- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Hello,
I'm using Intel FPGA AI 2023.2 on ubuntu 20.04 host computer and trying to infer a custom CNN in a Intel Arria 10 SoC FPGA.
Due to some accuracy drops, I replaced the ReLU activation layers with the PReLU activation layer in my mode, supported by the Intel FPGA AI Suite.
The IR model is generated, but the accuracy drops from 97.46% to 63.20%. The model optimizer function is as follows:
mo
--saved_model_dir "{path_savedModelPath}"
--input_shape "{lst_inputShape}"
--model_name "{str_modelName}"
--output_dir "{path_irTargetPath}"
--use_new_frontend
Please note that --use_new_frontend is used, but the IR model is not generated otherwise.
The architecture is A10_FP16_Generic.arch. The options used for dla_compiler are as follows:
dla_compiler
--march "{path_archPath}"
--network-file "{path_xmlPath}"
--o "{path_binPath}"
--foutput-format=open_vino_hetero
--fplugin "HETERO:FPGA,CPU"
--fanalyze-performance
--fdump-performance-report
--fanalyze-area
--fdump-area-report
But the graph is no compiled and the following error is displayed:
Layer (Name: StatefulPartitionedCall/model/p_re_lu_7/add_0_48_result, Type: Result) WRONG MESSAGE: Layer (Name: StatefulPartitionedCall/model/p_re_lu_7/add, Type: Eltwise) WRONG MESSAGE:
Layer (Name: StatefulPartitionedCall/model/p_re_lu_7/mul, Type: Eltwise) is not supported:
FPGA plugin: 'Constant' nodes are not supported as input of nodes Eltwise
Layer (Name: StatefulPartitionedCall/model/p_re_lu_7/Relu_1, Type: Relu) WRONG MESSAGE:
Layer (Name: StatefulPartitionedCall/model/p_re_lu_7/Neg_1, Type: PowerIE) WRONG MESSAGE:
Layer (Name: Constant_2809, Type: Constant) is not supported:
Error occurred.
../compiler/aot_plugin/src/dla_executable_network.cpp:134 Graph is not supported on FPGA plugin due to existance of layer (Name: StatefulPartitionedCall/model/p_re_lu_7/mul, Type: Eltwise)
in topology. Most likely you need to use heterogeneous plugin instead of FPGA plugin directly.
Find the model in the following link https://consigna.ugr.es/?s=download&token=11ed96b6-769d-4875-b8c7-0b73c1d0149a
Same problem still present in OpenVINO 2022.3.1 + Intel FPGA AI Suite 2023.3
Link Copied
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Hi,
The link provided is not working as it is showing missing token.
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
@JohnT_Intelit works. The token is in the link.If you encounter difficulties downloading it, could you please provide an alternative method for securely sending files with a size exceeding 71MB?
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Hi,
I am able to download it. Sorry for the confussion.
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Hi,
Is it possible to try other arch? Or you would like to only use generaric.arch file only?
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Hi,
Is there a chance to try different type of bitstream to see the result?
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Hi,
Can you list out the architecture use and what is the differences observed?
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Hi,
Can you list out the architecture use and what is the differences observed?
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Hi,
Can you list out the architecture use and what is the differences observed?
Anticipate your reply
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
We do not receive any response from you to the previous question/reply/answer that I have provided. This thread will be transitioned to community support. If you have a new question, feel free to open a new thread to get the support from Intel experts. Otherwise, the community users will continue to help you on this thread. Thank you.
![](/skins/images/7FC17B7B85029576C25F1E43CE255B51/responsive_peak/images/icon_anonymous_message.png)
- Subscribe to RSS Feed
- Mark Topic as New
- Mark Topic as Read
- Float this Topic for Current User
- Bookmark
- Subscribe
- Printer Friendly Page