Batuhan Akkuş

Results 18 comments of Batuhan Akkuş

Hello, Did you find how to train the model?

I have the same issue with automatic (basic). I use the notebook with a custom ONNX file that I use CNV network and generate by Brevitas. I am sure that...

Hello, I'm looking for the same example. Did you find any document?

Hello, It is written [here](https://xilinx.github.io/brevitas/getting_started.html) how to export basic model to ONNX format after training. Weight-activation-bias model export_onnx_qcdq(quant_weight_act_bias_lenet, torch.randn(1, 3, 32, 32), export_path='4b_weight_act_bias_lenet.onnx') FINN expects FINN-ONNX and not all ONNX...

> Hello, I encountered the same problem and I follow your reply. I have set the env variables and run "./run-docker.sh quicktest" and it is still giving the same error....

Hello, I have the same error in the same example with a custom network #936

Hello Auphelia, Thank you for your reply. I will try it with the FINN version and check the transformation. I am just comparing two different bit-width QAT for between 1...

Hello @auphelia , What is the situation right now for FINN and Brevitas versions? Can I use the latest ones for both? Bests,

> This could happen if the design request more resource than target platform capacity( too much LUT, FlipFlop ... etc ). Also check estimation report's resource part to ensure everything...

Hello @auphelia , I could not solve it. This is the vivado log below. There is an issue about _**Misformed interface info attr: xilinx.com:interface:axis:1.0 m_axis_0**_ Could you help me? CC:...