-
Notifications
You must be signed in to change notification settings - Fork 164
Open
Labels
Description
参考链接:https://cloud.tencent.com/developer/article/1748267
报错信息:
(py36_pose) zhangxin@zx:~/github/X2Paddle$ x2paddle --framework=caffe \
--prototxt=/home/zhangxin/github/openpose-CMU/models/hand/pose_deploy.prototxt \ --weight=/home/zhangxin/github/openpose-CMU/models/hand/pose_iter_102000.caffemodel \ --save_dir=/home/zhangxin/gitlab_md/pose-service/data/hand \ --params_merge
TensorRT dynamic library (libnvinfer.so) that Paddle depends on is not configured correctly. (error code is libnvinfer.so: cannot open shared object file: No such file or directory)
Suggestions:
- Check if TensorRT is installed correctly and its version is matched with paddlepaddle you installed.
- Configure TensorRT dynamic library environment variables as follows:
- Linux: set LD_LIBRARY_PATH by
export LD_LIBRARY_PATH=... - Windows: set PATH by `set PATH=XXX;paddle.version = 1.8.5
Now translating model from caffe to paddle.
Traceback (most recent call last):
File "/home/zhangxin/miniconda3/envs/py36_pose/bin/x2paddle", line 33, in
sys.exit(load_entry_point('x2paddle==0.8.8', 'console_scripts', 'x2paddle')())
File "/home/zhangxin/miniconda3/envs/py36_pose/lib/python3.6/site-packages/x2paddle-0.8.8-py3.6.egg/x2paddle/convert.py", line 275, in main
args.caffe_proto, params_merge)
File "/home/zhangxin/miniconda3/envs/py36_pose/lib/python3.6/site-packages/x2paddle-0.8.8-py3.6.egg/x2paddle/convert.py", line 146, in caffe2paddle
model = CaffeDecoder(proto, weight, caffe_proto)
File "/home/zhangxin/miniconda3/envs/py36_pose/lib/python3.6/site-packages/x2paddle-0.8.8-py3.6.egg/x2paddle/decoder/caffe_decoder.py", line 248, in init
self.load_using_pb()
File "/home/zhangxin/miniconda3/envs/py36_pose/lib/python3.6/site-packages/x2paddle-0.8.8-py3.6.egg/x2paddle/decoder/caffe_decoder.py", line 256, in load_using_pb
data.MergeFromString(open(self.model_path, 'rb').read())
google.protobuf.message.DecodeError: Error parsing message