keras 从TensorFlow到OpenMV的任何示例工作流？

bd1hkmkf 于 2023-04-06 发布在其他

关注(0)|答案(1)|浏览(215)

我在MobileNet-V2上训练了一个图像多分类模型（只增加了Dense层），并进行了全整数量化（INT 8），然后导出model.tflite文件，使用TF Class（）调用该模型。
下面是我的代码来量化它：

import tensorflow as tf
import numpy as np
import pathlib

def representative_dataset():
    for _ in range(100):
        data = np.random.rand(1, 96, 96, 3)  // random tensor for test
        yield [data.astype(np.float32)]

converter = tf.lite.TFLiteConverter.from_saved_model('saved_model/my_model')
converter.optimizations = [tf.lite.Optimize.DEFAULT]
converter.representative_dataset = representative_dataset
tflite_quant_model = converter.convert()

tflite_models_dir = pathlib.Path("/tmp/mnist_tflite_models/")
tflite_models_dir.mkdir(exist_ok=True, parents=True)

tflite_model_quant_file = tflite_models_dir/"mnist_model_quant.tflite"
tflite_model_quant_file.write_bytes(tflite_quant_model)

在训练时的测试中，该模型的准确率相当不错。然而，在openmv上测试时，所有对象都输出相同的标签（尽管概率略有不同）。
我查了一些资料，其中一个提到TF Classify（）有offset和scale参数，这与训练时将RGB值压缩到[-1，0]或[0，1]有关，但官方API文档中没有这个参数。

for obj in tf.classify(self.net , img1, min_scale=1.0, scale_mul=0.5, x_overlap=0.0, y_overlap=0.0):
          print("**********\nTop 1 Detections at [x=%d,y=%d,w=%d,h=%d]" % obj.rect())
          sorted_list = sorted(zip(self.labels, obj.output()), key = lambda x: x[1], reverse = True)
          for i in range(1):
          print("%s = %f" % (sorted_list[i][0], sorted_list[i][1]))
          return sorted_list[i][0]

那么有没有从tensorflow训练模型到部署到openmv的工作流程的例子呢？

keras

来源：https://stackoverflow.com/questions/71734880/any-example-workflow-from-tensorflow-to-openmv

1条答案

按热度按时间

q5lcpyga1#

好吧，你确实在1年前问过这个问题，但我还是来帮你的！
如果你想为OpenMV H7 Plus训练一个图像分类模型，你可以查看这个repo。
你也可以用这段代码来推断它们：

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()

    # 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")

希望能有所帮助！

赞(0）回复(0）举报 2023-04-06

我来回答

keras 从TensorFlow到OpenMV的任何示例工作流？

1条答案

相关问题

热门标签

最新问答