pimy 发布的帖子

pimy

@kidswong999 我想让他慢一些，但是我改变1500这个地方的数值大小没有作用

pimy

可以注意一下缩进

pimy

import pyb

s1 = pyb.Servo(1)   # create a servo object on position P7 #在P7引脚创建servo对象
s2 = pyb.Servo(2)   # create a servo object on position P8 #在P8引脚创建servo对象

s1.angle(45)        # move servo 1 to 45 degrees #将servo1移动到45度
s2.angle(0)         # move servo 2 to 0 degrees #将servo2移动到0度

# move servo1 and servo2 synchronously, taking 1500ms #同步移动servo1和servo2，耗时1500ms
s1.angle(-60, 1500)
s2.angle(30, 1500)

s1.angle(-60, 1500)我对这个函数就行数值修改，舵机运行速度并没有得到改善

pimy

舵机云台如何自己定义他的0度

pimy

CSDN上有解决办法，或者看最新的官网视频交通那个

pimy

别沉啊。。。。。。。。

pimy

要嘛自己加点锡膏吹一下要嘛就寄回去修

pimy

# Edge Impulse - OpenMV Image Classification Example

import sensor, image, time, os, tf, uos, gc

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)          # Let the camera adjust.

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:
    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()
while(True):
    clock.tick()

    img = sensor.snapshot()
    roil = (3,35,62,92)
    # default settings just do one detection... change them to search the image...
    for obj in net.classify(img,roi=roil,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]))
            
    roir = (126,35,62,92)
    # default settings just do one detection... change them to search the image...
    for obj in net.classify(img,roi=roir,min_scale=1.0, scale_mul=0.8, x_overlap=0.5, y_overlap=0.5):
        print("**********\nPredictions2 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_list2 = list(zip(labels, obj.output()))
        for p in range(len(predictions_list2)):
            
            print("%s = %f" % (predictions_list2[p][0], predictions_list2[p][1]))
        print(clock.fps(), "fps")

Predictions at [x=3,y=35,w=62,h=92]
0 = 0.000000
4 = 0.000000
8 = 0.996094

Predictions2 at [x=126,y=35,w=62,h=92]
0 = 0.996094
4 = 0.000000
8 = 0.000000
5.22268 fps

左边识别8右边识别4 但是右边roi中没有识别到

pimy

@kidswong999 改了之后问题还是没有得到解决右边还是一点没有

pimy

# Template Matching Example - Normalized Cross Correlation (NCC)
#
# This example shows off how to use the NCC feature of your OpenMV Cam to match
# image patches to parts of an image... expect for extremely controlled enviorments
# NCC is not all to useful.
#
# WARNING: NCC supports needs to be reworked! As of right now this feature needs
# a lot of work to be made into somethin useful. This script will reamin to show
# that the functionality exists, but, in its current state is inadequate.

import time, sensor, image,os,tf
from image import SEARCH_EX, SEARCH_DS
from pyb import UART
#从imgae模块引入SEARCH_EX和SEARCH_DS。使用from import仅仅引入SEARCH_EX,
#SEARCH_DS两个需要的部分，而不把image模块全部引入。
uart = UART(3, 9600)
# Reset sensor
sensor.reset()

# Set sensor settings
# Max resolution for template matching with SEARCH_EX is QQVGA
sensor.set_framesize(sensor.QQVGA)
# You can set windowing to reduce the search image.
#sensor.set_windowing(((640-80)//2, (480-60)//2, 80, 60))
sensor.set_pixformat(sensor.GRAYSCALE)

net = "trained.tflite"
labels = [line.rstrip('\n') for line in open("labels.txt")]

# Load template.
# Template should be a small (eg. 32x32 pixels) grayscale image.
template1 = ["/1.pgm"]
template2 = ["/2.pgm"]
template3 = ["/3.pgm","/3a.pgm","/3b.pgm"]
template4 = ["/4.pgm","/4a.pgm","/4b.pgm"]
template5 = ["/5.pgm","/5a.pgm","/5b.pgm"]
template6 = ["/6.pgm","/6a.pgm","/6b.pgm"]
template7 = ["/7.pgm","/7a.pgm","/7b.pgm"]
template8 = ["/8.pgm","/8a.pgm","/8b.pgm"]

A0=1
A9=1
B0=1
A1=0
A2=0
A3=0
A4=0
A5=0
A6=0
A7=0
A8=0
B0=1
C0=1
C1=0
C2=1
D0=1
D1=1


#加载模板图片

clock = time.clock()

# Run template matching
while (True):
        clock.tick()
        img = sensor.snapshot()
        while(A0):
            clock.tick()
            img = sensor.snapshot()
            t1 = image.Image(template1[0])
            r1 = img.find_template(t1, 0.80, step=4, search=SEARCH_EX) #, roi=(10, 0, 60, 60))
            if r1:
                img.draw_rectangle(r1)
                A1=1
                A0=0
            t2 = image.Image(template2[0])
            r2 = img.find_template(t2, 0.80, step=4, search=SEARCH_EX) #, roi=(10, 0, 60, 60))
            if r2:
                img.draw_rectangle(r2)
                A2=1
                A0=0
            t3 = image.Image(template3[0])
            r3 = img.find_template(t3, 0.85, step=4, search=SEARCH_EX) #, roi=(10, 0, 60, 60))
            if r3:
                img.draw_rectangle(r3)
                print('3') #打印模板名字
                A3=1
                A0=0
            t4 = image.Image(template4[0])
            r4 = img.find_template(t4, 0.80, step=4, search=SEARCH_EX) #, roi=(10, 0, 60, 60))
            if r4:
                img.draw_rectangle(r4)
                print('4') #打印模板名字
                A4=1
                A0=0
            t5 = image.Image(template5[0])
            r5 = img.find_template(t5, 0.80, step=4, search=SEARCH_EX) #, roi=(10, 0, 60, 60))
            if r5:
                img.draw_rectangle(r5)
                print('5') #打印模板名字
                A5=1
                A0=0
            t6 = image.Image(template6[0])
            r6 = img.find_template(t6, 0.80, step=4, search=SEARCH_EX) #, roi=(10, 0, 60, 60))
            if r6:
                img.draw_rectangle(r6)
                print('6') #打印模板名字
                A6=1
                A0=0
            t7 = image.Image(template7[0])
            r7 = img.find_template(t7, 0.80, step=4, search=SEARCH_EX) #, roi=(10, 0, 60, 60))
            if r7:
                img.draw_rectangle(r7)
                print('7') #打印模板名字
                A7=1
                A0=0
            t8 = image.Image(template8[0])
            r8 = img.find_template(t8, 0.85, step=4, search=SEARCH_EX) #, roi=(10, 0, 60, 60))
            if r8:
                img.draw_rectangle(r8)
                print('8') #打印模板名字
                A8=1
                A0=0

        while(A9):
            if A1==1:
                uart.write('1')
                print('1') #打印模板名字
                num=1
                A9=0
            if A2==1:
                uart.write('2')
                print('2') #打印模板名字
                num=2
                A9=0
            if A3==1:
                uart.write('3')
                print('3')
                num=3
                A9=0
            if A4==1:
                uart.write('4')
                print('4')
                num=4
                A9=0
            if A5==1:
                uart.write('5')
                print('5')
                num=5
                A9=0
            if A6==1:
                uart.write('6')
                print('6')
                num=6
                A9=0
            if A7==1:
                uart.write('7')
                print('7')
                num=7
                A9=0
            if A8==1:
                uart.write('8')
                print('8')
                num=8
                A9=0

        while(True):
            while(B0):
                    if (uart.any()):
                        B = uart.read()
                        print(B)
                        if B==b'1':
                            print("1")
                            B0=0
                            C0=1
            while(C0):
                img = sensor.snapshot()
                roiL=(20,43,53,60)
                for obj in tf.classify(net, img, roiL,min_scale=1, 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())
                    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]))
                    num1=ord(predictions_list[i][0])-48
                    if predictions_list[i][1]>0.7 and num1==num:
                        uart.write('1')
                        B0=1
                        print('11')
                        C1=1
                        C0=0
                roiR=(89,43,53,60)
                for obj in tf.classify(net, img, roiR,min_scale=1, scale_mul=0.8, x_overlap=0.5, y_overlap=0.5):
                    print("**********\nPredictions2 at [x=%d,y=%d,w=%d,h=%d]" % obj.rect())
                    img.draw_rectangle(obj.rect())
                    predictions_list2 = list(zip(labels, obj.output()))
                for p in range(len(predictions_list2)):
                    print("%s = %f" % (predictions_list2[p][0], predictions_list2[p][1]))
                    num2=ord(predictions_list2[p][0])-48
                    if predictions_list2[p][1]>0.7 and num2 == num:
                        uart.write('2')
                        B0=1
                        print("22")
                        C1=1
                        C0=0
                if C1==0:
                    uart.write('0')
                    print("00")
            print(clock.fps(), "fps")

我用这个程序跑神经网络然后出现roiL 和roiR识别差距拍的右边的模板进行训练但是是左边秒识别右边一点都识别不了

pimy

模板匹配只能用灰度图吗？

pimy

版本固件是否对神经网络有影响 opemv plus