Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

How to transfer the .ckpt to .pb? #389

Open
lucky-xu-1994 opened this issue Jul 28, 2020 · 9 comments
Open

How to transfer the .ckpt to .pb? #389

lucky-xu-1994 opened this issue Jul 28, 2020 · 9 comments

Comments

@lucky-xu-1994
Copy link

I have learned a lot to how transfer .ckpt to .pb, but it needs the input_tensor_name and output_node_names , in this project I can't find them, so how can I transfer the .ckpt to .pb? please help!

@world2025
Copy link

@lucky-xu-1994 你好,你这个搞定了嘛?我发现找不到模型的输入输出节点

@lucky-xu-1994
Copy link
Author

@lucky-xu-1994 你好,你这个搞定了嘛?我发现找不到模型的输入输出节点

你把ckpt文件的输入输出节点打印出来,如果是这个工程文件的的话,
我找到的是六个特征图的输出节点,每个特征图输出一个分类和位置回归,例如:第一个特征图是“ssd_512_vgg/softmax/Softmax”(分类),"ssd_512_vgg/block4_box/Reshape"(位置回归),要是想得到最终的结果,需要将所有层的输出综合一起做非极大值抑制,具体可以参考工程文件中的notebooks/ssd_notebook.ipynb,
输入节点是一个队列输入,如果想要方便测试单张图片,可以在冻结模型时通过输入占位符进行冻结。

@world2025
Copy link

可以加qq或微信吗?qq:843783062 微信:tk-conquer

@world2025
Copy link

@lucky-xu-1994 然后我就很迷惑

@lucky-xu-1994
Copy link
Author

@lucky-xu-1994 然后我就很迷惑

你要打印的是节点名字,试试这个,找一下soft_max输出
from tensorflow.python import pywrap_tensorflow
import tensorflow as tf
import os
model_dir = '/home/pb/'
ckpt='/home/logs/model.ckpt-332005'

with tf.Session() as sess:
saver = tf.train.import_meta_graph(ckpt +'.meta', clear_devices=True)
graph_def = tf.get_default_graph().as_graph_def(add_shapes=True)
node_list = [n.name for n in graph_def.node]
result_file = os.path.join(model_dir,'result1.txt')
with open(result_file,'w+') as f:
for node in node_list:
#print("node_name", node)
f.write(node+'\n')

print('done')

@world2025
Copy link

import tensorflow as tf
import os
model_dir = './out/'
ckpt='F:/SSD/SSD-Tensorflow/train_model/model.ckpt-750'
with tf.Session() as sess:
    saver = tf.train.import_meta_graph(ckpt +'.meta', clear_devices=True)
graph_def = tf.get_default_graph().as_graph_def(add_shapes=True)
node_list = [n.name for n in graph_def.node]
result_file = os.path.join(model_dir,'result1.txt')
with open(result_file,'w+') as f:
    for node in node_list:
         #print("node_name", node)
        f.write(node+'\n')
        print('done')

代码格式是这样的吧

@lucky-xu-1994
Copy link
Author

import tensorflow as tf
import os
model_dir = './out/'
ckpt='F:/SSD/SSD-Tensorflow/train_model/model.ckpt-750'
with tf.Session() as sess:
saver = tf.train.import_meta_graph(ckpt +'.meta', clear_devices=True)
graph_def = tf.get_default_graph().as_graph_def(add_shapes=True)
node_list = [n.name for n in graph_def.node]
result_file = os.path.join(model_dir,'result1.txt')
with open(result_file,'w+') as f:
for node in node_list:
#print("node_name", node)
f.write(node+'\n')
print('done')

代码格式是这样的吧

你把session下面的代码都放在会话结构中,然后仔细看一下网络的定义,找一下softmax输出
具体你可以参照 https://blog.csdn.net/guyuealian/article/details/82218092
以及https://blog.csdn.net/zkgoup/article/details/105657577?utm_medium=distribute.pc_relevant.none-task-blog-BlogCommendFromMachineLearnPai2-1.nonecase&depth_1-utm_source=distribute.pc_relevant.none-task-blog-BlogCommendFromMachineLearnPai2-1.nonecase

@world2025
Copy link

好的,谢谢

@world2025
Copy link

你好,我又来麻烦你了,哈哈,我找到的是六个特征图的输出节点,每个特征图输出一个分类和位置回归,例如:第一个特征图是“ssd_512_vgg/softmax/Softmax”(分类),"ssd_512_vgg/block4_box/Reshape"(位置回归),要是想得到最终的结果,需要将所有层的输出综合一起做非极大值抑制,具体可以参考工程文件中的notebooks/ssd_notebook.ipynb,
输入节点是一个队列输入,如果想要方便测试单张图片,可以在冻结模型时通过输入占位符进行冻结。
根据你之前说的,我现在也是得到了输入输出节点,现在是我想弄成可以发布服务的那种,那模型的输出就得是做过后处理的,请问一下如果将所有层的输出综合一起做非极大值抑制,我看了下那个推理文件,这个好像是得到6个输出节点后再进行后处理

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants