-
Hello!
I'm trying to compare performance between an Ultra96-V2 board and a desktop GPU running the same network and model.
To achieve that on the board, I am trying to compile an item from the Vitis…
-
Hi everyone,
I'm a student at Scuola Superiore Sant'Anna in Pisa.
I'm trying to accelerate a network model on a ZCU102 ultrascale+ using Vitis-AI tools v1.2.
The network model has multiple inpu…
-
Hi,
When compiling my network, I get the following error:
[VAI_C][Error] Dilation > 1 is not supported for DepthWise or Deconvolution, current layer is [fc6_separable_conv2d_depthwise].
[VAI_C][E…
Laadr updated
4 years ago
-
Hi,
I have trouble finding a recent document explaining how quantization is done. Is it still done using a uniform symmetric quantization ?
I am asking this question because it occurs to me that i…
Laadr updated
3 years ago
-
-
Hi everyone,
I'm a student at Scuola Superiore Sant'Anna in Pisa.
I'm trying to accelerate a network model on a ZCU102 ultrascale+ using Vitis-AI tools v1.2.
I can successfully quantize the mod…
-
Hi.
I did alveo example "adas_detection" and I made sure that result images write on output directory.
But I can't see result images in code by cv::imshow().
The terminal print below:
termin…
-
I have met a question when I try to use DPUv1Manager.export and DPUv2Manager.export to save model.
The problem description is below:
runfile('/home/zhiyuan/nanodet/tools/export_QAT_onnx.py', wdir…
-
Fetcher failure for URL: 'file:///proj/yocto/dnndk/zynqmp_latest when during make in the petalinux part
[platform.log](https://github.com/Xilinx/Vitis_Embedded_Platform_Source/files/4953905/platform.…
-
Hi there, I'm following the latest Vitis-AI/VART/README.md (from commit: 4ea2380) for setting up ZCU102 in Vitis AI, such that I can cross-compile my network models on host and run them on ZCU102.
Ho…