sld-columbia / esp

Embedded Scalable Platforms: Heterogeneous SoC architecture and IP integration made easy
Other
343 stars 107 forks source link

Error while using hls4ml #148

Closed mayank-kabra2001 closed 2 years ago

mayank-kabra2001 commented 2 years ago

Hi, I was using hls4ml and trying to implement accelerator using this tutorial (https://www.esp.cs.columbia.edu/docs/hls4ml/hls4ml-guide/).

In the Accelerator generation section while doing hls4ml convert -c keras-config.yml , I found some errors related to python. image

Can someone help me out!!

GiuseppeDiGuglielmo commented 2 years ago

@mayank-kabra2001 I am assuming that you are using the latest version of hls4ml (i.e. main branch). Can you please try the following steps:

git clone https://github.com/hls-fpga-machine-learning/hls4ml.git
cd hls4ml
git checkout v0.6.0 
pip install .

if it does not work yet, please try:

git checkout v0.5.0 
pip install .

Let me know, Giuseppe

mayank-kabra2001 commented 2 years ago

Actually it was CentOS issue, I tried installing hls4ml in ubuntu and it worked.

After doing all the steps for acclerator generation and integration correctly. I named my accelerator mlp_3layers_test and while integration in esp it got renamed to mlp_3layers_test_hls4ml. Now in SoC design and testing I used make mlp_3layers_test_hls4ml and I am facing this error.

image

mlp_3layers_test_hls4ml_hls.log