- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
We have 5-D tensor in our graph. 5-D operations are not supported by OpenVINO. Specifically, in our case, transpose and concat.
So we decided to offload the computations to Tensorflow.
We followed the procedure provided at https://software.intel.com/en-us/articles/OpenVINO-ModelOptimizer#offloading-computations-tensorflow
and have managed to generate libtensorflow_call_layer.so.
Our application is in python and we are using internal GPU.
We want to know how to provide the extension (libtensorflow_call_layer.so) to the inference engine plugin (IEPlugin).
Thanks in advance,
Sridhar
Link Copied
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Noticed the following statement "The custom layer supports inference only on a CPU, not on Intel® Integrated Graphics or on Intel® FPGA."
What is the plan to support 5-D Tensor or offloading unsupported ops to Tensorflow (while running IE with Integrated Graphics) ?
For CPU, is this correct way of providing extension?
plugin.add_cpu_extension('/home/u1/tensorflow/libtensorflow_call_layer.so')
Thanks,
Sridhar.
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Hi Sridhar,
To add a custom layer in your application you need to have the following lines of code:
InferencePlugin plugin = PluginDispatcher({"path to plugin directory", ""}).getPluginByDevice("CPU"); IExtensionPtr extension_ptr = make_so_pointer<IExtension>("path to custom layer library"); plugin.AddExtension(extension_ptr);
Will reply back with what the support will be for 5-D tensors and offloading parts of a model to native tensorflow to be ran on Integrated graphics.
Kind Regards,
Monique Jones
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Hi Monique,
Thanks much for your reply. Can you please provide the python equivalent code for what you have posted ?
We tried a few variants, but could not get it to work.
Best Regards,
Sridhar.
- Subscribe to RSS Feed
- Mark Topic as New
- Mark Topic as Read
- Float this Topic for Current User
- Bookmark
- Subscribe
- Printer Friendly Page