Mobilenet V1的训练后量化不起作用 [英] post training quantization for mobilenet V1 not working
问题描述
我正在尝试将mobilenet V1 .pb文件转换为量化的tflite文件.我使用以下命令进行量化:
I am trying to convert mobilenet V1 .pb file to quantized tflite file. I used the below command to do the quantization:
tflite_convert \
--output_file=/home/wc/users/Mostafiz/TPU/models/mobilnet/test2_4thSep/mobilenetv1_test5.tflite \
--graph_def_file=/home/wc/users/Mostafiz/TPU/models/mobilnet/mobileNet_frozen_graph.pb \
--output_format=TFLITE \
--inference_type=QUANTIZED_UINT8 \
--inference_input_type=QUANTIZED_UINT8 \
--input_shape=1,224,224,3 \
--input_array=input \
--output_array=MobilenetV1/Predictions/Reshape_1 \
--inference_output_type=QUANTIZED_UINT8 \
--default_ranges_min=0 \
--default_ranges_max=6 \
--std_dev_values=127 \
--mean_value=128
.tflile文件创建成功,没有任何错误.但是,当我尝试使用.tflile进行推理时,输出类混乱了.没有测试图像给出正确的结果.
The .tflile file is created without any error. But when I am trying to use the .tflile for inference the output classes are messed up. None of the test images are giving correct result.
不确定我在哪里做错了,有人可以帮我吗?
Not sure where I am doing wrong, can someone please help me?
为了进行推断,我使用了tensorflow提供的'label_image.py'.这是代码:
For inference I am using 'label_image.py' provided by tensorflow. here is the code:
"""label_image for tflite"""
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import argparse
import numpy as np
from PIL import Image
from tensorflow.lite.python import interpreter as interpreter_wrapper
def load_labels(filename):
my_labels = []
input_file = open(filename, 'r')
for l in input_file:
my_labels.append(l.strip())
return my_labels
if __name__ == "__main__":
floating_model = False
parser = argparse.ArgumentParser()
parser.add_argument("-i", "--image", default="/tmp/grace_hopper.bmp", \
help="image to be classified")
parser.add_argument("-m", "--model_file", \
default="/tmp/mobilenet_v1_1.0_224_quant.tflite", \
help=".tflite model to be executed")
parser.add_argument("-l", "--label_file", default="/tmp/labels.txt", \
help="name of file containing labels")
parser.add_argument("--input_mean", default=127.5, help="input_mean")
parser.add_argument("--input_std", default=127.5, \
help="input standard deviation")
args = parser.parse_args()
interpreter = interpreter_wrapper.Interpreter(model_path=args.model_file)
interpreter.allocate_tensors()
input_details = interpreter.get_input_details()
output_details = interpreter.get_output_details()
# check the type of the input tensor
if input_details[0]['dtype'] == np.float32:
floating_model = True
# NxHxWxC, H:1, W:2
height = input_details[0]['shape'][1]
width = input_details[0]['shape'][2]
img = Image.open(args.image)
img = img.resize((width, height))
# add N dim
input_data = np.expand_dims(img, axis=0)
if floating_model:
input_data = (np.float32(input_data) - args.input_mean) / args.input_std
interpreter.set_tensor(input_details[0]['index'], input_data)
interpreter.invoke()
output_data = interpreter.get_tensor(output_details[0]['index'])
results = np.squeeze(output_data)
top_k = results.argsort()[-5:][::-1]
labels = load_labels(args.label_file)
for i in top_k:
if floating_model:
print('{0:08.6f}'.format(float(results[i]))+":", labels[i])
else:
print('{0:08.6f}'.format(float(results[i]/255.0))+":", labels[i])
谢谢.
推荐答案
虚拟量化可能无法正常工作,因为我们需要猜测激活函数的default_max和defual_min值.
The dummy quantization may not work properly as we need to guess the default_max and defual_min values for activation functions.
正如Sudarsh在评论中提到的,我们应该进行后期训练全整数量化,以将.pb转换为INT8 tflite文件.
As Sudarsh mentioned in the comment, we should do a post training full integer quantization to convert .pb to INT8 tflite file.
您可以点击此链接开始-此处
you can follow this link to start with - here
希望有帮助.
致谢.
这篇关于Mobilenet V1的训练后量化不起作用的文章就介绍到这了,希望我们推荐的答案对大家有所帮助,也希望大家多多支持IT屋!