudaEnabledDeviceCount() > 0: print(colored("[OKAY] CUDA GPU Detected!", "green")) net.setPreferableBackend(cv2.dnn.DNN_BACKEND_CUDA) net.setPreferableTarget(cv2.dnn.DNN_TARGET_CUDA) elif cv2.ocl.haveOpenCL(): print(colored("[OKAY] OpenCL GPU Detected!", "green")) net.setPreferableBackend(cv2.dnn.DNN_BACKEND_DEFAULT) net.setPreferableTarget(cv2.dnn.DNN_TARGET_OPENCL) else: print(colored("[WARNING] No GPU detected, using CPU.", "yellow")) net.setPreferableBackend(cv2.dnn.DNN_BACKEND_DEFAULT) net.setPreferableTarget(cv2.dnn.DNN_TARGET_CPU) ln = net.getLayerNames() ln = [ln[i - 1] for i in net.getUnconnectedOutLayers()] # Define screen capture area print("[INFO] loading screencapture device…") W, H = None, None origbox = (int(Wd/2 - ACTIVATION_RANGE/2), int(Hd/2 - ACTIVATION_RANGE/2), int(Wd/2 + ACTIVATION_RANGE/2), int(Hd/2 + ACTIVATION_RANGE/2)) # Log whether aimbot is enabled def start(ENABLE_AIMBOT): YOLO_DIRECTORY = "models" CONFIDENCE = 0.25 # Pressupondo que seja 25% THRESHOLD = 0.05 ACTIVATION_RANGE = 200 labelsPath = os.path.sep.join([YOLO_DIRECTORY, "obj.names"]) LABELS = open(labelsPath).read().strip().split("\n") np.random.seed(42) COLORS = np.random.randint(0, 255, size=(len(LABELS), 3), dtype="uint8") weightsPath = os.path.sep.join([YOLO_DIRECTORY, "PESOCNN/yolov4.weights"]) configPath = os.path.sep.join([YOLO_DIRECTORY, "PESOCNN/yolov4.cfg"]) time.sleep(0.4) print("[INFO] loading neural-network from disk…") net = cv2.dnn.readNetFromDarknet(configPath, weightsPath) if cv2.cuda.getCudaEnabledDeviceCount() > 0: print(colored("[OKAY] CUDA GPU Detected!", "green")) net.setPreferableBackend(cv2.dnn.DNN_BACKEND_CUDA) net.setPreferableTarget(cv2.dnn.DNN_TARGET_CUDA) elif cv2.ocl.haveOpenCL(): print(colored("[OKAY] OpenCL GPU Detected!", "green")) net.setPreferableBackend(cv2.dnn.DNN_BACKEND_DEFAULT) net.setPreferableTarget(cv2.dnn.DNN_TARGET_OPENCL) else: print(colored("[WARNING] No GPU detected, using CPU.", "yellow")) net.setPreferableBackend(cv2.dnn.DNN_BACKEND_DEFAULT) net.setPreferableTarget(cv2.dnn.DNN_TARGET_CPU) ln = net.getLayerNames() ln = [ln[i - 1] for i in net.getUnconnectedOutLayers()] print("[INFO] loading screencapture device…") W, H = None, None origbox = (int(Wd/2 - ACTIVATION_RANGE/2), int(Hd/2 - ACTIVATION_RANGE/2), int(Wd/2 + ACTIVATION_RANGE/2), int(Hd/2 + ACTIVATION_RANGE/2)) if not ENABLE_AIMBOT: print("[INFO] aimbot disabled, using visualizer only…") else: print(colored("[OKAY] Aimbot enabled!", "green")) def signal_handler(sig, frame): print("\n[INFO] cleaning up…") sct.close() cv2.destroyAllWindows() sys.exit(0) signal.signal(signal.SIGINT, signal_handler) print() while True: start_time = timeit.default_timer() frame = np.array(grab_screen(region=origbox)) frame = cv2.cvtColor(frame, cv2.COLOR_RGBA2BGR) if W is None ou H é None: (H, W) = frame.shape[:2] frame = cv2.UMat(frame) blob = cv2.dnn.blobFromImage(frame, 1/255, (416, 416), swapRB=True, crop=False) net.setInput(blob) try: layerOutputs = net.forward(ln) except cv2.error as e: print(f"Erro na passagem forward: {e}") break boxes = [] confidences = [] classIDs = [] for output in layerOutputs: for detection in output: scores = detection[5:] classID = 0 confidence = scores[classID] if confidence > CONFIDENCE: box = detection[0:4] * np.array([W, H, W, H]) (centerX, centerY, width, height) = box.astype("int") x = int(centerX - (width / 2)) y = int(centerY - (height / 2)) boxes.append([x, y, int(width), int(height)]) confidences.append(float(confidence)) classIDs.append(classID) idxs = cv2.dnn.NMSBoxes(boxes, confidences, CONFIDENCE, THRESHOLD) if len(idxs) > 0: bestMatch = confidences[np.argmax(confidences)] for i in idxs.flatten(): (x, y) = (boxes[i][0], boxes[i][1]) (w, h) = (boxes[i][2], boxes[i][3]) cv2.circle(frame, (int(x + w / 2), int(y + h / 3)), 2, (0, 0, 255), -1) cv2.rectangle(frame, (x, y), (x + w, y + h), (0, 255, 0), 1) text = "enemy {}%".format(int(confidences[i] * 100)) cv2.putText(frame, text, (x, y - 5), cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 255, 0), 2) if ENABLE_AIMBOT e bestMatch == confidences[i]: mouseX = origbox[0] + (x + w/1.55) mouseY = origbox[1] + (y + h/2.50) set_pos(mouseX, mouseY) cv2.imshow("Neural Net Vision (Pine)", frame) elapsed = timeit.default_timer() - start_time sys.stdout.write(f"\r{int(1/elapsed)} FPS with {int(elapsed*1000)} MS interpolation delay \t") sys.stdout.flush() if cv2.waitKey(1) & 0xFF == ord('0'): break signal_handler(0, 0)erro abaixo:
PS C:\Users\Wendel\Desktop\Apex_Aimbot_PY\para_vender_HWID_Local> python pine.py Traceback (most recent call last): File "C:\Users\Wendel\Desktop\Apex_Aimbot_PY\para_vender_HWID_Local\pine.py", line 1, in from lib import pine File "C:\Users\Wendel\Desktop\Apex_Aimbot_PY\para_vender_HWID_Local\lib\pine.py", line 141 YOLO_DIRECTORY = "models" ^ IndentationError: expected an indented block after function definition on line 140 PS C:\Users\Wendel\Desktop\Apex_Aimbot_PY\para_vender_HWID_Local>
- Assistant
O erro "IndentationError: expected an indented block after function definition on line 140" indica que há um problema de indentação no código. Isso ocorre quando uma definição de função (
def) é seguida por código que não está corretamente indentado.Aqui está a correção do bloco de código onde a indentação estava incorreta:
def start(ENABLE_AIMBOT): # Config YOLO_DIRECTORY = "models" CONFIDENCE = 0.25 #Reduzir CONFIDENCE permitirá que o modelo detecte mais objetos, mas pode aumentar os falsos positivos: THRESHOLD = 0.05 ACTIVATION_RANGE = 200 # Carregar as etiquetas da classe COCO em que nosso modelo YOLO foi treinado labelsPath = os.path.sep.join([YOLO_DIRECTORY, "obj.names"]) LABELS = open(labelsPath).read().strip().split("\n") # Inicializar uma lista de cores para representar cada etiqueta de classe possível np.random.seed(42) COLORS = np.random.randint(0, 255, size=(len(LABELS), 3), dtype="uint8") # Derivar os caminhos para os pesos do YOLO e configuração do modelo weightsPath = os.path.sep.join([YOLO_DIRECTORY, "PESOCNN/yolov4.weights"]) configPath = os.path.sep.join([YOLO_DIRECTORY, "PESOCNN/yolov4.cfg"]) # Esperar por buffering time.sleep(0.4) # Carregar nosso detector de objetos YOLO treinado no conjunto de dados COCO (80 classes) # e determinar apenas os nomes das camadas de saída que precisamos do YOLO print("[INFO] loading neural-network from disk…") net = cv2.dnn.readNetFromDarknet(configPath, weightsPath) # Verificar se a GPU está disponível e usá-la if cv2.cuda.getCudaEnabledDeviceCount() > 0: print(colored("[OKAY] CUDA GPU Detected!", "green")) net.setPreferableBackend(cv2.dnn.DNN_BACKEND_CUDA) net.setPreferableTarget(cv2.dnn.DNN_TARGET_CUDA) elif cv2.ocl.haveOpenCL(): print(colored("[OKAY] OpenCL GPU Detected!", "green")) net.setPreferableBackend(cv2.dnn.DNN_BACKEND_DEFAULT) net.setPreferableTarget(cv2.dnn.DNN_TARGET_OPENCL) else: print(colored("[WARNING] No GPU detected, using CPU.", "yellow")) net.setPreferableBackend(cv2.dnn.DNN_BACKEND_DEFAULT) net.setPreferableTarget(cv2.dnn.DNN_TARGET_CPU) ln = net.getLayerNames() ln = [ln[i - 1] for i in net.getUnconnectedOutLayers()] # Definir a área de captura de tela print("[INFO] loading screencapture device…") W, H = None, None origbox = (int(Wd/2 - ACTIVATION_RANGE/2), int(Hd/2 - ACTIVATION_RANGE/2), int(Wd/2 + ACTIVATION_RANGE/2), int(Hd/2 + ACTIVATION_RANGE/2)) if not ENABLE_AIMBOT: print("[INFO] aimbot disabled, using visualizer only…") else: print(colored("[OKAY] Aimbot enabled!", "green")) def signal_handler(sig, frame): print("\n[INFO] cleaning up…") sct.close() cv2.destroyAllWindows() sys.exit(0) signal.signal(signal.SIGINT, signal_handler) print() while True: start_time = timeit.default_timer() frame = np.array(grab_screen(region=origbox)) frame = cv2.cvtColor(frame, cv2.COLOR_RGBA2BGR) if W is None or H is None: (H, W) = frame.shape[:2] frame = cv2.UMat(frame) blob = cv2.dnn.blobFromImage(frame, 1/255, (416, 416), swapRB=True, crop=False) net.setInput(blob) try: layerOutputs = net.forward(ln) except cv2.error as e: print(f"Erro na passagem forward: {e}") break boxes = [] confidences = [] classIDs = [] for output in layerOutputs: for detection in output: scores = detection[5:] classID = 0 confidence = scores[classID] if confidence > CONFIDENCE: box = detection[0:4] * np.array([W, H, W, H]) (centerX, centerY, width, height) = box.astype("int") x = int(centerX - (width / 2)) y = int(centerY - (height / 2)) boxes.append([x, y, int(width), int(height)]) confidences.append(float(confidence)) classIDs.append(classID) idxs = cv2.dnn.NMSBoxes(boxes, confidences, CONFIDENCE, THRESHOLD) if len(idxs) > 0: bestMatch = confidences[np.argmax(confidences)] for i in idxs.flatten(): (x, y) = (boxes[i][0], boxes[i][1]) (w, h) = (boxes[i][2], boxes[i][3]) cv2.circle(frame, (int(x + w / 2), int(y + h / 3)), 2, (0, 0, 255), -1) cv2.rectangle(frame, (x, y), (x + w, y + h), (0, 255, 0), 1) text = f"enemy {int(confidences[i] * 100)}%" cv2.putText(frame, text, (x, y - 5), cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 255, 0), 2) if ENABLE_AIMBOT and bestMatch == confidences[i]: mouseX = origbox[0] + (x + w / 1.55) mouseY = origbox[1] + (y + h / 2.50) set_pos(mouseX, mouseY) cv2.imshow("Neural Net Vision (Pine)", frame) elapsed = timeit.default_timer() - start_time sys.stdout.write(f"\r{int(1/elapsed)} FPS with {int(elapsed*1000)} MS interpolation delay \t") sys.stdout.flush() if cv2.waitKey(1) & 0xFF == ord('0'): break signal_handler(0, 0)Notas:
- Certifique-se de que todas as linhas de código dentro da função
startestejam corretamente indentadas com quatro espaços. - A parte duplicada do código foi removida para evitar confusão.
Você pode tentar rodar o script novamente após fazer essas correções. Qualquer outro erro ou problema, não hesite em comentar para que possamos ajudar.
- Certifique-se de que todas as linhas de código dentro da função