- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Share procedures that NCSDK 2.05.00.02 was successfully "make examples" to RaspberryPi3 / Ubuntu16.04.
I am happy if it will be helpful to everyone.
After implementation, I have only tested the limited scope that I need.
If you can do, I would like to tell you the results of your run test.
■ Notes
Intel's informal procedures.
Tensorflow 1.8.0 is not officially supported by Intel.
No responsibility can be incurred no matter what happens.
Please take responsibility for your actions.
The NCSDK version to be installed is "v2.05.00.02".
Successful July 12, 2018
■ Installation sequence
$ cd ~
$ wget https://github.com/google/protobuf/releases/download/v3.5.1/protobuf-all-3.5.1.tar.gz
$ tar -zxvf protobuf-all-3.5.1.tar.gz
$ cd protobuf-3.5.1
$ ./configure
$ sudo make -j1
$ sudo make install
$ cd python
$ export LD_LIBRARY_PATH=../src/.libs
$ python3 setup.py build --cpp_implementation
$ python3 setup.py test --cpp_implementation
$ sudo python3 setup.py install --cpp_implementation
$ sudo ldconfig
$ protoc --version
$ wget https://github.com/lhelontra/tensorflow-on-arm/releases/download/v1.8.0/tensorflow-1.8.0-cp35-none-linux_armv7l.whl
$ sudo pip3 install tensorflow-1.8.0-cp35-none-linux_armv7l.whl
$ rm tensorflow-1.8.0-cp35-none-linux_armv7l.whl
$ cd ncsdk
$ make examples -j1
■ Problem
Tensorflow 1.7.0 is always "make error" when building InceptionV3. (symbol undefined …)
Tensorflow 1.7.0's github also had a similar issue.
Tensorflow 1.7.0 seems to be unstable.
Link Copied
0 Replies

Reply
Topic Options
- Subscribe to RSS Feed
- Mark Topic as New
- Mark Topic as Read
- Float this Topic for Current User
- Bookmark
- Subscribe
- Printer Friendly Page