Question

我正在尝试使用YoloV3优化tensorRT

我来到了这篇名为Have you Optimized your Deep Learning Model Before Deployment?

的帖子

Docker用于帖子。

使用Enabling GPUs in the Container Runtime Ecosystem安装nvidia-docker2

从aminehy/tensorrt-opencv-python3提取了最新版本的docker映像docker pull aminehy/tensorrt-opencv-python3:version-1.3

这是图片

$ sudo docker images
REPOSITORY                        TAG                             IMAGE ID            CREATED             SIZE
nvcr.io/nvidia/cuda               10.1-cudnn7-devel-ubuntu18.04   b4879c167fc1        2 weeks ago         3.67GB
aminehy/tensorrt-opencv-python3   version-1.3                     0302e477816d        4 months ago        5.36GB
aminehy/tensorrt-opencv-python3   latest                          604502819d12        4 months ago        4.94GB
aminehy/tensorrt-opencv-python3   version-1.1                     d693210c500c        4 months ago        4.94GB

我跑了

$sudo docker run -it --rm -v $(pwd):/workspace --runtime=nvidia -w /workspace -v /tmp/.X11-unix:/tmp/.X11-unix -e DISPLAY=unix$DISPLAY aminehy/tensorrt-opencv-python3:version-1.3```

=====================
== NVIDIA TensorRT ==
=====================

NVIDIA Release 19.05 (build 6392482)

NVIDIA TensorRT 5.1.5 (c) 2016-2019, NVIDIA CORPORATION.  All rights reserved.
Container image (c) 2019, NVIDIA CORPORATION.  All rights reserved.

https://developer.nvidia.com/tensorrt

To install Python sample dependencies, run /opt/tensorrt/python/python_setup.sh

root@a38b20eeb740:/workspace# cd /opt/tensorrt/python/
root@a38b20eeb740:/opt/tensorrt/python# chmod +x python_setup.sh 
root@a38b20eeb740:/opt/tensorrt/python# ./python_setup.sh
Requirement already satisfied: Pillow in /usr/local/lib/python3.5/dist-packages (from -r /opt/tensorrt/samples/sampleSSD/requirements.txt (line 1)) (6.0.0)
WARNING: You are using pip version 19.2.1, however version 19.3.1 is available.
You should consider upgrading via the 'pip install --upgrade pip' command.
Ignoring torch: markers 'python_version == "3.7"' don't match your environment
......
......
......
Setting up graphsurgeon-tf (5.1.5-1+cuda10.1) ...
Setting up uff-converter-tf (5.1.5-1+cuda10.1) ...
Traceback (most recent call last):
  File "<string>", line 1, in <module>
  File "/usr/lib/python2.7/dist-packages/uff/__init__.py", line 1, in <module>
    from uff import converters, model  # noqa
  File "/usr/lib/python2.7/dist-packages/uff/model/__init__.py", line 1, in <module>
    from . import uff_pb2 as uff_pb  # noqa
  File "/usr/lib/python2.7/dist-packages/uff/model/uff_pb2.py", line 6, in <module>
    from google.protobuf.internal import enum_type_wrapper
ImportError: No module named google.protobuf.internal
chmod: cannot access '/bin/convert_to_uff.py': No such file or directory

在convert_to_uff.py内似乎找不到任何名为bin的文件

怎么回事？

我哪里出错了？

Answer 1

尝试重新安装protobuf，以确保：

pip install protobuf

'/bin/convert_to_uff.py'：没有这样的文件或目录

1 个答案: