csm6 发布的帖子

刚刚又改了一下代码，发现不报错了，但是串行终端没有输出数据，这个代码是哪里出问题了呀？

import sensor, image, time, os, tf, uos, gc, pyb, machine,math,tf
from pyb import UART
uart = UART(3, 9600)
sensor.reset()
sensor.set_pixformat(sensor.RGB565)
sensor.set_framesize(sensor.QVGA)
sensor.set_windowing((240, 240))
sensor.skip_frames(time=2000)
sensor.set_auto_gain(False)
sensor.set_auto_whitebal(False)

net = None
labels = None

ROI = (20,20,200,200)

try:
    # load the model, alloc the model file on the heap if we have at least 64K free after loading
    net = tf.load("trained.tflite", load_to_fb=uos.stat('trained.tflite')[6] > (gc.mem_free() - (64*1024)))
except Exception as e:
    print(e)
    raise Exception('Failed to load "trained.tflite", did you copy the .tflite and labels.txt file onto the mass-storage device? (' + str(e) + ')')

try:
    labels = [line.rstrip('\n') for line in open("labels.txt")]
except Exception as e:
    raise Exception('Failed to load "labels.txt", did you copy the .tflite and labels.txt file onto the mass-storage device? (' + str(e) + ')')

clock = time.clock()

def compare():
	img1 = sensor.snapshot()
	img1.draw_rectangle(ROI)
	statistics = img1.get_statistics(roi = ROI)
	img2 = sensor.snapshot()
	img2.draw_rectangle(ROI)
	statistics2 = img2.get_statistics(roi = ROI)
	num1 = statistics.mode()
	num2 = statistics.mode()
	if(abs(num1-num2)>50):  return 1
    #print("1")return 0
	
	
def rubbish():
    clock.tick()
    
    pyb.delay(1000)

    img = sensor.snapshot()

    # default settings just do one detection... change them to search the image...
    for obj in net.classify(img, min_scale=1.0, scale_mul=0.8, x_overlap=0.5, y_overlap=0.5):
        print("**********\nPredictions at [x=%d,y=%d,w=%d,h=%d]" % obj.rect())
        img.draw_rectangle(obj.rect())
        # This combines the labels and confidence values into a list of tuples
        predictions_list = list(zip(labels, obj.output()))

        for i in range(len(predictions_list)):
            print("%s = %f" % (predictions_list[i][0], predictions_list[i][1]))
	
    print(clock.fps(), "fps")
    if (sum(predictions_list[i][1])/len(predictions_list[i][1]))>0.8:
        print(prediction_list[i][1])
        uart.write(predictions_list[i][0])
    

while(True):
    res = compare()
    if(res==1):
        print(OK)
        rubbish()
        while(True):
            if uart.any():
                notice = uart.readline().decode()
            if notice =='G':
                rubbish()

这个代码是哪里有问题吗？怎么运行不了也拍不了照片，传不了值？自动就停止运行了？跟arduino连接也没反应

import sensor, image, time, os, tf, uos, gc, pyb, machine,math,tf
from pyb import UART
uart = UART(3, 9600)
sensor.reset()
sensor.set_pixformat(sensor.RGB565)
sensor.set_framesize(sensor.QVGA)
sensor.set_windowing((240, 240))
sensor.skip_frames(time=2000)
sensor.set_auto_gain(False)
sensor.set_auto_whitebal(False)

net = None
labels = None

ROI = (20,20,200,200)

try:
    # load the model, alloc the model file on the heap if we have at least 64K free after loading
    net = tf.load("trained.tflite", load_to_fb=uos.stat('trained.tflite')[6] > (gc.mem_free() - (64*1024)))
except Exception as e:
    print(e)
    raise Exception('Failed to load "trained.tflite", did you copy the .tflite and labels.txt file onto the mass-storage device? (' + str(e) + ')')

try:
    labels = [line.rstrip('\n') for line in open("labels.txt")]
except Exception as e:
    raise Exception('Failed to load "labels.txt", did you copy the .tflite and labels.txt file onto the mass-storage device? (' + str(e) + ')')

clock = time.clock()

def compare():
	img1 = sensor.snapshot()
	img1.draw_rectangle(ROI)
	statistics = img1.get_statistics(roi = ROI)
	img2 = sensor.snapshot()
	img2.draw_rectangle(ROI)
	statistics2 = img2.get_statistics(roi = ROI)
	num1 = statistics.mode()
	num2 = statistics.mode()
	if(abs(num1-num2)>20):return 1
	else:return 0
	
	
def rubbish():
    clock.tick()
    
    pyb.delay(1000)

    img = sensor.snapshot()

    # default settings just do one detection... change them to search the image...
    for obj in net.classify(img, min_scale=1.0, scale_mul=0.8, x_overlap=0.5, y_overlap=0.5):
        print("**********\nPredictions at [x=%d,y=%d,w=%d,h=%d]" % obj.rect())
        img.draw_rectangle(obj.rect())
        # This combines the labels and confidence values into a list of tuples
        predictions_list = list(zip(labels, obj.output()))

        for i in range(len(predictions_list)):
            print("%s = %f" % (predictions_list[i][0], predictions_list[i][1]))
	
    print(clock.fps(), "fps")
    if (sum(predictions_list[i][1])/len(predictions_list[i][1]))>0.8:
        print(prediction_list[i][1])
        uart.write(predictions_list[i][0])
    else:
        rubbish()

if(compare()==1):
	rubbish()
	while(True):
		if uart.any():
			notice = uart.readline().decode()
		if notice =='G':
			rubbish()

@fmcq 在 openmv连接超声波模块，提示pix format错误 中说：

mport time,utime,pyb
from pyb import Pin

wave_echo_pin = Pin('P7', Pin.IN, Pin.PULL_NONE)
wave_trig_pin = Pin('P8', Pin.OUT_PP, Pin.PULL_DOWN)

wave_distance = 0
tim_counter = 0
flag_wave = 0

#超声波启动
def wave_start():
wave_trig_pin.value(1)
utime.sleep_us(15)
wave_trig_pin.value(0)

#超声波距离计算
def wave_distance_calculation():
#全局变量声明
global tim_counter
#频率f为0.2MHZ 高电平时间t=计数值1/f
wave_distance = tim_counter5*0.017
#输出最终的测量距离（单位cm）
print('wave_distance',wave_distance)

#超声波数据处理
def wave_distance_process():
global flag_wave
if(flag_wave == 0):
wave_start()
if(flag_wave == 2):
wave_distance_calculation()
flag_wave = 0

#配置定时器
tim =pyb.Timer(1, prescaler=720, period=65535) #相当于freq=0.2M

#外部中断配置
def callback(line):
global flag_wave,tim_counter
#上升沿触发处理
if(wave_echo_pin.value()):
tim.init(prescaler=720, period=65535)
flag_wave = 1
#下降沿
else:
tim.deinit()
tim_counter = tim.counter()
tim.counter(0)
extint.disable()
flag_wave = 2
#中断配置
extint = pyb.ExtInt(wave_echo_pin, pyb.ExtInt.IRQ_RISING_FALLING, pyb.Pin.PULL_DOWN, callback)

while(True):
wave_distance_process()
time.sleep(100)
print('wave_distance',wave_distance)

想问一下，这个代码最后是怎么实现超声波测距的吗

oenmv能外接一个超声波传感器吗？

前面打印name 一直是'c',我就把代码改成这样了，又提示了这个错误

import sensor, image, time, os, tf, uos, gc,pyb,machine
from pyb import UART
uart = UART(3,115200)


green = (10,100,-50,15,-15,50)
red = (0,100,-30,50,-30,30)
blue = (10,100,-20,40,-10,40)
orange = (10,80,-10,30,-20,35)
brown = (0,80,-10,20,-20,30)
yellow = (50,80,-10,10,-20,60)
white = (10,100,-20,30,-30,20)
gray = (20,80,-10,15,-10,25)


sensor.reset()                         # Reset and initialize the sensor.
sensor.set_pixformat(sensor.RGB565)    # Set pixel format to RGB565 (or GRAYSCALE)
sensor.set_framesize(sensor.QVGA)      # Set frame size to QVGA (320x240)
sensor.set_windowing((240, 240))       # Set 240x240 window.
sensor.skip_frames(time = 2000)
sensor.set_auto_gain(False)
sensor.set_auto_whitebal(False)
clock = time.clock()



while(True):
    clock.tick()


    def rubbish():
        net = None
        labels = None

        try:
            # load the model, alloc the model file on the heap if we have at least 64K free after loading
            net = tf.load("trained.tflite", load_to_fb=uos.stat('trained.tflite')[6] > (gc.mem_free() - (64 * 1024)))
        except Exception as e:

            raise Exception(
                'Failed to load "trained.tflite", did you copy the .tflite and labels.txt file onto the mass-storage device? (' + str(
                    e) + ')')

        try:
            labels = [line.rstrip('\n') for line in open("labels.txt")]
        except Exception as e:
            raise Exception(
                'Failed to load "labels.txt", did you copy the .tflite and labels.txt file onto the mass-storage device? (' + str(
                    e) + ')')

        image = sensor.snapshot()

        scores = net.classify(image)

        # default settings just do one detection... change them to search the image...
        for obj in net.classify(image, min_scale=1.0, scale_mul=0.8, x_overlap=0.5, y_overlap=0.5):

            image.draw_rectangle(obj.rect())
            # This combines the labels and confidence values into a list of tuples
            predictions_list = list(zip(labels, obj.output()))
            name = predictions_list[0][0]
            for i in range(len(predictions_list)):

                max = 0.8
                if predictions_list[i][1] > max:
                    max = predictions_list[i][1]
                    name = predictions_list[i][0]

            if name == 'KHSLJ':
                name = 'k'
            elif name == 'YHLJ':
                name = 'y'
            elif name == 'CYLJ':
                name = 'c'
            elif name == 'QTLJ':
                name = 'q'

        return name
        
    name = rubbish()

    img = sensor.snapshot()
    blobs1 = img.find_blobs([green])
    blobs2 = img.find_blobs([red])
    blobs3 = img.find_blobs([blue])
    blobs4 = img.find_blobs([orange])
    blobs5 = img.find_blobs([brown])
    blobs6 = img.find_blobs([yellow])
    blobs7 = img.find_blobs([white])
    blobs8 = img.find_blobs([gray])

    if blobs1:
        rubbish()
        uart.write(name)
        print(name)

    if blobs2:
        rubbish()
        uart.write(name)

    if blobs3:
        rubbish()
        uart.write(name)
    if blobs4:
        rubbish()
        uart.write(name)

    if blobs5:
        rubbish()
        uart.write(name)

    if blobs6:
        rubbish()
        uart.write(name)

    if blobs7:
        rubbish()
        uart.write(name)

    if blobs8:
        rubbish()
        uart.write(name)


# Edge Impulse - OpenMV Image Classification Example

import sensor, image, time, os, tf, uos, gc,pyb,machine
from pyb import UART
uart = UART(3,115200)


green = (10,100,-50,15,-15,50)
red = (0,100,-30,50,-30,30)
blue = (10,100,-20,40,-10,40)
orange = (10,80,-10,30,-20,35)
brown = (0,80,-10,20,-20,30)
yellow = (50,80,-10,10,-20,60)
white = (10,100,-20,30,-30,20)
gray = (20,80,-10,15,-10,25)


sensor.reset()                         # Reset and initialize the sensor.
sensor.set_pixformat(sensor.RGB565)    # Set pixel format to RGB565 (or GRAYSCALE)
sensor.set_framesize(sensor.QVGA)      # Set frame size to QVGA (320x240)
sensor.set_windowing((240, 240))       # Set 240x240 window.
sensor.skip_frames(time = 2000)
sensor.set_auto_gain(False)
sensor.set_auto_whitebal(False)
clock = time.clock()

name = 'c'

while(True):
    clock.tick()


    def rubbish():
        net = None
        labels = None

        try:
            # load the model, alloc the model file on the heap if we have at least 64K free after loading
            net = tf.load("trained.tflite", load_to_fb=uos.stat('trained.tflite')[6] > (gc.mem_free() - (64 * 1024)))
        except Exception as e:

            raise Exception(
                'Failed to load "trained.tflite", did you copy the .tflite and labels.txt file onto the mass-storage device? (' + str(
                    e) + ')')

        try:
            labels = [line.rstrip('\n') for line in open("labels.txt")]
        except Exception as e:
            raise Exception(
                'Failed to load "labels.txt", did you copy the .tflite and labels.txt file onto the mass-storage device? (' + str(
                    e) + ')')

        image = sensor.snapshot()

        scores = net.classify(image)

        # default settings just do one detection... change them to search the image...
        for obj in net.classify(image, min_scale=1.0, scale_mul=0.8, x_overlap=0.5, y_overlap=0.5):

            image.draw_rectangle(obj.rect())
            # This combines the labels and confidence values into a list of tuples
            predictions_list = list(zip(labels, obj.output()))
            name = predictions_list[0][0]
            for i in range(len(predictions_list)):

                max = 0.8
                if predictions_list[i][1] > max:
                    max = predictions_list[i][1]
                    name = predictions_list[i][0]

            if name == 'KHSLJ':
                name = 'k'
            elif name == 'YHLJ':
                name = 'y'
            elif name == 'CYLJ':
                name = 'c'
            elif name == 'QTLJ':
                name = 'q'

        return name
    img = sensor.snapshot()
    blobs1 = img.find_blobs([green])
    blobs2 = img.find_blobs([red])
    blobs3 = img.find_blobs([blue])
    blobs4 = img.find_blobs([orange])
    blobs5 = img.find_blobs([brown])
    blobs6 = img.find_blobs([yellow])
    blobs7 = img.find_blobs([white])
    blobs8 = img.find_blobs([gray])

    if blobs1:
        rubbish()
        uart.write(name)

    if blobs2:
        rubbish()
        uart.write(name)

    if blobs3:
        rubbish()
        uart.write(name)
    if blobs4:
        rubbish()
        uart.write(name)

    if blobs5:
        rubbish()
        uart.write(name)

    if blobs6:
        rubbish()
        uart.write(name)

    if blobs7:
        rubbish()
        uart.write(name)

    if blobs8:
        rubbish()
        uart.write(name)