python - 导入错误 : No module named 'nets'

Question

我试图从 tensorflow/models 中提供的 export_inference_graph.py 脚本将 trained_checkpoint 转换为最终卡住模型，但出现以下错误结果。是的，我已经将 $PYTHONPATH 设置为“models/slim”，但我仍然收到此错误，有人可以帮我吗？

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

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

$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用我正在使用带有 tensorflow-gpu 版本的 Ubuntu 16.04。

Answer 1

查看 Protobuf 编译 https://github.com/tensorflow/models/blob/master/research/object_detection/g3doc/installation.md并正确设置 PYTHONPATH，这就是我为 Windows 解决此问题的方法

对于 Windows:

来自tensorflow/models/research/

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