Nvidia digits to train cnn with caffe

General discussion about topics related to OpenMV.
User avatar
chrisPyres66
Posts: 90
Joined: Mon Jul 16, 2018 9:22 am
Location: France

Nvidia digits to train cnn with caffe

Postby chrisPyres66 » Wed Apr 03, 2019 4:47 am

Dear all,

Do you know if it is possible to use Nvidia digits software to train CNN and then convert it to openmv ?

Thanks,
User avatar
iabdalkader
Posts: 844
Joined: Sun May 24, 2015 3:53 pm

Re: Nvidia digits to train cnn with caffe

Postby iabdalkader » Wed Apr 03, 2019 1:47 pm

Hi, yes and I used it before.
User avatar
chrisPyres66
Posts: 90
Joined: Mon Jul 16, 2018 9:22 am
Location: France

Re: Nvidia digits to train cnn with caffe

Postby chrisPyres66 » Thu Apr 04, 2019 6:11 am

Nice, do you have some advice because i dont manage to quantize to openmv camera with :

Code: Select all

python2 ~/openmv/ml/cmsisnn/nn_quantizer.py --gpu --model ./quantizer.prototxt --weights ./snapshot_iter_240.caffemodel --save ./V22_Lenet.pkl
I used a lenet network with my own image set.
As nvidia digits is used in a docker, i modified the directory in the generated prototxt but it stops at this step :

Code: Select all

I0404 11:27:20.907341 24927 net.cpp:257] Network initialization done.
I0404 11:27:20.940609 24927 net.cpp:746] Ignoring source layer train-data
F0404 11:27:20.940631 24927 blob.cpp:496] Check failed: count_ == proto.data_size() (500 vs. 0) 
*** Check failure stack trace: ***
Abandon (core dumped)
I joined the original and modified prototxt files.

I tried with a custom network from an openmv network but with the same results ...
I should misunderstand a step. Thanks for your help,
Attachments
nvidiaDigits_files.zip
(1.5 KiB) Downloaded 131 times
User avatar
iabdalkader
Posts: 844
Joined: Sun May 24, 2015 3:53 pm

Re: Nvidia digits to train cnn with caffe

Postby iabdalkader » Thu Apr 04, 2019 12:31 pm

Maybe it's a different version of caffe, I think you need to install it from source:
https://github.com/NVIDIA/DIGITS/blob/d ... Install.md

Return to “General Topics”

Who is online

Users browsing this forum: Bing [Bot] and 4 guests