现象：

WARNING:root:Variable [resnet_v1_50/block1/unit_1/bottleneck_v1/conv1/BatchNorm/beta] is not available in checkpoint
WARNING:root:Variable [resnet_v1_50/block1/unit_1/bottleneck_v1/conv1/BatchNorm/beta/Momentum] is not available in checkpoint
WARNING:root:Variable [resnet_v1_50/block1/unit_1/bottleneck_v1/conv1/BatchNorm/gamma] is not available in checkpoint
WARNING:root:Variable [resnet_v1_50/block1/unit_1/bottleneck_v1/conv1/BatchNorm/gamma/Momentum] is not available in checkpoint
WARNING:root:Variable [resnet_v1_50/block1/unit_1/bottleneck_v1/conv1/BatchNorm/moving_mean] is not available in checkpoint
WARNING:root:Variable [resnet_v1_50/block1/unit_1/bottleneck_v1/conv1/BatchNorm/moving_variance] is not available in checkpoint
WARNING:root:Variable [resnet_v1_50/block1/unit_1/bottleneck_v1/conv1/weights] is not available in checkpoint
WARNING:root:Variable [resnet_v1_50/block1/unit_1/bottleneck_v1/conv1/weights/Momentum] is not available in checkpoint
WARNING:root:Variable [resnet_v1_50/block1/unit_1/bottleneck_v1/conv2/BatchNorm/beta] is not available in checkpoint
WARNING:root:Variable [resnet_v1_50/block1/unit_1/bottleneck_v1/conv2/BatchNorm/beta/Momentum] is not available in checkpoint
WARNING:root:Variable [resnet_v1_50/block1/unit_1/bottleneck_v1/conv2/BatchNorm/gamma] is not available in checkpoint
WARNING:root:Variable [resnet_v1_50/block1/unit_1/bottleneck_v1/conv2/BatchNorm/gamma/Momentum] is not available in checkpoint
WARNING:root:Variable [resnet_v1_50/block1/unit_1/bottleneck_v1/conv2/BatchNorm/moving_mean] is not available in checkpoint
WARNING:root:Variable [resnet_v1_50/block1/unit_1/bottleneck_v1/conv2/BatchNorm/moving_variance] is not available in checkpoint
WARNING:root:Variable [resnet_v1_50/block1/unit_1/bottleneck_v1/conv2/weights] is not available in checkpoint
WARNING:root:Variable [resnet_v1_50/block1/unit_1/bottleneck_v1/conv2/weights/Momentum] is not available in checkpoint
WARNING:root:Variable [resnet_v1_50/block1/unit_1/bottleneck_v1/conv3/BatchNorm/beta] is not available in checkpoint
WARNING:root:Variable [resnet_v1_50/block1/unit_1/bottleneck_v1/conv3/BatchNorm/beta/Momentum] is not available in checkpoint
WARNING:root:Variable [resnet_v1_50/block1/unit_1/bottleneck_v1/conv3/BatchNorm/gamma] is not available in checkpoint
WARNING:root:Variable [resnet_v1_50/block1/unit_1/bottleneck_v1/conv3/BatchNorm/gamma/Momentum] is not available in checkpoint
WARNING:root:Variable [resnet_v1_50/block1/unit_1/bottleneck_v1/conv3/BatchNorm/moving_mean] is not available in checkpoint
WARNING:root:Variable [resnet_v1_50/block1/unit_1/bottleneck_v1/conv3/BatchNorm/moving_variance] is not available in checkpoint
WARNING:root:Variable [resnet_v1_50/block1/unit_1/bottleneck_v1/conv3/weights] is not available in checkpoint
WARNING:root:Variable [resnet_v1_50/block1/unit_1/bottleneck_v1/conv3/weights/Momentum] is not available in checkpoint
WARNING:root:Variable [resnet_v1_50/block1/unit_1/bottleneck_v1/shortcut/BatchNorm/beta] is not available in checkpoint
WARNING:root:Variable [resnet_v1_50/block1/unit_1/bottleneck_v1/shortcut/BatchNorm/beta/Momentum] is not available in checkpoint
WARNING:root:Variable [resnet_v1_50/block1/unit_1/bottleneck_v1/shortcut/BatchNorm/gamma] is not available in checkpoint

这个报的warning是你要的变量在 checkpoint里面找不到！！！！！！！！！！！

那checkpoint里面是什么？？？？？？？？？？？？？那就去看咯：

然后就吧checkpoint的信息打印出来：

import tensorflow as tf

from tensorflow.python.tools.inspect_checkpoint import print_tensors_in_checkpoint_file

latest_ckp = tf.train.latest_checkpoint('./')  # checkpoint 所在的路径是当前文件夹（./）,如果是其他，请改过来

print_tensors_in_checkpoint_file(latest_ckp, all_tensors=True, tensor_name='')
然后发现：

tensor_name:  FeatureExtractor/resnet_v1_50/block4/unit_2/bottleneck_v1/conv3/BatchNorm/beta
[-1.2371869 -1.3236059 -1.2312554 ... -1.3017322 -1.2117504 -1.4911506]
tensor_name:  FeatureExtractor/resnet_v1_50/block4/unit_2/bottleneck_v1/conv3/BatchNorm/gamma
[1.4568403 1.4048293 1.0624585 ... 1.1037463 1.0324904 1.0967498]
tensor_name:  FeatureExtractor/resnet_v1_50/block4/unit_2/bottleneck_v1/conv3/BatchNorm/moving_mean
[-0.08689928  0.00798311 -0.02823892 ... -0.04347016 -0.07710622
 -0.04719209]
tensor_name:  FeatureExtractor/resnet_v1_50/block4/unit_2/bottleneck_v1/conv3/BatchNorm/moving_variance
[0.00452107 0.00487971 0.00305854 ... 0.00261809 0.00344088 0.00306313]
tensor_name:  FeatureExtractor/resnet_v1_50/block4/unit_2/bottleneck_v1/conv3/weights
[[[[ 1.2295754e-03 -9.4967345e-03 -6.6470391e-05 ... -9.7579239e-03
     1.1851139e-02 -1.0630138e-02]
   [-4.5038795e-04 -3.9205588e-03 -6.4933673e-03 ...  9.1390898e-03
    -1.1232623e-02 -9.8358802e-03]
   [ 1.3918030e-02 -7.1829297e-03  3.0942420e-03 ... -6.6203251e-03

原来是少了FeatureExtractor，这时候就去找restore var 的code
var_name = (
    re.split('^' + self._extract_features_scope + '/',
             var_name)[-1])
_extract_features_scope就是：FeatureExtractor
发现他把这个给干掉了，所以：
问题是，tensorflow object detection 在model zoom新下载的模型命名方式改变了，如果使用旧的代码加载新的模型就会出现这个问题，解决方案是research/object_detection/meta_architectures/ssd_meta_arch.py
var_name = (
    re.split('^' + self._extract_features_scope + '/',
             var_name)[-1])
改为：
var_name = (
    re.split('^'  + '/',
             var_name)[-1])
同样的其他模型也是这样。

但是，后面还是出现：

WARNING:root:Variable [resnet_v1_50/block1/unit_1/bottleneck_v1/conv1/BatchNorm/beta/Momentum] is not available in checkpoint
WARNING:root:Variable [resnet_v1_50/block1/unit_1/bottleneck_v1/conv1/BatchNorm/gamma/Momentum] is not available in checkpoint
WARNING:root:Variable [resnet_v1_50/block1/unit_1/bottleneck_v1/conv1/weights/Momentum] is not available in checkpoint

仔细看，你会发现，这只是Momentum造成的，是优化器中的参数，不是模型参数，Momentum是动量的意思，优化器使用这个是为了

避免收敛到局部极值。這個不影響的。如果不想報錯可以：

if fine_tune_checkpoint_type == 'classification':
  var_name = (
      re.split('^'  + '/',
               var_name)[-1])
  # var_name = (
  #     re.split('^' + self._extract_features_scope + '/',
  #              var_name)[-1])
if 'Momentum' in var_name:
    continue
variables_to_restore[var_name] = variable

加一個：

if 'Momentum' in var_name:
    continue

如果是Moment 變量就不加載。

不过，如果对这套代码不了解的，建议update最新的代码。

tensorflow，object，detection，在model zoom，新下载的模型，WARNING:root:Variable [resnet_v1_50/block1/unit_3/bottleneck_v1/conv3/BatchNorm/gamma] is not available in checkpoint的更多相关文章

  1. TensorFlow Object Detection API中的Faster R-CNN /SSD模型参数调整

    关于TensorFlow Object Detection API配置,可以参考之前的文章https://becominghuman.ai/tensorflow-object-detection-ap ...

  2. [Tensorflow] Object Detection API - predict through your exclusive model

    开始预测 一.训练结果 From: Testing Custom Object Detector - TensorFlow Object Detection API Tutorial p.6 训练结果 ...

  3. TensorFlow object detection API应用

    前一篇讲述了TensorFlow object detection API的安装与配置,现在我们尝试用这个API搭建自己的目标检测模型. 一.准备数据集 本篇旨在人脸识别,在百度图片上下载了120张张 ...

  4. TensorFlow object detection API应用--配置

    目标检测在图形识别的基础上有了更进一步的应用,但是代码也更加繁琐,TensorFlow专门为此开设了一个object detection API,接下来看看怎么使用它. object detectio ...

  5. 对于谷歌开源的TensorFlow Object Detection API视频物体识别系统实现教程

    本教程针对Windows10实现谷歌近期公布的TensorFlow Object Detection API视频物体识别系统,其他平台也可借鉴. 本教程将网络上相关资料筛选整合(文末附上参考资料链接) ...

  6. Tensorflow object detection API(1)---环境搭建与测试

    参考: https://blog.csdn.net/dy_guox/article/details/79081499 https://blog.csdn.net/u010103202/article/ ...

  7. 基于TensorFlow Object Detection API进行迁移学习训练自己的人脸检测模型（二）

    前言 已完成数据预处理工作,具体参照: 基于TensorFlow Object Detection API进行迁移学习训练自己的人脸检测模型(一) 设置配置文件 新建目录face_faster_rcn ...

  8. 使用Tensorflow Object Detection进行训练和推理

    整体流程(以PASCAL VOC为例) 1.下载PASCAL VOC2012数据集,并将数据集转为tfrecord格式 2.选择并下载预训练模型 3.配置训练文件configuration(所有的训练 ...

  9. TensorFlow Object Detection API（Windows下训练）

    本文为作者原创,转载请注明出处(http://www.cnblogs.com/mar-q/)by 负赑屃 最近事情比较多,前面坑挖的有点久,今天终于有时间总结一下,顺便把Windows下训练跑通.Li ...

随机推荐

  1. rocketmq 4.3.2 解决远程不能消费问题，解决未识别到公网IP问题

    1.解决远程不能消费问题 问题描述: nameserver和broker启动后,用tools(命令如下)能发送消息和消费消息,在局域网服务器能发送消息,消费启动后收不到消息通知问题 sh tools. ...

  2. C# .NET 实体类转Dictionary

    -- System.Reflection.PropertyInfo[] cfgItemProperties = cfgItem.GetType().GetProperties(System.Refle ...

  3. 浏览器端使用javascript调用腾讯翻译api

    最近在学习的小玩意,发现腾讯的文档十分坑爹,里面有很多错误的指示. 不过腾讯的机器翻译还是很牛的,我觉得翻译水准比谷歌好很多. 腾讯的机器翻译貌似在试用阶段,不收费,用QQ或微信登录即可申请使用. 首 ...

  4. MD5 Hashing in Java

    参考: MD5 Hashing in Java

  5. C++ 线性搜索算法演示的代码

    将做工程过程中比较好的内容做个备份,下边代码段是关于C++ 线性搜索算法演示的代码. #include<iostream>#include<conio> int linears ...

  6. python（list、字典、元组、字符串方法、文件读写）草稿

    1.list 定义list a = [] 添加元素 a.append('xx')   #在list末尾添加 a.insert(0,'abc')   #在指定某位置添加元素.指定的下标不存在就在末尾添加 ...

  7. 贝叶斯、朴素贝叶斯及调用spark官网 mllib NavieBayes示例

    贝叶斯法则   机器学习的任务:在给定训练数据A时,确定假设空间B中的最佳假设.   最佳假设:一种方法是把它定义为在给定数据A以及B中不同假设的先验概率的有关知识下的最可能假设   贝叶斯理论提供了 ...

  8. Linux下安装docker(1)

    1.由于centos系统已经自带docker源了,所以可以直接安装: yum install docker 如果是centos6.5版本的,使用yum -y install docker-io 进行安 ...

  9. 同一台windows下配置安装多个mysql实例，实现主从同步

    一.安装多个mysql 参见: https://blog.csdn.net/wrh_csdn/article/details/80198795 https://www.cnblogs.com/qjoa ...

  10. PackagesNotFoundError: The following packages are not available from current channels

    因为要用到lifelines 包,在cmd中使用conda install lifelines ,显示如下错误: PackagesNotFoundError: The following packag ...