导入错误:没有名为“nets"的模块

问题描述

我正在尝试从 tensorflow/models 中提供的 export_inference_graph.py 脚本中将trained_checkpoint 转换为最终冻结模型，但结果出现以下错误.是的，我已经将 $PYTHONPATH 设置为models/slim"，但仍然出现此错误，有人可以帮我吗?

I am trying to convert trained_checkpoint to final frozen model from the export_inference_graph.py script provided in tensorflow/models,but the following error results.And yes,I have already setup $PYTHONPATH to "models/slim" but still I get this error,can someone help me out?

$ echo $PYTHONPATH
:/home/ishara/tensorflow_models/models:/home/ishara/tensorflow_models/models/slim

********************************问题*******************************************************************************

*****************************problem****************************************************************************

$sudo python3 object_detection/export_inference_graph.py  --input_type image_tensor  --pipeline_config_path = "ssd_inception_v2_pets.config"  --trained_checkpoint_prefix="output/model.ckpt-78543"  --output_directory="birds_inference_graph.pb"

Traceback (most recent call last):
  File "object_detection/export_inference_graph.py", line 74, in <module>
    from object_detection import exporter
  File "/usr/local/lib/python3.5/dist-packages/object_detection-0.1-py3.5.egg/object_detection/exporter.py", line 28, in <module>

  File "/usr/local/lib/python3.5/dist-packages/object_detection-0.1-py3.5.egg/object_detection/builders/model_builder.py", line 30, in <module>
  File "/usr/local/lib/python3.5/dist-packages/object_detection-0.1-py3.5.egg/object_detection/models/faster_rcnn_inception_resnet_v2_feature_extractor.py", line 28, in <module>
ImportError: No module named 'nets'

我已经为此苦苦挣扎了好几天，尝试了很多解决方案都没有奏效我正在使用带有 tensorflow-gpu 版本的 Ubuntu 16.04.

---

I have been struggling with this for days now,tried many solutions nothing workI am using Ubuntu 16.04 with tensorflow-gpu version.

推荐答案

查看 Protobuf Compilation athttps://github.com/tensorflow/models/blob/master/research/object_detection/g3doc/installation.md并正确设置 PYTHONPATH，这就是我为 Windows 解决这个问题的方法

Take a look at Protobuf Compilation athttps://github.com/tensorflow/models/blob/master/research/object_detection/g3doc/installation.mdand set PYTHONPATH correctly, this is how I solved this for Windows

对于 Windows:

For Windows:

第一步:protoc object_detection/protos/*.proto --python_out=.

第二步:

set PYTHONPATH= <Path to 'research' Directory> ; <Path to 'slim' Directory>

例如:

set PYTHONPATH=C:\Users\Guy\Desktop\models\research;C:\Users\Guy\Desktop\models\research\slim

这篇关于导入错误:没有名为“nets"的模块的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持！