-
Notifications
You must be signed in to change notification settings - Fork 297
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
use modified model of zynqnet and run on CPU but segment fault. #52
Comments
Some people also had segmentation faults with the original ZynqNet. It usually helped when the SHARED_DRAM memory was increased. Try allocating more memory there (eg. 2x more, doesn‘t really matter).
… Am 12.06.2018 um 07:12 schrieb KingOfBanana ***@***.***>:
Hi David,
I want to put zynqnet on zynq 7Z030 which has less brams compared to your 7045, so I have modified your zynqnet model. I changed the output channels of some layers to reduce the conv kernels in zynqnet to reduce the requirement of bram.I ran my customed program on my PC found it has segment fault, but yours original program has no error.I just used your tools to regenerate the weights.bin, indata.bin, network.cpp and network.hpp and replaced them in original netwok. Do you think any other changes should be taken? Thanks!
—
You are receiving this because you are subscribed to this thread.
Reply to this email directly, view it on GitHub, or mute the thread.
|
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Hi David,
I want to put zynqnet on zynq 7Z030 which has less brams compared to your 7045, so I have modified your zynqnet model. I changed the output channels of some layers to reduce the conv kernels in zynqnet to reduce the requirement of bram.I ran my customed program on my PC found it has segment fault, but yours original program has no error.I just used your tools to regenerate the weights.bin, indata.bin, network.cpp and network.hpp and replaced them in original netwok. Do you think any other changes should be taken? Thanks!
The text was updated successfully, but these errors were encountered: