dengshushu68
2019-06-22 17:00
采纳率: 100%
浏览 11.9k

Tensorflow object detection API 训练自己数据时报错 Windows fatal exception: access violation

python3.6, tf 1.14.0,Tensorflow object detection API 跑demo图片和改为摄像头进行物体识别均正常,

训练自己的数据训练自己数据时报错 Windows fatal exception: access violation
用的ssd_mobilenet_v1_coco_2018_01_28模型,
命令:python model_main.py -pipeline_config_path=/pre_model/pipeline.config -model_dir=result -num_train_steps=2000 -alsologtostderr

其实就是按照网上基础的训练来的,一直报这个,具体错误输出如下:

(py36) D:\pythonpro\TensorFlowLearn\face_tf_model>python model_main.py -pipeline_config_path=/pre_model/pipeline.config -model_dir=result -num_train_steps=2000 -alsologtostderr
WARNING: Logging before flag parsing goes to stderr.
W0622 16:50:30.230578 14180 lazy_loader.py:50]
The TensorFlow contrib module will not be included in TensorFlow 2.0.
For more information, please see:

W0622 16:50:30.317274 14180 deprecation_wrapper.py:119] From D:\Anaconda3\libdata\tf_models\research\slim\nets\inception_resnet_v2.py:373: The name tf.GraphKeys is deprecated. Please use tf.compat.v1.GraphKeys instead.

W0622 16:50:30.355400 14180 deprecation_wrapper.py:119] From D:\Anaconda3\libdata\tf_models\research\slim\nets\mobilenet\mobilenet.py:397: The name tf.nn.avg_pool is deprecated. Please use tf.nn.avg_pool2d instead.

W0622 16:50:30.388313 14180 deprecation_wrapper.py:119] From model_main.py:109: The name tf.app.run is deprecated. Please use tf.compat.v1.app.run instead.

W0622 16:50:30.397290 14180 deprecation_wrapper.py:119] From D:\Anaconda3\envs\py36\lib\site-packages\object_detection-0.1-py3.6.egg\object_detection\utils\config_util.py:98: The name tf.gfile.GFile is deprecated. Please use tf.io.gfile.GFile instead.

Windows fatal exception: access violation

Current thread 0x00003764 (most recent call first):
File "D:\Anaconda3\envs\py36\lib\site-packages\tensorflow\python\lib\io\file_io.py", line 84 in _preread_check
File "D:\Anaconda3\envs\py36\lib\site-packages\tensorflow\python\lib\io\file_io.py", line 122 in read
File "D:\Anaconda3\envs\py36\lib\site-packages\object_detection-0.1-py3.6.egg\object_detection\utils\config_util.py", line 99 in get_configs_from_pipeline_file
File "D:\Anaconda3\envs\py36\lib\site-packages\object_detection-0.1-py3.6.egg\object_detection\model_lib.py", line 606 in create_estimator_and_inputs
File "model_main.py", line 71 in main
File "D:\Anaconda3\envs\py36\lib\site-packages\absl\app.py", line 251 in _run_main
File "D:\Anaconda3\envs\py36\lib\site-packages\absl\app.py", line 300 in run
File "D:\Anaconda3\envs\py36\lib\site-packages\tensorflow\python\platform\app.py", line 40 in run
File "model_main.py", line 109 in

(py36) D:\pythonpro\TensorFlowLearn\face_tf_model>

请大神指点下

  • 点赞
  • 写回答
  • 关注问题
  • 收藏
  • 邀请回答

5条回答 默认 最新

  • dengshushu68 2019-06-24 10:38
    已采纳

    折腾了两天,最后折服了,降版本到1.12,-gpu,装cuda搞定,谢谢了

    点赞 打赏 评论
  • 喵喵女士爱吃鱼 2019-06-22 19:56

    重现更新下tensorflow看看,是不是The TensorFlow contrib module will not be included in TensorFlow 2.0.这里的问题

    点赞 打赏 评论
  • 永不落的sun2 2019-08-12 11:18

    楼上的老哥,这只是版本更新的警告来的,不影响程序的运行。
    问题应该是出现在protobuf或者是tf-gpu1.14的版本问题上,反正我安装完1.12-gpu之后问题就解决了。https://github.com/fo40225/tensorflow-windows-wheel/tree/master/1.12.0
    这个问题应该是protobuf 的stream读写操作涉及到了禁用的虚拟地址,python程序是没有权限进行这种操作的,如果强行给他权限,可能会导致非常非常多的难以估计的系统问题,甚至有崩溃的可能,所以,还是降版本稳妥一点。

    点赞 打赏 评论
  • weixin_43930148 2020-01-10 10:36

    除了这样处理还可以怎么弄?我是cpu下载的也是TensorFlow 不是gpu但是开始训练就出现一样的错误。求解决

    点赞 打赏 评论
  • Lqi_jia 2020-03-08 14:04

    我也是,降成1.12版本会出现tensorflow_api什么的缺少v1,请问你解决了吗

    点赞 打赏 评论

相关推荐 更多相似问题