上傳檔案到 'IDS_detection'

IDS_detection/IDS_freeze_trigger.py

@@ -0,0 +1,542 @@
+from ctypes import *
+from pyueye import ueye
+import numpy as np
+import cv2
+import sys
+import ctypes
+import struct
+import threading
+import time
+import datetime
+import os
+import pymysql
+import tensorflow as tf
+import requests as req
+import sys
+import mysql.connector
+from mysql.connector import Error
+from urllib import parse
+from PIL import Image
+
+
+
+#setting
+#-------------------------------------------------------------------------------
+hCam = ueye.HIDS(0)
+sensor_info = ueye.SENSORINFO()
+camera_info = ueye.CAMINFO()
+pcImageMemory = ueye.c_mem_p()
+MemID = ueye.int()
+rectAOI = ueye.IS_RECT()
+rectAOI.s32X     = 100
+rectAOI.s32Y     = 100
+rectAOI.s32Width = 800
+rectAOI.s32Height = 600
+pitch = ueye.INT()
+nBitsPerPixel = ueye.INT(24)    #24: bits per pixel for color mode; take 8 bits per pixel for monochrome
+channels = 3                    #3: channels for color mode(RGB); take 1 channel for monochrome
+m_nColorMode = ueye.INT()		# Y8/RGB16/RGB24/REG32
+bytes_per_pixel = int(nBitsPerPixel / 8)
+dZoomValue = ueye.DOUBLE()
+#fps = ueye.DOUBLE(60) # set you want fps
+Real_FPS =ueye.DOUBLE() # get real fps
+exposure_value = ueye.DOUBLE(10) # set exposure value
+cbSizeOfParam = 8
+BurstSize = ueye.UINT(1)
+status_new=0
+status_old=0
+trigger_delay_time = ueye.UINT(0)
+#-------------------------------------------------------------------------------
+
+
+print("START")
+# Starts the driver and establishes the connection to the camera
+nRet = ueye.is_InitCamera(hCam, None)
+if nRet != ueye.IS_SUCCESS:
+    ueye.is_InitCamera(hCam, None)
+    #print("is_InitCamera ERROR")
+
+nRet = ueye.is_SetExternalTrigger(hCam, ueye.IS_SET_TRIGGER_HI_LO)
+if nRet != ueye.IS_SUCCESS:
+    print("is_SetExternalTrigger ERROR")
+
+nRet = ueye.is_SetTriggerDelay(hCam,trigger_delay_time)
+if nRet != ueye.IS_SUCCESS:
+    print("is_SetTriggerDelay ERROR")
+print(nRet)
+
+nRet = ueye.is_Trigger(hCam, ueye.IS_TRIGGER_CMD_SET_BURST_SIZE,BurstSize,ueye.sizeof(BurstSize))
+if nRet != ueye.IS_SUCCESS:
+    print("is_Trigger ERROR")
+
+# Reads out the data hard-coded in the non-volatile camera memory and writes it to the data structure that cInfo points to
+nRet = ueye.is_GetCameraInfo(hCam, camera_info)
+if nRet != ueye.IS_SUCCESS:
+    print("is_GetCameraInfo ERROR")
+
+# You can query additional information about the sensor type used in the camera
+nRet = ueye.is_GetSensorInfo(hCam, sensor_info)
+if nRet != ueye.IS_SUCCESS:
+    print("is_GetSensorInfo ERROR")
+'''
+nRet = ueye.is_ResetToDefault(hCam)
+if nRet != ueye.IS_SUCCESS:
+    print("is_ResetToDefault ERROR")
+'''
+# Set display mode to DIB
+nRet = ueye.is_SetDisplayMode(hCam, ueye.IS_SET_DM_DIB)
+
+# Set the right color mode
+if int.from_bytes(sensor_info.nColorMode.value, byteorder='big') == ueye.IS_COLORMODE_BAYER:
+    # setup the color depth to the current windows setting
+    ueye.is_GetColorDepth(hCam, nBitsPerPixel, m_nColorMode)
+    bytes_per_pixel = int(nBitsPerPixel / 8)
+    print("IS_COLORMODE_BAYER: ", )
+    print("\tm_nColorMode:", m_nColorMode)
+    print("\tnBitsPerPixel:", nBitsPerPixel)
+    print("\tbytes_per_pixel:", bytes_per_pixel)
+
+elif int.from_bytes(sensor_info.nColorMode.value, byteorder='big') == ueye.IS_COLORMODE_CBYCRY:
+    # for color camera models use RGB32 mode
+    m_nColorMode = ueye.IS_CM_BGRA8_PACKED
+    nBitsPerPixel = ueye.INT(32)
+    bytes_per_pixel = int(nBitsPerPixel / 8)
+    print("IS_COLORMODE_CBYCRY: ", )
+    print("\tm_nColorMode: \t\t", m_nColorMode)
+    print("\tnBitsPerPixel: \t\t", nBitsPerPixel)
+    print("\tbytes_per_pixel: \t\t", bytes_per_pixel)
+
+elif int.from_bytes(sensor_info.nColorMode.value, byteorder='big') == ueye.IS_COLORMODE_MONOCHROME:
+    # for color camera models use RGB32 mode
+    m_nColorMode = ueye.IS_CM_MONO8
+    nBitsPerPixel = ueye.INT(8)
+    bytes_per_pixel = int(nBitsPerPixel / 8)
+    print("IS_COLORMODE_MONOCHROME: ", )
+    print("\tm_nColorMode: \t\t", m_nColorMode)
+    print("\tnBitsPerPixel: \t\t", nBitsPerPixel)
+    print("\tbytes_per_pixel: \t\t", bytes_per_pixel)
+else:
+    # for monochrome camera models use Y8 mode
+    m_nColorMode = ueye.IS_CM_MONO8
+    nBitsPerPixel = ueye.INT(8)
+    bytes_per_pixel = int(nBitsPerPixel / 8)
+    print("else")
+
+'''
+nRet = ueye.is_AOI(hCam, ueye.IS_AOI_IMAGE_SET_AOI, rectAOI, ueye.sizeof(rectAOI))
+if nRet != ueye.IS_SUCCESS:
+    print("is_AOI ERROR")
+'''
+# Can be used to set the size and position of an "area of interest"(AOI) within an image
+nRet = ueye.is_AOI(hCam, ueye.IS_AOI_IMAGE_GET_AOI, rectAOI, ueye.sizeof(rectAOI))
+if nRet != ueye.IS_SUCCESS:
+    print("is_AOI ERROR")
+width = rectAOI.s32Width
+height = rectAOI.s32Height
+
+print("Exposure value : {}".format(exposure_value))
+print("Maximum image width:", width)
+print("Maximum image height:", height)
+# ---------------------------------------------------------------------------------------------------------------------------------------
+# Allocates an image memory for an image having its dimensions defined by width and height and its color depth defined by nBitsPerPixel
+nRet = ueye.is_AllocImageMem(hCam, width, height, nBitsPerPixel, pcImageMemory, MemID)
+if nRet != ueye.IS_SUCCESS:
+    print("is_AllocImageMem ERROR")
+else:
+    # Makes the specified image memory the active memory
+    nRet = ueye.is_SetImageMem(hCam, pcImageMemory, MemID)
+    if nRet != ueye.IS_SUCCESS:
+        print("is_SetImageMem ERROR")
+    else:
+        # Set the desired color mode
+        nRet = ueye.is_SetColorMode(hCam, m_nColorMode)
+
+# Activates the camera's live video mode (free run mode)
+nRet = ueye.is_FreezeVideo(hCam, ueye.IS_DONT_WAIT)
+if nRet != ueye.IS_SUCCESS:
+    print("is_FreezeVideo ERROR")
+
+# Enables the queue mode for existing image memory sequences
+nRet = ueye.is_InquireImageMem(hCam, pcImageMemory, MemID, width, height, nBitsPerPixel, pitch)
+if nRet != ueye.IS_SUCCESS:
+    print("is_InquireImageMem ERROR")
+else:
+    print("Press q to leave the programm")
+# ---------------------------------------------------------------------------------------------------------------------------------------
+Count=0
+
+
+def cut_rectangle():
+    image_size = 150
+    # img = cv2.imread("D:\\fatwolf\\company_files\\opencv\\2021-05-05-11_13_47.png")
+    # img = cv2.imread("D:\\fatwolf\\company_files\\opencv\\2.png")
+    #img = cv2.imread("C:\\Users\\User\\Desktop\\tfcoffebean\\test\\1.png")
+    # img = cv2.imread("C:\\Users\\User\\Desktop\\IDS\\p\\12033_248.png")
+    # img_size = img.shape
+    # print(img_size)
+    img = cv2.imread('D:\\fatwolf\\company_files\\python_code\\test_code\\test_pic\\12033_267.png')
+
+    # img = cv2.resize(img1,(968,548))
+    point_color = (0, 0, 255)
+    command1 = "SELECT Name,X, X1 ,Y ,Y1 FROM `cut` WHERE Name LIKE 'roi1'"
+    l = conn.cursor()
+    l.execute(command1)
+    conn.commit()
+    r1 = l.fetchone()
+
+    # print(r1[0])
+    count = 1
+    def roi1():
+        # x = r1[1]
+        # x1 = r1[2]
+        # y = r1[3]
+        # y1 = r1[4]
+        #x = 743
+        #x1 = 892
+        #y = 17
+        #y1 = 164
+        x = 1257
+        x1 = 1355
+        y = 185
+        y1 = 278
+        i = 1
+        i1 = 1
+        i2 = 1
+        i3 = 1
+        i4 = 1
+        i5 = 1
+        i6 = 1
+        number = count
+
+        for i in range(6):
+            roi = img[y:y1, x:x1]
+            cv2.rectangle(img, (x, y), (x1, y1), point_color, 1)
+            roi = cv2.resize(roi, (image_size, image_size), 0, 0, cv2.INTER_LINEAR)
+            cv2.imwrite('D:\\fatwolf\\company_files\\python_code\\test_code\\test_pic\\pic' + '00_' + str(number) + '.png', roi)
+            number = number + 1
+            y = y + 150
+            y1 = y1 + 150
+        x = x + 145
+        x1 = x1 + 145
+        y = 1355
+        y1 = 278
+        '''
+        for i in range(6):
+            roi = img[y:y1, x:x1]
+            cv2.rectangle(img, (x, y), (x1, y1), point_color, 1)
+            roi = cv2.resize(roi, (image_size, image_size), 0, 0, cv2.INTER_LINEAR)
+            cv2.imwrite('D:\\fatwolf\\company_files\\paper_coffee\\pic\\' + '00_' + str(number) + '.png', roi)
+            number = number + 1
+            x = x + 150
+            x1 = x1 + 150
+        y = y + 145
+        y1 = y1 + 145
+        x = 1257
+        x1 = 1355
+        '''
+        '''
+        for i1 in range(6):
+            roi = img[y:y1, x:x1]
+            cv2.rectangle(img, (x, y), (x1, y1), point_color, 1)
+            roi = cv2.resize(roi, (image_size, image_size), 0, 0, cv2.INTER_LINEAR)
+            cv2.imwrite('D:\\fatwolf\\company_files\\paper_coffee\\pic\\' + '00_' + str(number) + '.png', roi)
+            number = number + 1
+            x = x + 150
+            x1 = x1 + 150
+        y = y + 145
+        y1 = y1 + 145
+        x = 743
+        x1 = 892
+
+        for i2 in range(6):
+            roi = img[y:y1, x:x1]
+            cv2.rectangle(img, (x, y), (x1, y1), point_color, 1)
+            roi = cv2.resize(roi, (image_size, image_size), 0, 0, cv2.INTER_LINEAR)
+            cv2.imwrite('D:\\fatwolf\\company_files\\paper_coffee\\pic\\' + '00_' + str(number) + '.png', roi)
+            number = number + 1
+            x = x + 150
+            x1 = x1 + 150
+        y = y + 145
+        y1 = y1 + 145
+        x = 743
+        x1 = 892
+
+        for i3 in range(6):
+            roi = img[y:y1, x:x1]
+            cv2.rectangle(img, (x, y), (x1, y1), point_color, 1)
+            roi = cv2.resize(roi, (image_size, image_size), 0, 0, cv2.INTER_LINEAR)
+            cv2.imwrite('D:\\fatwolf\\company_files\\paper_coffee\\pic\\' + '00_' + str(number) + '.png', roi)
+            number = number + 1
+            x = x + 150
+            x1 = x1 + 150
+        y = y + 145
+        y1 = y1 + 145
+        x = 743
+        x1 = 892
+
+        for i4 in range(6):
+            roi = img[y:y1, x:x1]
+            cv2.rectangle(img, (x, y), (x1, y1), point_color, 1)
+            roi = cv2.resize(roi, (image_size, image_size), 0, 0, cv2.INTER_LINEAR)
+            cv2.imwrite('D:\\fatwolf\\company_files\\paper_coffee\\pic\\' + '00_' + str(number) + '.png', roi)
+            number = number + 1
+            x = x + 150
+            x1 = x1 + 150
+        y = y + 145
+        y1 = y1 + 145
+        x = 743
+        x1 = 892
+
+        for i5 in range(6):
+            roi = img[y:y1, x:x1]
+            cv2.rectangle(img, (x, y), (x1, y1), point_color, 1)
+            roi = cv2.resize(roi, (image_size, image_size), 0, 0, cv2.INTER_LINEAR)
+            cv2.imwrite('D:\\fatwolf\\company_files\\paper_coffee\\pic\\' + '00_' + str(number) + '.png', roi)
+            number = number + 1
+            x = x + 150
+            x1 = x1 + 150
+        y = y + 145
+        y1 = y1 + 145
+        x = 743
+        x1 = 892
+
+        for i6 in range(6):
+            roi = img[y:y1, x:x1]
+            cv2.rectangle(img, (x, y), (x1, y1), point_color, 1)
+            roi = cv2.resize(roi, (image_size, image_size), 0, 0, cv2.INTER_LINEAR)
+            cv2.imwrite('D:\\fatwolf\\company_files\\paper_coffee\\pic\\' + '00_' + str(number) + '.png', roi)
+            number = number + 1
+            x = x + 150
+            x1 = x1 + 150
+        y = y + 145
+        y1 = y1 + 145
+        x = 743
+        x1 = 892
+    '''
+    start = datetime.datetime.now()
+    roi1()
+    end = datetime.datetime.now()
+    print("cut_rectangle Run Time：", end - start)
+
+
+def cnn():
+    # data file
+
+    data_dir = r"D:\\fatwolf\\company_files\\python_code\\test_code\\test_pic\\pic"
+
+    print(data_dir)
+    allName = os.listdir(data_dir)
+
+    # train or test
+    train = False
+    # model address
+    model_path = "model/image_model"
+    allTestDataName = []
+
+    def read_data(data_dir):
+        datas = []
+        labels = []
+        fpaths = []
+        for filename in os.listdir(data_dir):
+            fpath = os.path.join(data_dir, filename)
+            allTestDataName.append(filename)
+            image = Image.open(fpath)
+            data = np.array(image) / 255.0
+            label = int(filename.split("_")[0])
+            datas.append(data)
+            labels.append(label)
+            # allTestDataName.append(filename)
+
+        datas = np.array(datas)
+        labels = np.array(labels)
+        allTestDataName.sort(key=lambda x: int(x[:-4]))
+        # print(allTestDataName)
+
+        # print("shape of datas: {}\tshape of labels: {}".format(datas.shape, labels.shape))
+        return allTestDataName, datas, labels
+
+    allTestDataName, datas, labels = read_data(data_dir)
+    # num_classes = len(set(labels))
+    num_classes = 4
+
+    datas_placeholder = tf.compat.v1.placeholder(tf.float32, [None, 150, 150, 3])
+
+    labels_placeholder = tf.compat.v1.placeholder(tf.int32, [None])
+
+    dropout_placeholdr = tf.compat.v1.placeholder(tf.float32)
+
+    conv0 = tf.layers.conv2d(datas_placeholder, 20, 5, activation=tf.nn.relu)
+    pool0 = tf.layers.max_pooling2d(conv0, [2, 2], [2, 2])
+
+    conv1 = tf.layers.conv2d(pool0, 40, 4, activation=tf.nn.relu)
+    pool1 = tf.layers.max_pooling2d(conv1, [2, 2], [2, 2])
+
+    flatten = tf.layers.flatten(pool1)
+
+    fc = tf.layers.dense(flatten, 400, activation=tf.nn.relu)
+
+    dropout_fc = tf.layers.dropout(fc, dropout_placeholdr)
+
+    logits = tf.layers.dense(dropout_fc, num_classes)
+
+    predicted_labels = tf.arg_max(logits, 1)
+
+    losses = tf.nn.softmax_cross_entropy_with_logits(
+        labels=tf.one_hot(labels_placeholder, num_classes),
+        logits=logits
+    )
+    mean_loss = tf.reduce_mean(losses)
+
+    optimizer = tf.compat.v1.train.AdamOptimizer(learning_rate=1e-2).minimize(losses)
+
+    saver = tf.compat.v1.train.Saver()
+
+    with tf.compat.v1.Session() as sess:
+
+        if train:
+            print("train mode")
+
+            sess.run(tf.global_variables_initializer())
+
+            train_feed_dict = {
+                datas_placeholder: datas,
+                labels_placeholder: labels,
+                dropout_placeholdr: 0.25
+            }
+            for step in range(500):
+                _, mean_loss_val = sess.run([optimizer, mean_loss], feed_dict=train_feed_dict)
+
+                if step % 50 == 0:
+                    print("step = {}\tmean loss = {}".format(step, mean_loss_val))
+            saver.save(sess, model_path)
+            print("train done save model{}".format(model_path))
+        else:
+            # print("reloading model")
+            saver.restore(sess, model_path)
+            # print("{}reload model".format(model_path))
+
+            label_name_dict = {
+                0: "Brokenbeans",
+                1: "Peaberry",
+                2: "shellbean",
+                3: "Worms"
+            }
+            test_feed_dict = {
+                datas_placeholder: datas,
+                labels_placeholder: labels,
+                dropout_placeholdr: 0
+            }
+            predicted_labels_val = sess.run(predicted_labels, feed_dict=test_feed_dict)
+
+            for fpath, real_label, predicted_label in zip(allTestDataName, labels, predicted_labels_val):
+                real_label_name = label_name_dict[real_label]
+                # print("訓練前",real_label_name)
+                predicted_label_name = label_name_dict[predicted_label]
+                # print("訓練後",predicted_label_name)
+                # print("{}\t => {}".format(fpath, predicted_label_name))
+                fpath = os.path.basename(fpath)
+
+                print(f"{fpath}\t => {predicted_label_name}")
+                path1 = 'output.txt'
+                f = open(path1, 'a+')
+                f.write(f"{fpath} => {predicted_label_name}""\n")
+                f.close()
+                if predicted_label_name == "shellbean" or "Peaberry" or "Worms":
+                    print("觸發噴嘴")
+                else:
+                    print('沒有觸發')
+                '''
+                sqlStuff = "INSERT INTO result(picname,identify)""VALUES (%s,%s)"
+                data = [(fpath, predicted_label_name)]
+                a = conn.cursor()
+                a.executemany(sqlStuff, data)
+                conn.commit()
+
+                try:
+                    connection = mysql.connector.connect(
+                        host='127.0.0.1',  # 主機名稱
+                        database='coffee_detection',  # 資料庫名稱
+                        user='root',  # 帳號
+                        password='g53743001')  # 密碼
+                    # 新增資料
+                    sql = "INSERT INTO result(picname,identify)""VALUES (%s,%s)"
+                    new_data = ("test", "test2")
+                    cursor = connection.cursor()
+                    cursor.execute(sql, new_data)
+
+                    # 確認資料有存入資料庫
+                    connection.commit()
+
+                except Error as e:
+                    print("資料庫連接失敗：", e)
+
+                finally:
+                    if (connection.is_connected()):
+                        cursor.close()
+                        connection.close()
+
+                '''
+            dirListing = os.listdir(data_dir)
+            # print(len(dirListing))
+
+
+
+
+
+
+
+# Continuous image display
+while (nRet == ueye.IS_SUCCESS):
+    # In order to display the image in an OpenCV window we need to...
+    # ...extract the data of our image memory
+    array = ueye.get_data(pcImageMemory, width, height, nBitsPerPixel, pitch, copy=False)
+    frame = np.reshape(array, (height.value, width.value, bytes_per_pixel))
+    #frame = cv2.resize(frame, (1280,1024), fx=0.5, fy=0.5)
+    cv2.imshow("SimpleLive_Python_uEye_OpenCV", frame)
+    trigger_status = ueye.is_SetExternalTrigger(hCam,ueye.IS_GET_TRIGGER_STATUS)
+    status_new = trigger_status
+    print(status_old, status_new)
+
+    if status_old == 1 and status_new == 0:
+        #for i in range(1):
+        now = time.strftime("%Y-%m-%d-%H_%M_%S", time.localtime(time.time()))
+        FileParams = ueye.IMAGE_FILE_PARAMS()
+        FileParams.pwchFileName = "C:/Users/User/Desktop/IDS/test/status04/" + now + ".png"
+        FileParams.nFileType = ueye.IS_IMG_PNG
+        FileParams.ppcImageMem = None
+        FileParams.pnImageID = None
+        FileParams.nQuality = 10
+        nRet1 = ueye.is_ImageFile(hCam, ueye.IS_IMAGE_FILE_CMD_SAVE, FileParams, ueye.sizeof(FileParams))
+        print('take photo')
+        nRet1 = ueye.is_FreezeVideo(hCam, ueye.IS_DONT_WAIT)
+    status_old = status_new
+    start3 = datetime.datetime.now()
+
+    time.sleep(0.3)
+    print(Count)
+    print(nRet)
+    end3 = datetime.datetime.now()
+    print("拍照執行時間：", end3 - start3)
+
+    cut_rectangle()
+    start2 = datetime.datetime.now()
+    cnn()
+    end2 = datetime.datetime.now()
+    print("辨識執行時間：", end2 - start2)
+    #end = datetime.datetime.now()
+
+    #print("完整執行時間：", end - start)
+    print('-----------------------------------------------------------')
+    tf.reset_default_graph()
+
+    # Press q if you want to end the loop
+    if cv2.waitKey(1) & 0xFF == ord('q'):
+        break
+
+# ---------------------------------------------------------------------------------------------------------------------------------------
+# Releases an image memory that was allocated using is_AllocImageMem() and removes it from the driver management
+ueye.is_FreeImageMem(hCam, pcImageMemory, MemID)
+# Disables the hCam camera handle and releases the data structures and memory areas taken up by the uEye camera
+ueye.is_ExitCamera(hCam)
+# Destroys the OpenCv windows
+cv2.destroyAllWindows()