xilinx / pynq-dl Goto Github PK
View Code? Open in Web Editor NEWXilinx Deep Learning IP
License: BSD 3-Clause "New" or "Revised" License
Xilinx Deep Learning IP
License: BSD 3-Clause "New" or "Revised" License
When i try to run the HLS script it fails:
In file included from C:/Xilinx/Vivado/2018.3/include/hls_fpo.h:186:0,
from C:/Xilinx/Vivado/2018.3/include/hls_half.h:44,
from C:/Xilinx/Vivado/2018.3/include/etc/ap_private.h:90,
from C:/Xilinx/Vivado/2018.3/include/ap_common.h:641,
from C:/Xilinx/Vivado/2018.3/include/ap_int.h:54,
from ../../../../xf_resize_config.h:34,
from ../../../../xf_resize_accel.cpp:30:
C:/Xilinx/Vivado/2018.3/include/floating_point_v7_0_bitacc_cmodel.h:135:0: note: this is the location of the previous definition
#define __GMP_LIBGMP_DLL 1
@e Simulation failed.
ERROR: [SIM 211-100] CSim failed with errors.
INFO: [SIM 211-3] *************** CSIM finish ***************
4
while executing
"source hls_script.tcl"
invoked from within
"hls::main hls_script.tcl"
("uplevel" body line 1)
invoked from within
"uplevel 1 hls::main {*}$args"
(procedure "hls_proc" line 5)
invoked from within
"hls_proc $argv"
INFO: [Common 17-206] Exiting vivado_hls at Tue Feb 12 19:01:09 2019...
Hello. I encountered an error when installing using the command:
llecting git+https://github.com/Xilinx/PYNQ-DL.git
Cloning https://github.com/Xilinx/PYNQ-DL.git to /tmp/pip-req-build-tnq2hrn9
Installing collected packages: pynqDL
Running setup.py install for pynqDL ... error
Complete output from command /opt/python3.6/bin/python3.6 -u -c "import setuptools, tokenize;file='/tmp/pip-req-build-tnq2hrn9/setup.py';f=getattr(tokenize, 'open', open)(file);code=f.read().replace('\r\n', '\n');f.close();exec(compile(code, file, 'exec'))" install --record /tmp/pip-record-ucjpjnm0/install-record.txt --single-version-externally-managed --compile:
Reading package lists...
Building dependency tree...
Reading state information...
0 upgraded, 0 newly installed, 0 to remove and 0 not upgraded.
ERROR: You must give at least one requirement to install (see "pip help install")
Traceback (most recent call last):
File "", line 1, in
File "/tmp/pip-req-build-tnq2hrn9/setup.py", line 106, in
install_packages()
File "/tmp/pip-req-build-tnq2hrn9/setup.py", line 48, in install_packages
subprocess.check_call(['pip3.6', 'install'])
File "/opt/python3.6/lib/python3.6/subprocess.py", line 291, in check_call
raise CalledProcessError(retcode, cmd)
subprocess.CalledProcessError: Command '['pip3.6', 'install']' returned non-zero exit status 1.
----------------------------------------
Command "/opt/python3.6/bin/python3.6 -u -c "import setuptools, tokenize;file='/tmp/pip-req-build-tnq2hrn9/setup.py';f=getattr(tokenize, 'open', open)(file);code=f.read().replace('\r\n', '\n');f.close();exec(compile(code, file, 'exec'))" install --record /tmp/pip-record-ucjpjnm0/install-record.txt --single-version-externally-managed --compile" failed with error code 1 in /tmp/pip-req-build-tnq2hrn9/
Hello,
I have tried installing this with the following (as stated in the instructions):
sudo -H pip3.6 install --upgrade git+https://github.com/Xilinx/PYNQ-DL.git
however, this gave the following error
pip3.6: command not found
I believe the new command is pip3 (since this change worked with another git repo), so I changed it to the following:
sudo -H pip3 install --upgrade git+https://github.com/Xilinx/PYNQ-DL.git
This showed the installation was successful and following this, I had rebooted, however, no new notebooks appeared, any advice would but much appreciated.
I download this whole project with to my pynq board and change the overlay path to the right place. When I run the first time, the data printed is the same as darius-cnn-ip.ipynb, so it's loaded right . However, when I explore the detailed parameter, I find many problems.
First, when I print the OFM array, I find many negative number in it??? The input IFM and weight is the same as the demo which is random ranging from 0 to 255. I can't explain why the convolution and max pooling can change positive integer to negtive integer.......
Then, I change the parameter for pooling and run the demo again, I find the OFM does't change. I can't explain why this happens.
You can also find the first problem, just by changing your demo in darius-cnn-ip.ipynb:
for i in range(0, 15, 4): print(hex(ofm[i]))
change to a larger range:
for i in range(0, 159, 4): print(hex(ofm[i]))
and many problems.
You can try different pooling parameter and see if the output OFM is changed.
If my operation is wrong, can you show me the right using process?
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.