hello, i am sorry to trouble you . when i use your code ,i met some problem.
(tensorflow1.9.0 cuda9.0 python3.5)
command$ python train_modelnet40_acsd.py
error: Traceback (most recent call last):
File "train_modelnet40_acsd.py", line 179, in
train(args)
File "train_modelnet40_acsd.py", line 33, in train
model = importlib.import_module(model_name)
File "/usr/lib/python3.5/importlib/init.py", line 126, in import_module
return _bootstrap._gcd_import(name[level:], package, level)
File "", line 986, in _gcd_import
File "", line 969, in _find_and_load
File "", line 958, in _find_and_load_unlocked
File "", line 673, in _load_unlocked
File "", line 665, in exec_module
File "", line 222, in _call_with_frames_removed
File "/home/f/f1/step2 point wise/pointwise-master/pointcnn2_acsd.py", line 10, in
conv3p_module = tf.load_op_library(BASE_DIR + '/tf_ops/conv3p/tf_conv3p.so')
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/framework/load_library.py", line 56, in load_op_library
lib_handle = py_tf.TF_LoadLibrary(library_filename)
tensorflow.python.framework.errors_impl.NotFoundError: /home/f/f1/step2 point wise/pointwise-master/tf_ops/conv3p/tf_conv3p.so: undefined symbol: _ZN10tensorflow8internal21CheckOpMessageBuilder9NewStringB5cxx11Ev
Could you see the solution in this issue: https://github.com/scenenn/pointwise/issues/7
It could be related to some ABI flag in gcc. Thanks.
thanks ,i made a mistake yesterday. now it is working .
------------------ 原始邮件 ------------------
发件人: "Binh-Son Hua"[email protected];
发送时间: 2019年7月1日(星期一) 晚上11:37
收件人: "scenenn/pointwise"[email protected];
抄送: "妞妞打蛋蛋"[email protected]; "Author"[email protected];
主题: Re: [scenenn/pointwise] help can not train (#14)
Could you see the solution in this issue: #7
It could be related to some ABI flag in gcc. Thanks.
—
You are receiving this because you authored the thread.
Reply to this email directly, view it on GitHub, or mute the thread.