我用串口发送单个num就可以，但是以数据包的行使就不行，而且还自动断开openmv，只能识别一次，而且打印不了

[gy5f]

Tensorflow数字识别

import sensor, image, time, os, tf, uos, gc
from pyb import UART
uart = UART(3, 9600)
net = None
labels = None

# 初始化函数
def num_init_setup():
    global sensor, net, labels, clock      # 设置为全局变量
    sensor.reset()                         # 初始化感光元件
    sensor.set_pixformat(sensor.GRAYSCALE) # 设置图像格式为灰度
    sensor.set_framesize(sensor.QVGA)      # 设置图像大小为 QVGA (320x240)
    sensor.set_windowing((240, 240))       # 设置窗口大小为 240x240
    sensor.skip_frames(10)                 # 跳过一些帧，使以上设置生效

    try:
        # 加载模型文件
        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()        # 创建时钟对象

# 主函数
def num_main():
    while 1:
        clock.tick()                # 更新FPS帧率时钟
        img = sensor.snapshot()     # 拍一张照片并返回图像

        # 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())
            # 将分类和对应的相似度以列表套元组形式返回
            predictions_list = list(zip(labels, obj.output()))
            # 打印分类和与图像中检测到的物体的对应的相似度
            #for i in range(len(predictions_list)):
                #print("%s = %f" % (predictions_list[i][0], predictions_list[i][1]))
            if max(obj.output()) > 0.7:   # 当识别到的最大的相似度大于0.7时才认为是识别到了数字
                # 将识别到的数字赋值给num
                num = labels[obj.output().index(max(obj.output()))]
                # 打印识别到的数字
                print('识别到的数字是 %s' % num)
                #uart.write('\n')
                ##uart.write("识别到了，大傻瓜！！！\r\n")
                #uart.write(num)
                num1 = bytearray([0xFE,0xBC,num,0xEF])
                uart.write(num1)
                time.sleep_ms(100)

        #print(clock.fps(), "fps")  # 打印帧率

# 程序入口
if __name__ == '__main__':
    num_init_setup()  # 执行初始化函数
    try:
        num_main()    # 执行主函数
    except:
        pass

   

[kidswong999]

import sensor, image, time, os, tf, uos, gc
from pyb import UART
uart = UART(3, 9600)
net = None
labels = None

sensor.reset()                         # 初始化感光元件
sensor.set_pixformat(sensor.GRAYSCALE) # 设置图像格式为灰度
sensor.set_framesize(sensor.QVGA)      # 设置图像大小为 QVGA (320x240)
sensor.set_windowing((240, 240))       # 设置窗口大小为 240x240
sensor.skip_frames(10)                 # 跳过一些帧，使以上设置生效

try:
    # 加载模型文件
    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()        # 创建时钟对象


while True:
    clock.tick()                # 更新FPS帧率时钟
    img = sensor.snapshot()     # 拍一张照片并返回图像

    # 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())
        # 将分类和对应的相似度以列表套元组形式返回
        predictions_list = list(zip(labels, obj.output()))
        # 打印分类和与图像中检测到的物体的对应的相似度
        #for i in range(len(predictions_list)):
            #print("%s = %f" % (predictions_list[i][0], predictions_list[i][1]))
        if max(obj.output()) > 0.7:   # 当识别到的最大的相似度大于0.7时才认为是识别到了数字
            # 将识别到的数字赋值给num
            num = labels[obj.output().index(max(obj.output()))]
            # 打印识别到的数字
            print('识别到的数字是 %s' % num)
            #uart.write('\n')
            ##uart.write("识别到了，大傻瓜！！！\r\n")
            #uart.write(num)
            num1 = bytearray([0xFE,0xBC,obj.output().index(max(obj.output())),0xEF])
            uart.write(num1)
            time.sleep_ms(100)

    #print(clock.fps(), "fps")  # 打印帧率