tensorflow运行SegNet问题

palizhen22hao 2017-11-06 11:55:43
使用下面的segnet实现代码
https://github.com/tkuanlun350/Tensorflow-SegNet
在main中已经修改了camvid数据集里面三个txt文件的数据路径，但是报错
The model is set to Training
Max training Iteration: 20000
Initial lr: 0.001000
CamVid Image dir: /home/jiang/lane/SegNet/CamVid/train.txt
CamVid Val dir: /home/jiang/lane/SegNet/CamVid/val.txt
Batch Size: 1
Log dir: /tmp3/first350/TensorFlow/Logs
Filling queue with 146 CamVid images before starting to train. This will take a few minutes.
Filling queue with 146 CamVid images before starting to train. This will take a few minutes.
2017-11-06 23:39:54.802996: I tensorflow/core/platform/cpu_feature_guard.cc:137] Your CPU supports instructions that this TensorFlow binary was not compiled to use: SSE4.1 SSE4.2 AVX AVX2 FMA
Traceback (most recent call last):
File "/home/jiang/lane/Tensorflow-SegNet-master/main.py", line 52, in <module>
tf.app.run()
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/platform/app.py", line 48, in run
_sys.exit(main(_sys.argv[:1] + flags_passthrough))
File "/home/jiang/lane/Tensorflow-SegNet-master/main.py", line 49, in main
model.training(FLAGS, is_finetune=False)
File "/home/jiang/lane/Tensorflow-SegNet-master/model.py", line 389, in training
sess.run(init)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 889, in run
run_metadata_ptr)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 1120, in _run
feed_dict_tensor, options, run_metadata)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 1317, in _do_run
options, run_metadata)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 1336, in _do_call
raise type(e)(node_def, op, message)
tensorflow.python.framework.errors_impl.InvalidArgumentError: No OpKernel was registered to support Op 'MaxPoolWithArgmax' with these attrs. Registered devices: [CPU], Registered kernels:
<no registered kernels>

[[Node: pool1 = MaxPoolWithArgmax[T=DT_FLOAT, Targmax=DT_INT64, ksize=[1, 2, 2, 1], padding="SAME", strides=[1, 2, 2, 1]](conv1/Relu)]]

Caused by op u'pool1', defined at:
File "/home/jiang/lane/Tensorflow-SegNet-master/main.py", line 52, in <module>
tf.app.run()
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/platform/app.py", line 48, in run
_sys.exit(main(_sys.argv[:1] + flags_passthrough))
File "/home/jiang/lane/Tensorflow-SegNet-master/main.py", line 49, in main
model.training(FLAGS, is_finetune=False)
File "/home/jiang/lane/Tensorflow-SegNet-master/model.py", line 372, in training
loss, eval_prediction = inference(train_data_node, train_labels_node, batch_size, phase_train)
File "/home/jiang/lane/Tensorflow-SegNet-master/model.py", line 182, in inference
padding='SAME', name='pool1')
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/gen_nn_ops.py", line 3525, in max_pool_with_argmax
padding=padding, Targmax=Targmax, name=name)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/op_def_library.py", line 787, in _apply_op_helper
op_def=op_def)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.py", line 2956, in create_op
op_def=op_def)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.py", line 1470, in __init__
self._traceback = self._graph._extract_stack() # pylint: disable=protected-access

InvalidArgumentError (see above for traceback): No OpKernel was registered to support Op 'MaxPoolWithArgmax' with these attrs. Registered devices: [CPU], Registered kernels:
<no registered kernels>

[[Node: pool1 = MaxPoolWithArgmax[T=DT_FLOAT, Targmax=DT_INT64, ksize=[1, 2, 2, 1], padding="SAME", strides=[1, 2, 2, 1]](conv1/Relu)]]

不知道怎么回事 查半天也没查出来
...全文
1375 8 打赏 收藏 转发到动态 举报
写回复
用AI写文章
8 条回复
切换为时间正序
请发表友善的回复…
发表回复
weixin_44011046 2020-10-11
  • 打赏
  • 举报
 回复
楼组找见咋解决了嘛
Vivian_345 2019-11-22
  • 打赏
  • 举报
 回复
Instructions for updating: Colocations handled automatically by placer. 想问一下 这个问题怎么解决~
weixin_43470529 2019-07-23
  • 打赏
  • 举报
 回复
runfile('C:/Users/dell/Desktop/Tensorflow-SegNet-master/main.py', wdir='C:/Users/dell/Desktop/Tensorflow-SegNet-master')
The model is set to Training
Max training Iteration: 20000
Initial lr: 0.001000
CamVid Image dir: C:/Users/dell/Desktop/Tensorflow-SegNet-master/CamVid/train.txt
CamVid Val dir: C:/Users/dell/Desktop/Tensorflow-SegNet-master/CamVid/val.txt
Batch Size: 5
Log dir: C:/Users/dell/Desktop/Tensorflow-SegNet-master/CamVid/Logs
WARNING:tensorflow:From C:\anaconda3\envs\tensorflow\lib\site-packages\tensorflow\python\framework\op_def_library.py:263: colocate_with (from tensorflow.python.framework.ops) is deprecated and will be removed in a future version.
Instructions for updating:
Colocations handled automatically by placer.
WARNING:tensorflow:From C:\Users\dell\Desktop\Tensorflow-SegNet-master\Inputs.py:107: slice_input_producer (from tensorflow.python.training.input) is deprecated and will be removed in a future version.
Instructions for updating:
Queue-based input pipelines have been replaced by `tf.data`. Use `tf.data.Dataset.from_tensor_slices(tuple(tensor_list)).shuffle(tf.shape(input_tensor, out_type=tf.int64)[0]).repeat(num_epochs)`. If `shuffle=False`, omit the `.shuffle(...)`.
WARNING:tensorflow:From C:\anaconda3\envs\tensorflow\lib\site-packages\tensorflow\python\training\input.py:374: range_input_producer (from tensorflow.python.training.input) is deprecated and will be removed in a future version.
Instructions for updating:
Queue-based input pipelines have been replaced by `tf.data`. Use `tf.data.Dataset.range(limit).shuffle(limit).repeat(num_epochs)`. If `shuffle=False`, omit the `.shuffle(...)`.
WARNING:tensorflow:From C:\anaconda3\envs\tensorflow\lib\site-packages\tensorflow\python\training\input.py:320: input_producer (from tensorflow.python.training.input) is deprecated and will be removed in a future version.
Instructions for updating:
Queue-based input pipelines have been replaced by `tf.data`. Use `tf.data.Dataset.from_tensor_slices(input_tensor).shuffle(tf.shape(input_tensor, out_type=tf.int64)[0]).repeat(num_epochs)`. If `shuffle=False`, omit the `.shuffle(...)`.
WARNING:tensorflow:From C:\anaconda3\envs\tensorflow\lib\site-packages\tensorflow\python\training\input.py:190: limit_epochs (from tensorflow.python.training.input) is deprecated and will be removed in a future version.
Instructions for updating:
Queue-based input pipelines have been replaced by `tf.data`. Use `tf.data.Dataset.from_tensors(tensor).repeat(num_epochs)`.
WARNING:tensorflow:From C:\anaconda3\envs\tensorflow\lib\site-packages\tensorflow\python\training\input.py:199: QueueRunner.__init__ (from tensorflow.python.training.queue_runner_impl) is deprecated and will be removed in a future version.
Instructions for updating:
To construct input pipelines, use the `tf.data` module.
WARNING:tensorflow:From C:\anaconda3\envs\tensorflow\lib\site-packages\tensorflow\python\training\input.py:199: add_queue_runner (from tensorflow.python.training.queue_runner_impl) is deprecated and will be removed in a future version.
Instructions for updating:
To construct input pipelines, use the `tf.data` module.
WARNING:tensorflow:From C:\anaconda3\envs\tensorflow\lib\site-packages\tensorflow\python\training\input.py:202: to_float (from tensorflow.python.ops.math_ops) is deprecated and will be removed in a future version.
Instructions for updating:
Use tf.cast instead.
Filling queue with 146 CamVid images before starting to train. This will take a few minutes.
WARNING:tensorflow:From C:\Users\dell\Desktop\Tensorflow-SegNet-master\Inputs.py:44: shuffle_batch (from tensorflow.python.training.input) is deprecated and will be removed in a future version.
Instructions for updating:
Queue-based input pipelines have been replaced by `tf.data`. Use `tf.data.Dataset.shuffle(min_after_dequeue).batch(batch_size)`.
Filling queue with 146 CamVid images before starting to train. This will take a few minutes.

WARNING: The TensorFlow contrib module will not be included in TensorFlow 2.0.
For more information, please see:
* https://github.com/tensorflow/community/blob/master/rfcs/20180907-contrib-sunset.md
* https://github.com/tensorflow/addons
If you depend on functionality not listed there, please file an issue.

INFO:tensorflow:Summary name conv_classifier/weight_loss (raw) is illegal; using conv_classifier/weight_loss__raw_ instead.
INFO:tensorflow:Summary name loss/cross_entropy (raw) is illegal; using loss/cross_entropy__raw_ instead.
INFO:tensorflow:Summary name loss/total_loss (raw) is illegal; using loss/total_loss__raw_ instead.
WARNING:tensorflow:From C:\anaconda3\envs\tensorflow\lib\site-packages\tensorflow\python\ops\math_ops.py:3066: to_int32 (from tensorflow.python.ops.math_ops) is deprecated and will be removed in a future version.
Instructions for updating:
Use tf.cast instead.
WARNING:tensorflow:From C:\Users\dell\Desktop\Tensorflow-SegNet-master\model.py:393: start_queue_runners (from tensorflow.python.training.queue_runner_impl) is deprecated and will be removed in a future version.
Instructions for updating:
To construct input pipelines, use the `tf.data` module.
青玉白露 2019-04-08
  • 打赏
  • 举报
 回复
之前几天一直在解决这个问题： 新建一个环境，python=3.6 安装tensorflow版本指定为1.11。 注意Util.py文件的cpu还是gpu
ylh1234 2017-12-08
  • 打赏
  • 举报
 回复
你现在会了吗？。。
千殇_不哭 2017-11-20
  • 打赏
  • 举报
 回复
MaxPoolWithArgmax这个使用theano实现的 我不知道你这版tf实现的是什么情况，我用keras，后台使用theano调的成功了 但是效果不太行，可以讨论下
palizhen22hao 2017-11-07
  • 打赏
  • 举报
 回复
求大神指导啊
palizhen22hao 2017-11-07
  • 打赏
  • 举报
 回复
基于tensorflow2.5实现的segnet图像分割算法python源码+数据集.zip
基于tensorflow2.5实现的segnet图像分割算法python源码+数据集.zip 基于tensorflow2.5实现的segnet图像分割算法python源码+数据集.zip 基于tensorflow2.5实现的segnet图像分割算法python源码+数据集.zip 基于tensorflow2.5实现的segnet图像分割算法python源码+数据集.zip 基于tensorflow2.5实现的segnet图像分割算法python源码+数据集.zip 基于tensorflow2.5实现的segnet图像分割算法python源码+数据集.zip 基于tensorflow2.5实现的segnet图像分割算法python源码+数据集.zip 基于tensorflow2.5实现的segnet图像分割算法python源码+数据集.zip 基于tensorflow2.5实现的segnet图像分割算法python源码+数据集.zip 基于tensorflow2.5实现的segnet图像分割算法python源码+数据集.zip 基于tensorflow2.5实现的segnet图像分割算法python源码+数据集.zip 【资源说明】 1、该资源内项目代码都是经过测试运行成功，功能正常的情况下才上传的，请放心下载使用。 2、适用人群：主要针对计算机相关专业(如计科、信息安全、数据科学与大数据技术、人工智能、通信、物联网、数学、电子信息等)的同学或企业员工下载使用，具有较高的学习借鉴价值。 3、不仅适合小白学习实战练习，也可作为大作业、课程设计、毕设项目、初期项目立项演示等，欢迎下载，互相学习，共同进步！
matlab清除所有命令代码-river_ice_segmentation:深度学习的河冰分割
matlab清除所有命令代码该存储库为所报告的所有实验提供python和matlab代码。 它包含用于实验的几个开源存储库的修改版本，尽管本文没有报告所有这些。 这些是报告的模型及其对应的文件夹： DenseNet：[python / tensorflow] DeepLab：，[python / tensorflow] UNet，SegNet：[python / keras] SVM：[matlab] ，并且包含这些模型的其他实施方式，这些实施方式均无法很好地实现上述功能。 未报告的型号： FCN： 视频细分： 用于运行每个模型的命令在相应文件夹中的.md文件中提供。 例如，用于UNet和DenseNet的命令位于和中。 这些命令按层次结构组织为实验类别，并包含目录以方便导航。 以下脚本可用于数据准备和结果生成： 数据扩充/子补丁生成：， 拼接子补丁分割结果，并可以选择评估它们： 生成冰浓度图： 可视化和评估细分结果： 用于运行这些命令的命令位于各个模型文件中，也位于各个模型文件中。 某些命令可能需要通用的实用程序脚本，例如。 如果某个命令不起作用，则找不到与某个实验相对应的命令，或者
图像语义分割-----SegNet学习笔记+tensorflow
SegNet网络是一个像素级的语义分割模型，即会针对图像中的每一个像素，对每一个像素进行分类，去识别该像素属于的类别，整个网络分为4层下采样以及4层上采样，最后将一个[W, H, 3]的输入图像处理成[W, H, NUM_CLASSES]的向量，再通过softmax进行分类，转化为[W, H, 1]的张量，再对属于不同种类的像素分别涂上不同的颜色，从新变成[W, H, 3]的图像，但是其中的物体以...
SegNet-tensorflow编译小结
文章目录代码及相关库的下载编译SegNet-tensorflow代码训练数据集 代码及相关库的下载 从github上下载SegNet-tensorflow的代码，命令如下： $git clone https://github.com/tkuanlun350/Tensorflow-SegNet.git SegNet 安装readme中要求的库。 $pip install tensorfl...
图像分割semantic segmentation SegNet详解+tensorflow代码使用【附下载】
原论文链接：SegNet ResNet传送门：Resnet-cifar10 Inceptionv3传送门：inceptionv3     逐像素的semantic segmentation是目前比较活跃的一个研究热点。在深度网络出现之前，效果比较好的方法有随机数，boosting等。而目前比较热门的语义分割结构有：U-Net、SegNet、DeepLab、FCN、ENet、LinkNet等等...
脚本语言

37,720

社区成员

34,239

社区内容

发帖
与我相关
我的任务
社区描述
JavaScript，VBScript，AngleScript，ActionScript，Shell，Perl，Ruby，Lua，Tcl，Scala，MaxScript 等脚本语言交流。
社区管理员
  • 脚本语言(Perl/Python)社区
  • IT.BOB
加入社区
  • 近7日
  • 近30日
  • 至今

加载中

查看更多榜单

试试用AI创作助手写篇文章吧

+ 用AI写文章