Search found 8 matches

by adrielkuek
Wed Jan 09, 2019 3:58 am
Forum: Technical Discussion
Topic: Implementing low-cost pre-trained NN like MobileNet/SqueezeNet
Replies: 11
Views: 2666

Re: Implementing low-cost pre-trained NN like MobileNet/SqueezeNet

Oh so its fixed? Cool I can try it out and test it. Is the network model updated in your Git repo? If it is, I'll go over and download the files and try once more.

Thanks!

Adriel
by adrielkuek
Wed Jan 09, 2019 2:45 am
Forum: Technical Discussion
Topic: Implementing low-cost pre-trained NN like MobileNet/SqueezeNet
Replies: 11
Views: 2666

Re: Implementing low-cost pre-trained NN like MobileNet/SqueezeNet

Thanks Kwabena, So its possible! Cool! Understand the implications for making the product scalable and balancing profit-margins as well. It's never an easy decision to make. For the case of nice SDRAM controllers for STM32s, I would think that the worst case scenario would be to go with a simple ser...
by adrielkuek
Wed Jan 09, 2019 1:55 am
Forum: Technical Discussion
Topic: Implementing low-cost pre-trained NN like MobileNet/SqueezeNet
Replies: 11
Views: 2666

Re: Implementing low-cost pre-trained NN like MobileNet/SqueezeNet

Hi kwabena, just a question on the memory heap onboard the M7. Not too sure has this been raised before. I was wondering of instead of storing the network weights and coefficients onboard the MCU heap, which is limited in size, is it possible to store it on an external SRAM instead? I presume the ne...
by adrielkuek
Sat Dec 15, 2018 12:41 am
Forum: Technical Discussion
Topic: Implementing low-cost pre-trained NN like MobileNet/SqueezeNet
Replies: 11
Views: 2666

Re: Implementing low-cost pre-trained NN like MobileNet/SqueezeNet

Which portion of the code is generating the issue? Is it the cmsis.nn functions or in the training phase when generating the .nerwork file? If you don’t mind sharing more info on the problem, I’m all in to help resolve the issue! ☺️ Let me know how can I help.

Thanks!
by adrielkuek
Thu Dec 13, 2018 5:12 am
Forum: Technical Discussion
Topic: Implementing low-cost pre-trained NN like MobileNet/SqueezeNet
Replies: 11
Views: 2666

Re: Implementing low-cost pre-trained NN like MobileNet/SqueezeNet

Hey kwabena, great hearing from you. I found the git repo links to some of the additional nn examples that you were mentioning about that was recently published. In particular, I was interested in the INRIA people detection example that you have. I've downloaded the inria.network NN file into the M7...
by adrielkuek
Mon Dec 10, 2018 4:43 am
Forum: Technical Discussion
Topic: Implementing low-cost pre-trained NN like MobileNet/SqueezeNet
Replies: 11
Views: 2666

Implementing low-cost pre-trained NN like MobileNet/SqueezeNet

Hi, Just wondering has anybody here managed to convert some of the popular low-cost NNs out there such as MobileNet_v1 or SqueezeNet_v1.0 to be implemented on the openMV M7? Understand that the accuracy will not be optimal, but we are looking at a quick proof-of-concept for such NN implementation on...
by adrielkuek
Mon Dec 03, 2018 4:01 am
Forum: Technical Discussion
Topic: Accessing/translating to lower level C/C++ code
Replies: 4
Views: 1875

Re: Accessing/translating to lower level C/C++ code

Understood. I have another enquiry that is not related to this topic. I would like to power the openMV module via external power from a battery source (3.6V) if possible. Looking at the schematic there are 2 diodes at D1 for reverse polarity protection. Is there a way to bypass the USB power line VB...
by adrielkuek
Fri Nov 30, 2018 3:44 am
Forum: Technical Discussion
Topic: Accessing/translating to lower level C/C++ code
Replies: 4
Views: 1875

Accessing/translating to lower level C/C++ code

Hi,

So after we have programmed a new project and verified the functionality of the camera in micropython in the openMV IDE, Is there any way that we can access the lower level C/C++ code for further optimisation/tunability?

Thanks!

Adriel

Go to advanced search