关于moilefacenet的pb模型转换成tf.lite #14

kongdaniel · 2020-04-24T11:41:03Z

你好请问你的pb模型是这么转换到lite，模型的，我现在在tf的1.80，1.12-1.15都试过，但总是转不了，请问你当时是怎么转换的呢。

syaringan357 · 2020-04-26T05:59:45Z

import tensorflow as tf

in_path = "../output/mobilefacenet/frozen_graphs/MobileFaceNet.pb"
out_path = "../output/mobilefacenet/tflite/MobileFaceNet.tflite"

input_tensor_name = ["input"]
input_tensor_shape = {"input": [2, 112, 112, 3]}
classes_tensor_name = ["embeddings"]

converter = tf.lite.TFLiteConverter.from_frozen_graph(in_path, input_tensor_name,
classes_tensor_name, input_shapes=input_tensor_shape)
tflite_model = converter.convert()

with open(out_path, "wb") as f:
f.write(tflite_model)

kongdaniel · 2020-04-26T06:26:05Z

我用你的代码依然不行，和版本有关系吗。我是1.15现在
2020-04-26 14:16:25.685949: I tensorflow/lite/toco/graph_transformations/graph_transformations.cc:39] Before general graph transformations: 1484 operators, 2717 arrays (0 quantized)
2020-04-26 14:16:25.696619: 他报这个错F .\tensorflow/lite/toco/toco_tooling.h:38] Check failed: s.ok() Found BatchNormalization as non-selected output from Switch, but only Merge supported. Control flow ops like Switch and Merge are not generally supported. We are working on fixing this, please see the Github issue at tensorflow/tensorflow#28485.
Fatal Python error: Aborted`

kongdaniel · 2020-04-26T06:45:45Z

还是保错，这是因为什么呢，请问你使用的是他原来的pb吗，假如不是，你是否是更改了他的代码，然后使得可以转换呢。似乎他原来的代码中生成的模型有程序控制流 2020-04-26 14:25:02.322529: I tensorflow/lite/toco/graph_transformations/graph_transformations.cc:39] Before Removing unused ops: 2421 operators, 4174 arrays (0 quantized) 2020-04-26 14:25:02.711969: I tensorflow/lite/toco/graph_transformations/graph_transformations.cc:39] After Removing unused ops pass 1: 1484 operators, 2717 arrays (0 quantized) 2020-04-26 14:25:03.052979: I tensorflow/lite/toco/graph_transformations/graph_transformations.cc:39] Before general graph transformations: 1484 operators, 2717 arrays (0 quantized) 2020-04-26 14:25:03.066037: F .\tensorflow/lite/toco/toco_tooling.h:38] Check failed: s.ok() Found BatchNormalization as non-selected output from Switch, but only Merge supported. Control flow ops like Switch and Merge are not generally supported. We are working on fixing this, please see the Github issue at tensorflow/tensorflow#28485. Fatal Python error: Aborted

…

------------------ 原始邮件 ------------------ 发件人: "syaringan357"<[email protected]>; 发送时间: 2020年4月26日(星期天) 中午1:59 收件人: "syaringan357/Android-MobileFaceNet-MTCNN-FaceAntiSpoofing"<[email protected]>; 抄送: "2459431805"<[email protected]>;"Author"<[email protected]>; 主题: Re: [syaringan357/Android-MobileFaceNet-MTCNN-FaceAntiSpoofing] 关于moilefacenet的pb模型转换成tf.lite (#14)

-- coding:utf-8 -- import tensorflow as tf in_path = "../output/mobilefacenet/frozen_graphs/MobileFaceNet.pb" out_path = "../output/mobilefacenet/tflite/MobileFaceNet.tflite" 模型输入节点 input_tensor_name = ["input"] input_tensor_shape = {"input": [2, 112, 112, 3]} 模型输出节点 classes_tensor_name = ["embeddings"] converter = tf.lite.TFLiteConverter.from_frozen_graph(in_path, input_tensor_name, classes_tensor_name, input_shapes=input_tensor_shape) converter.allow_custom_ops = True #converter.post_training_quantize = True tflite_model = converter.convert() with open(out_path, "wb") as f: f.write(tflite_model) — You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub, or unsubscribe.

syaringan357 · 2020-04-27T03:03:26Z

哦，我不是用他原来那个pb转的，用他的ckpt重新固化一个pb，再转。

syaringan357 · 2020-04-27T03:06:20Z

import os
import tensorflow as tf
from nets.MobileFaceNet import inference

training_checkpoint = "../output/mobilefacenet/MobileFaceNet_TF.ckpt"
OUTPUT_DIR = '../output/mobilefacenet/frozen_graphs'

def freeze_graph_def(sess, output_node_names):
# Replace all the variables in the graph with constants of the same values
output_graph_def = tf.compat.v1.graph_util.convert_variables_to_constants(
sess, sess.graph_def, output_node_names.split(","))
return output_graph_def

def save():
data_input = tf.placeholder(name='input', dtype=tf.float32, shape=[None, 112, 112, 3])

output, _ = inference(data_input, bottleneck_layer_size=192)
tf.identity(output, name='embeddings')
init = tf.global_variables_initializer()
with tf.Session() as sess:
    sess.run(init)

    saver = tf.train.Saver()
    saver.restore(sess, training_checkpoint)

    # Freeze the graph def
    output_graph_def = freeze_graph_def(sess, 'embeddings')

    output_pnet = os.path.join(OUTPUT_DIR, 'MobileFaceNet.pb')
    # Serialize and dump the output graph to the filesystem
    with tf.gfile.GFile(output_pnet, 'wb') as f:
        f.write(output_graph_def.SerializeToString())

if name == 'main':
save()

syaringan357 · 2020-04-27T03:07:58Z

凑合看把上面都是代码

kongdaniel · 2020-04-27T13:22:01Z

凑合看把上面都是代码

谢谢大佬，跪谢。

kongdaniel · 2020-05-01T10:46:12Z

import os
import tensorflow as tf
from nets.MobileFaceNet import inference

training_checkpoint = "../output/mobilefacenet/MobileFaceNet_TF.ckpt"
OUTPUT_DIR = '../output/mobilefacenet/frozen_graphs'

def freeze_graph_def(sess, output_node_names):

Replace all the variables in the graph with constants of the same values

output_graph_def = tf.compat.v1.graph_util.convert_variables_to_constants(
sess, sess.graph_def, output_node_names.split(","))
return output_graph_def

def save():
data_input = tf.placeholder(name='input', dtype=tf.float32, shape=[None, 112, 112, 3])
output, _ = inference(data_input, bottleneck_layer_size=192)
tf.identity(output, name='embeddings')
init = tf.global_variables_initializer()
with tf.Session() as sess:
    sess.run(init)

    saver = tf.train.Saver()
    saver.restore(sess, training_checkpoint)

    # Freeze the graph def
    output_graph_def = freeze_graph_def(sess, 'embeddings')

    output_pnet = os.path.join(OUTPUT_DIR, 'MobileFaceNet.pb')
    # Serialize and dump the output graph to the filesystem
    with tf.gfile.GFile(output_pnet, 'wb') as f:
        f.write(output_graph_def.SerializeToString())
if name == 'main':
save()

大哥，再问个问题，就是这一句output, _ = inference(data_input, bottleneck_layer_size=192)
为啥这里是192，我看他代码里写的都是128，所以说他默认的参数应该是128呀，但是，我用128转换他居然说要求192，这是啥原因。

syaringan357 · 2020-05-06T01:42:22Z

我也不太清楚，我也是按报错提示改的。可能是他一些代码经过长时间修改之后对不上了。

kongdaniel · 2020-05-06T02:40:30Z

这样啊，谢谢了。

…

------------------ 原始邮件 ------------------ 发件人: "syaringan357"<[email protected]>; 发送时间: 2020年5月6日(星期三) 上午9:42 收件人: "syaringan357/Android-MobileFaceNet-MTCNN-FaceAntiSpoofing"<[email protected]>; 抄送: "2459431805"<[email protected]>;"Author"<[email protected]>; 主题: Re: [syaringan357/Android-MobileFaceNet-MTCNN-FaceAntiSpoofing] 关于moilefacenet的pb模型转换成tf.lite (#14) 我也不太清楚，我也是按报错提示改的。可能是他一些代码经过长时间修改之后对不上了。 — You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub, or unsubscribe.

yp19940913 · 2021-04-25T08:31:53Z

你好，请问这个问题解决了吗？方便说一下解决方法嘛？多谢

kongdaniel · 2021-04-25T08:53:54Z

你好，请问这个问题解决了吗？方便说一下解决方法嘛？多谢

你好，你可以看作者发的代码，可以解决，当时，我就是用他的代码，现在我代码找不到了。换了块硬盘，找起来费劲得很。你如果用他的代码无语，那就正好，如果有误，我就再找找

leduy99 · 2021-12-31T08:58:18Z

Hi, I'm encouting the same problem and cannot solve this. My approach is to change 'Switch' op -> 'If' and 'Merge' -> 'While' but didn't work. Any suggestion? Tks :D

kongdaniel · 2021-12-31T09:06:57Z

sorry,I don't learn it so long,I forgeted it.

…

---原始邮件--- 发件人: ***@***.***> 发送时间: 2021年12月31日(周五) 下午4:58 收件人: ***@***.***>; 抄送: ***@***.******@***.***>; 主题: Re: [syaringan357/Android-MobileFaceNet-MTCNN-FaceAntiSpoofing] 关于moilefacenet的pb模型转换成tf.lite (#14) Hi, I'm encouting the same problem and cannot solve this. My approach is to change 'Switch' op -> 'If' and 'Merge' -> 'While' but didn't work. Any suggestion? Tks :D — Reply to this email directly, view it on GitHub, or unsubscribe. Triage notifications on the go with GitHub Mobile for iOS or Android. You are receiving this because you authored the thread.Message ID: ***@***.***>

leduy99 · 2021-12-31T09:24:18Z

But how can you export a tflite version from the model? :o

redaihanyu · 2022-05-06T06:55:13Z

import tensorflow as tf

in_path = "../output/mobilefacenet/frozen_graphs/MobileFaceNet.pb" out_path = "../output/mobilefacenet/tflite/MobileFaceNet.tflite"

input_tensor_name = ["input"] input_tensor_shape = {"input": [2, 112, 112, 3]} classes_tensor_name = ["embeddings"]

converter = tf.lite.TFLiteConverter.from_frozen_graph(in_path, input_tensor_name, classes_tensor_name, input_shapes=input_tensor_shape) tflite_model = converter.convert()

with open(out_path, "wb") as f: f.write(tflite_model)

您好，为什么您这里的batchsize 设置成 2呢，不应该是1吗？

guker mentioned this issue Feb 3, 2021

convert pb to tflite error sirius-ai/MobileFaceNet_TF#75

Open

Repository owner deleted a comment from marynavoitenko Feb 23, 2024

github-staff deleted a comment from thangtq-pionero Apr 26, 2024

github-staff deleted a comment from jguzej May 12, 2024

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

关于moilefacenet的pb模型转换成tf.lite #14

关于moilefacenet的pb模型转换成tf.lite #14

kongdaniel commented Apr 24, 2020 •

edited

Loading

syaringan357 commented Apr 26, 2020 •

edited

Loading

kongdaniel commented Apr 26, 2020

kongdaniel commented Apr 26, 2020 via email

syaringan357 commented Apr 27, 2020

syaringan357 commented Apr 27, 2020 •

edited

Loading

syaringan357 commented Apr 27, 2020

kongdaniel commented Apr 27, 2020

kongdaniel commented May 1, 2020

Replace all the variables in the graph with constants of the same values

syaringan357 commented May 6, 2020

kongdaniel commented May 6, 2020 via email

yp19940913 commented Apr 25, 2021

kongdaniel commented Apr 25, 2021

leduy99 commented Dec 31, 2021

kongdaniel commented Dec 31, 2021 via email

leduy99 commented Dec 31, 2021

redaihanyu commented May 6, 2022

关于moilefacenet的pb模型转换成tf.lite #14

关于moilefacenet的pb模型转换成tf.lite #14

Comments

kongdaniel commented Apr 24, 2020 • edited Loading

syaringan357 commented Apr 26, 2020 • edited Loading

kongdaniel commented Apr 26, 2020

kongdaniel commented Apr 26, 2020 via email

syaringan357 commented Apr 27, 2020

syaringan357 commented Apr 27, 2020 • edited Loading

syaringan357 commented Apr 27, 2020

kongdaniel commented Apr 27, 2020

kongdaniel commented May 1, 2020

Replace all the variables in the graph with constants of the same values

syaringan357 commented May 6, 2020

kongdaniel commented May 6, 2020 via email

yp19940913 commented Apr 25, 2021

kongdaniel commented Apr 25, 2021

leduy99 commented Dec 31, 2021

kongdaniel commented Dec 31, 2021 via email

leduy99 commented Dec 31, 2021

redaihanyu commented May 6, 2022

kongdaniel commented Apr 24, 2020 •

edited

Loading

syaringan357 commented Apr 26, 2020 •

edited

Loading

syaringan357 commented Apr 27, 2020 •

edited

Loading