# Edge Impulse - OpenMV Image Classification Example

import sensor, image, time, os, tf,tv

sensor.reset()                         # Reset and initialize the sensor.
sensor.set_pixformat(sensor.RGB565)    # Set pixel format to RGB565 (or GRAYSCALE)
sensor.set_framesize(sensor.SIF)      # Set frame size to QVGA (320x240)
#sensor.set_windowing((240, 240))       # Set 240x240 window.
#sensor.skip_frames(time=2000)          # Let the camera adjust.
tv.init(triple_buffer=False) # Initialize the tv.
tv.channel(8) # For wireless video transmitter shield
net = "trained.tflite"
labels = [line.rstrip('\n') for line in open("labels.txt")]

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

    img = sensor.snapshot()

    # default settings just do one detection... change them to search the image...
    for obj in tf.classify(net, 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]))
    tv.display(img)
    print(clock.fps(), "fps")

# Edge Impulse - OpenMV Image Classification Example

import sensor, image, time, os, tf

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

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

    img = sensor.snapshot()

    # default settings just do one detection... change them to search the image...
    for obj in tf.classify(net, 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")

OSError: Arena size is too small for activation buffers. Needed 225840 but only 156272 was available怎么解决？

# Edge Impulse - OpenMV Image Classification Example

import sensor, image, time, os, tf

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

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

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

    img = sensor.snapshot()

    # default settings just do one detection... change them to search the image...
    for obj in tf.classify(net, 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")

# Edge Impulse - OpenMV Image Classification Example

import sensor, image, time, os, tf

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

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

    img = sensor.snapshot()

    # default settings just do one detection... change them to search the image...
    for obj in tf.classify(net, 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")![0_1620558720938_QE6UF3PLPNUPB[X4]@X_0H4.png](https://fcdn.singtown.com/19884c9c-1911-498d-83e8-328570e1e469.png) 

# Edge Impulse - OpenMV Image Classification Example

import sensor, image, time, os, tf

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

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

    img = sensor.snapshot()

    # default settings just do one detection... change them to search the image...
    for obj in tf.classify(net, 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")

口罩识别报错

# Edge Impulse - OpenMV Image Classification Example

import sensor, image, time, os, tf

sensor.reset()                         # Reset and initialize the sensor.
sensor.set_pixformat(sensor.GRAYSCALE)    # 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 = "trained.tflite"
labels = [line.rstrip('\n') for line in open("labels.txt")]

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

    img = sensor.snapshot()

    # default settings just do one detection... change them to search the image...
    for obj in tf.classify(net, 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")

# Blob Detection and uart transport
import sensor, image, time
from pyb import UART
import json
# For color tracking to work really well you should ideally be in a very, very,
# very, controlled enviroment where the lighting is constant...
red_threshold   = (9,47,17,45,-6,29)
# You may need to tweak the above settings for tracking green things...
# Select an area in the Framebuffer to copy the color settings.

sensor.reset() # Initialize the camera sensor.
sensor.set_pixformat(sensor.RGB565) # use RGB565.
sensor.set_framesize(sensor.QQVGA) # use QQVGA for speed.
sensor.skip_frames(10) # Let new settings take affect.
sensor.set_auto_whitebal(False) # turn this off.
clock = time.clock() # Tracks FPS.

uart = UART(3, 115200)
def find_max(blobs):
    max_size=0
    for blob in blobs:
        if blob.pixels() > max_size:
            max_blob=blob
            max_size = blob.pixels()
    return max_blob

while(True):
    img = sensor.snapshot() # Take a picture and return the image.

    blobs = img.find_blobs([red_threshold])
    if blobs:
        max_blob=find_max(blobs)
        img.draw_rectangle(max_blob.rect())
        img.draw_cross(max_blob.cx(), max_blob.cy())

        output_str="(%d,%d)\r" % (max_blob.cx(),max_blob.cy())
        #output_str=json.dumps([max_blob.cx(),max_blob.cy()]) #方式2

        uart.write(output_str)
    time.sleep_ms(300)

Edge Impulse - OpenMV Image Classification Example

import sensor, image, time, os, tf

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

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

img = sensor.snapshot()

# default settings just do one detection... change them to search the image...
for obj in tf.classify(net, 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")

在stm32传输数据给openmv4 plus 时不使用decode函数能收到准确的ascii码，在使用后接收到的没有数据。

import sensor, image, time
from pyb import UART



clock = time.clock() # Tracks FPS.
uart = UART(3,115200)   #定义串口3变量
#设置串口
uart.init(115200, bits=8, parity=None, stop=0) # init with given parameters


#图像循环
while(True):
    if uart.any():
        a = uart.readline().decode()
        print(a)
    

import sensor, image, time
from pyb import UART



clock = time.clock() # Tracks FPS.
uart = UART(3,115200)   #定义串口3变量
#设置串口
uart.init(115200, bits=8, parity=None, stop=0) # init with given parameters


#图像循环
while(True):
    if uart.any():
        a = uart.readline()
        print(a)

# Edge Impulse - OpenMV Image Classification Example

只让这个识别度最高的1输出出来，要怎么改

import sensor, image, time, os, tf

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

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

    img = sensor.snapshot()

    # default settings just do one detection... change them to search the image...
    for obj in tf.classify(net, 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]))