pythonlessons

def residual_block(input_layer, input_channel, filter_num1, filter_num2, activate_type='leaky'):
    short_cut = input_layer
    conv = convolutional(input_layer, filters_shape=(1, 1, input_channel, filter_num1), activate_type=activate_type)
    conv = convolutional(conv       , filters_shape=(3, 3, filter_num1,   filter_num2), activate_type=activate_type)

    residual_output = short_cut + conv
    return residual_output
  
def cspdarknet53(input_data):
    input_data = convolutional(input_data, (3, 3,  3,  32), activate_type="mish")

pythonlessons

import tensorflow as tf
from yolov3.yolov4 import Create_Yolo
from yolov3.utils import load_yolo_weights
from yolov3.configs import *

if YOLO_TYPE == "yolov4":
    Darknet_weights = YOLO_V4_TINY_WEIGHTS if TRAIN_YOLO_TINY else YOLO_V4_WEIGHTS
if YOLO_TYPE == "yolov3":
    Darknet_weights = YOLO_V3_TINY_WEIGHTS if TRAIN_YOLO_TINY else YOLO_V3_WEIGHTS

pythonlessons

import tensorflow as tf
import numpy as np
physical_devices = tf.config.experimental.list_physical_devices('GPU')
if len(physical_devices) > 0:
    tf.config.experimental.set_memory_growth(physical_devices[0], True)
from yolov3.configs import *
from tensorflow.python.compiler.tensorrt import trt_convert as trt

def calibration_input():
    for i in range(100):

pythonlessons

from multiprocessing import Process, Pipe
import time
import numpy as np
  
def send_to_pipe(q, mylist): 
    # function to put elements into Pipe
    for num in mylist: 
        q.send(np.random.random((416, 416, 3)))
  
def pick_from_pipe(q, mylist): 

pythonlessons

from multiprocessing import Process, Pipe
import time
  
def send_to_pipe(q, mylist): 
    # function to put elements into Pipe
    for num in mylist: 
        q.send(num)
  
def pick_from_pipe(q, mylist): 
    # function to print pipe elements 

pythonlessons

from multiprocessing import Process, Queue
import time
import numpy as np
  
def send_to_queue(q, mylist): 
    # function to put elements into Queue
    for num in mylist: 
        q.put(np.random.random((416, 416, 3)))
  
def pick_from_queue(q, mylist): 

pythonlessons

from multiprocessing import Process, Queue
import time
  
def send_to_queue(q, mylist): 
    # function to put elements into Queue
    for num in mylist: 
        q.put(num)
  
def pick_from_queue(q, mylist): 
    # function to print queue elements 

pythonlessons

def Predict_bbox_mp(Frames_data, Predicted_data, Processing_times):
    gpus = tf.config.experimental.list_physical_devices('GPU')
    if len(gpus) > 0:
        try: tf.config.experimental.set_memory_growth(gpus[0], True)
        except RuntimeError: print("RuntimeError in tf.config.experimental.list_physical_devices('GPU')")
    Yolo = Load_Yolo_model()
    times = []
    while True:
        if Frames_data.qsize()>0:
            image_data = Frames_data.get()

pythonlessons

from multiprocessing import Process, Queue, Pipe
import cv2
import time
import random
import colorsys
import numpy as np
import tensorflow as tf
from yolov3.configs import *
from yolov3.yolov4 import *
from tensorflow.python.saved_model import tag_constants

pythonlessons

offset = 30
sct = mss.mss()
yolo = Load_Yolo_model()
while True:
    img = np.array(sct.grab({"top": 87-offset, "left": 1920, "width": 1280, "height": 720, "mon": -1}))
    img = cv2.cvtColor(img, cv2.COLOR_RGBA2RGB)
    image, bboxes = detect_enemy(yolo, np.copy(img), input_size=YOLO_INPUT_SIZE, CLASSES=TRAIN_CLASSES, rectangle_colors=(255,0,0))
    if len(bboxes) > 0:
        CreateXMLfile("XML_Detections", str(int(time.time())), img, bboxes, read_class_names(TRAIN_CLASSES))
        print("got it")