UPGRADE YOUR BROWSER

We have detected your current browser version is not the latest one. Xilinx.com uses the latest web technologies to bring you the best online experience possible. Please upgrade to a Xilinx.com supported browser:Chrome, Firefox, Internet Explorer 11, Safari. Thank you!

cancel
Showing results for 
Search instead for 
Did you mean: 
Contributor
Contributor
519 Views
Registered: ‎03-24-2018

Can not transfer model weight to the FPGA via jupyter notebook

Hi,

Now I can compile and quantize tensorflow network on  Jupyter notebook after ml-suite is upated newest version  ( 3 days ago on commit 33dadbbd1a98acbab353a379bbc7e96547a0c2e3 )

But now, I got other issue after I tried to run 6th step in https://github.com/Xilinx/ml-suite/blob/master/notebooks/image_classification_tensorflow.ipynb  as below:

My Os is ubuntu 16.04. And my card is VCU1525.

 Capture300.PNG

And the log is on the console as below:

 Capture301.PNG

Please advise me on this issues.

 Regards,

Long.

0 Kudos
2 Replies
Contributor
Contributor
485 Views
Registered: ‎03-24-2018

Re: Can not transfer model weight to the FPGA via jupyter notebook

Hi,

Any one can run fine for tensorflow on jupyter notebook ? 

https://github.com/Xilinx/ml-suite/blob/master/notebooks/image_classification_tensorflow.ipynb

Regards,

Long.

 

0 Kudos
Contributor
Contributor
454 Views
Registered: ‎11-08-2018

Re: Can not transfer model weight to the FPGA via jupyter notebook

Hi @duclong,

Even i got the same error on command line.

$ cd ml-suite/examples/classification

$ ./run.sh -p 1525 -t test_classify -k med -b 16

I am getting the following error:

Loading weights/bias/quant_params to FPGA...
ERROR: Failed to allocate A device memory
python: xblas.cpp:3163: void xblasLoadA(XBLASHandle&, int, const void*, const char*, XBLASConfig*, int): Assertion `ret' failed.

0 Kudos