UPGRADE YOUR BROWSER

We have detected your current browser version is not the latest one. Xilinx.com uses the latest web technologies to bring you the best online experience possible. Please upgrade to a Xilinx.com supported browser:Chrome, Firefox, Internet Explorer 11, Safari. Thank you!

cancel
Showing results for 
Search instead for 
Did you mean: 
Visitor dsskjelb
Visitor
627 Views
Registered: ‎11-01-2018

More instructions on how to run particular model on DNNDK

Hi,

I've tried quite a few things with the DNNDK kit, but have trouble getting some other model to run on it; The decent or dnnc tools fail at some point due to the tools not handling the layers I provide. So I wonder if you could provide some better guidance on steps to take to get around these issues. I'll provide one example. I followed this guide, and intended to run this model on DNNDK, but get this issue : 

*** Deephi DNNDK could not support LRN Layer, (pool1/norm1), please delete it or replace it with BatchNorm + Scale Layer and retrain.

Here is the guide I tried to follow :

https://movidius.github.io/blog/deploying-custom-caffe-models/

The question is - how would I modify the train_val.prototxt to remove LRN and replace it with BatchNorm + Scale? And why doesn't DNNDK support LRN?

I assume that if succesful, I would modify train_val.prototxt so uses BatchNorm and Scale instead of LRN, then run training and finally I might be able to run decent and dnnc on my Caffe model.

 

Hope you can help - I'm sure others have the same questions.

Thanks!

0 Kudos
3 Replies
Xilinx Employee
Xilinx Employee
584 Views
Registered: ‎02-18-2013

Re: More instructions on how to run particular model on DNNDK

@dsskjelbMay I know the model you want to run through DNNDK? 

BTW, the reason DNNDK does not support LRN is that it is seldom used in the modern networks. Most of the networks use Batchnorm which removes the need for LRN. 

 

Visitor wensher.ong
Visitor
334 Views
Registered: ‎04-09-2019

Re: More instructions on how to run particular model on DNNDK

@aluo I am also facing the same problem. I am trying to run DetectNet on DNNDK but got the exact same error as @dsskjelb. Is there any update on this issue?

Does it mean that we have to retrain the whole model using BatchNorm and Scale before rescaling it using DECENT?
0 Kudos
Visitor dsskjelb
Visitor
330 Views
Registered: ‎11-01-2018

Re: More instructions on how to run particular model on DNNDK

Hi,

I realized I didn't answer the question regarding what model I tried to run. I tried various already trained caffee models - e.g. dogs vs cats pretrained model that I found in model zoo I believe it was (https://github.com/BVLC/caffe/wiki/Model-Zoo) But I had issues getting any of the model zoo models to run on DNNDK because it didn't support the now outdated layers. So I had to modify the model and retrain on my laptop just to get it deployed on DNNDK. 

So testing out a pre-trained model on DNNDK was much more difficult than I anticipated.

0 Kudos