tensorflow pb模型获得权重wts

import tensorflow as tf
from tensorflow.python.platform import gfile
#path to your .pb file
GRAPH_PB_PATH = './model/tensorflow_inception_v3_stripped_optimized_quantized.pb'
with tf.Session(config=config) as sess:print("load graph")with gfile.FastGFile(GRAPH_PB_PATH,'rb') as f:graph_def = tf.GraphDef()graph_def.ParseFromString(f.read())sess.graph.as_default()tf.import_graph_def(graph_def, name='')graph_nodes=[n for n in graph_def.node]
wts = [n for n in graph_nodes if n.op=='Const']
from tensorflow.python.framework import tensor_utilfor n in wts:print("Name of the node - %s" % n.name)print("Value - ")print(tensor_util.MakeNdarray(n.attr['value'].tensor))

运行出现报错

Traceback (most recent call last):File "gen_pb_wts.py", line 5, in <module>with tf.Session(config=config) as sess:
NameError: name 'config' is not defined

将with tf.Session(config=config) as sess: 修改为tf.Session(）as sess: 重新运行部分结果如下

Name of the node - BoxPredictor_4/ClassPredictor_depthwise/BatchNorm/gamma
Value -
[1.0076598  0.600361   0.64767396 0.5886829  0.6474589  0.578997250.7420581  0.43999094 0.9291541  0.6562006  0.6434446  0.628889560.7723971  1.013845   0.5593387  0.5763445  0.60916996 0.662380341.0512784  0.58268934 0.52825654 0.55082077 0.4491668  0.64863170.717447   0.9524743  0.7800959  0.42979443 0.55822694 0.605744361.0343778  0.5154323  0.85758215 1.0833062  0.5687403  0.57528640.84560686 0.62819284 0.6473139  0.58606607 0.6454761  0.62704430.5428621  0.673155   0.9136668  0.62957346 0.855056   0.800636770.55059046 0.941908   0.6897346  0.5215224  0.64170074 1.01290.63292354 0.7850904  0.44446874 0.7453388  0.6934488  0.54195930.70664483 0.48354548 0.60087705 0.6893038  0.45109886 0.621808650.6481066  0.67009485 0.6451158  0.5812356  0.8095073  0.400866150.50798595 0.49360913 0.51697165 0.5107985  0.53685313 0.90887230.76556355 0.36509857 0.367629   0.80191237 0.6855312  0.9703071.0197186  0.671655   0.57405996 0.76866794 0.74245185 0.515310.6980881  0.8520622  0.54880375 0.91214556 0.710224   0.416815760.6096677  0.36241293 0.56075    0.5863032  0.6354018  0.51200031.0113248  0.8348537  0.7205713  0.67849016 0.97358465 0.448866460.8159403  0.64450437 0.5997353  0.54739535 0.6758225  0.619861540.6395207  0.5936247  0.5463965  0.5821391  0.6760462  1.06802520.55302185 0.7000822  0.8675259  0.6098902  0.74904156 0.57579580.2752119  0.64663106 0.56606585 0.5852428  0.82287776 0.52804360.6185344  0.6950132  1.0274562  0.7259649  1.0736766  0.6026730.8857293  0.59187907 0.78937036 0.4410297  0.7101182  0.81597390.55530983 0.6026916  0.7655125  0.63132054 0.52071196 0.576747950.919869   0.5550313  0.55495024 1.0107807  0.6631691  0.76980980.6434384  0.6741949  1.0766468  0.8970208  0.6370691  0.483588670.9154165  0.5827703  0.9874309  1.0530525  0.600562   0.84978940.6070317  0.5207939  0.7410717  0.75982136 0.57712764 0.5398030.72110265 1.1149868  0.6521509  0.86586046 0.49901482 0.61680510.52331764 0.65172225 1.0159032  0.6780148  0.51903594 0.848386350.6718971  0.8696038  0.4443711  0.48789653 0.7989498  0.65526380.4824569  0.4769425  0.63836104 0.54260814 0.49502477 0.8088910.7465959  0.586385   0.63334984 0.63899726 0.6576707  0.997949060.8469274  0.72964466 0.76935375 0.7605871  0.7410051  0.67826050.4853573  0.90893656 0.835856   0.6664103  0.6316711  0.719513540.7788348  0.58414733 0.85619235 0.87070334 0.6793145  0.90284630.7173049  0.64837295 0.44326815 0.82141757 0.65800077 0.87141890.90920067 0.7825849  0.5547908  1.0501481  0.6167052  0.800194740.56159836 0.7303601  0.6019257  0.9394907  0.57830775 0.6206071

tensorflow pb模型获得权重wts相关推荐

查看tensorflow pb模型文件的节点信息
查看tensorflow pb模型文件的节点信息: import tensorflow as tf with tf.Session() as sess:with open('./quantized_m ...
TensorFlow pb模型修改和优化
TensorFlow 模型训练完成后,通常会通过frozen过程保存一个最终的pb模型.保存的pb模型是以GraphDef数据结构保存的,可以序列化保存为二进制pb模型或者文本pbtxt模型.Grap ...
Tensorflow pb模型转uff模型方法及遇到KeyError20和expected Const问题解决
项目所需要将Tensorflow 生成的pb模型转为uff模型,方法很简单,但是遇到的问题着实很多,这里主要记录下问题及解决方法,总之,最后是成功生成uff格式的模型的,有需要的可以参考. pb模型转 ...
opencv打开pb_【OpenCV】OpenCV4调用tensorflow pb模型进行目标检测
先在visual studio 2015新建一个工程并配置好环境. OpenCV调用tensorflow的pb模型,不仅需要一个.pb文件,还需要一个.pbtxt文件. 一些预训练好的pb模型的下载地 ...
pytorch .pth模型转tensorflow .pb模型
训练好的pytorch模型如何转化为tensorflow的pb模型? 本人初步使用的是onnx框架: pytorch ---> onnx ----> tensorflow 使用onnx转 ...
MxNet 模型转Tensorflow pb模型
用mmdnn实现模型转换参考链接:https://www.twblogs.net/a/5ca4cadbbd9eee5b1a0713af 安装mmdnn pip install mmdnn 准备好mx ...
CNN: 查看tensorflow Pb模型所有层的名字
tensorflow的keras没有外部可视化配置文件,需要使用netron查看模型参数,或者从程序中打印出来, 打印代码: def get_all_layernames():"" ...
keras模型转换为tensorflow的pb模型结构
官方文档介绍如下, 此时博主电脑环境配置为:tensorflow-gpu 2.4.0.python3.6.cuda11.0.cudnn8.0,详细信息可见博主这篇博客应用 Applications ...
Tensorflow训练神经网络保存*.pb模型及载入*.pb模型
1 神经网络结构 1.0 保存*.pb模型 import tensorflow as tf from tensorflow.python.framework import graph_util fro ...
Tensorflow基于pb模型进行预训练（pb模型转CKPT模型）
Tensorflow基于pb模型进行预训练(pb模型转CKPT模型) 在网上看到很多教程都是tensorflow基于pb模型进行推理,而不是进行预训练.最近在在做项目的过程中发现之前的大哥只有一个pb ...

tensorflow pb模型获得权重wts

tensorflow pb模型获得权重wts

tensorflow pb模型获得权重wts相关推荐

最新文章

热门文章