Comments (12)
Official support to Ultrascale+ PYNQ boards (Ultra96/ZCU104) will be added soon.
from qnn-mo-pynq.
Official support to Ultrascale+ PYNQ boards (Ultra96/ZCU104) will be added soon.
Good news,and when it release?
from qnn-mo-pynq.
Is there any news ?
from qnn-mo-pynq.
Just pushed the update to PYNQ 2.3 and support to Ultra96 PYNQ board (with Ultrascale+ Zynq)
from qnn-mo-pynq.
Please let me know if this works for you
from qnn-mo-pynq.
hi @giuliogamba when will support ZCU104?
from qnn-mo-pynq.
@giuliogamba
Sorry for long reply, was out of the office.
Update did not solve problem, still getting "Bus error" with "unhandled alignment fault (7)"
from qnn-mo-pynq.
It seems odd, we were able to compile everything on Ultra96 board. Are you sure you pulled the latest version? On which board are you experiencing this?
from qnn-mo-pynq.
Yes, I tried the latest version too, without success.
Yes, It's odd, because app_hw work without problems, but lib_hw fail , both use same functions.
But I find problem source, it is "memset" which is for (char *)type buffer , in file "qnn/src/library/host/offload-utils.cpp" , it is used in "padTo" function.
It failing when zeroing testBuffer provided in singleInference() under lib_hw . If it is executed on additional buffer, it do not fail.
But final solution I use is in file "qnn/src/library/host/offload-utils.cpp" line 40 :
"OffloadUtils::memset(bufferPadded, 0, outputSize); "
need replace with
"OffloadUtils::memset((ExtMemWord *)bufferPadded, 0, outputSize);"
I testing on 2 different boards: Xilinx ZCU102 and Enclustra Mars XU3 .
And using lib_hw from Python3.6 for quicker prototyping.
from qnn-mo-pynq.
You are correct, the problem is in the memset when used on non-cacheable memory with -O3
as optimization strategy.
That's why we changed the optimization strategy here to -O2
and avoid the problem.
from qnn-mo-pynq.
Thanks for pointing to exact changes relayed to problem. I will recheck once again if I recompile all correctly and give report.
from qnn-mo-pynq.
Yes, you are right, optimization strategy changes result working lib_hw.
Thanks.
from qnn-mo-pynq.
Related Issues (20)
- Question on the output activation HOT 2
- platform ultra96 is v1 or v2? HOT 2
- If I want to know the location of detection boxes, what should i do HOT 2
- If I want to know the coordinates of Bounding-box (four points), what should I do HOT 1
- Try to get the boxs location
- ZCU104 Support HOT 1
- ZedBoard support HOT 2
- Hardware design rebuild support HOT 1
- Problems encountered while executing the example HOT 1
- Tinier yolo training HOT 1
- Errors rebuilding hardware design HOT 3
- Unable to run Tinyyolo with the video file
- How does it detect other targets?
- 无法运行 sudo pip3 install git + https://github.com/Xilinx/QNN-MO-PYNQ.git命令 HOT 1
- I want to use webcamera with tiny-yolo-image-loop
- No guidelines on contribution and different networks/models
- Who can tell me how to rebuild hardware design in Windows?thanks. HOT 2
- How to get hls project ?Thanks.
- issues about BNN
- Issues with Exporting RTL as a Vivado IP
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from qnn-mo-pynq.