Jiajun Thomas

when I run "sudo make -j8", it shows like these: make -C tvm make[1]: Entering directory '/home/enai/Desktop/project/heterocl/tvm' /bin/sh: 1: /home/enai/Desktop/project/heterocl: Permission denied /bin/sh: 1: /home/enai/Desktop/project/heterocl: Permission denied make[1]: execvp: /home/enai/Desktop/project/heterocl:...

> HI @lloo099. I believe the error is caused by the permission issues. You should make sure you have the right permission for those folders. And you do not have...

Sorry, it still has problems with permission. But I already use command"chmod 777 .." Could you help me with it? @seanlatias @Hecmay ``` g++ -std=c++11 -Wall -O2 -Iinclude -I/home/enai/Desktop/project/heterocl/tvm/dlpack/include -I/home/enai/Desktop/project/heterocl/tvm/dmlc-core/include...

> @lloo099, Just want to know how you changed the permission to that folder? Can you please try to use the fixes mentioned in this link? https://lanvu.wordpress.com/2011/08/05/fix-the-error-make-execvp-permission-denied/ > > If...

Hi @kevin-mahon , thanks for your sharing. I am also face the pytorch conversion issue. The error shows like this: TypeError: convert_from_pytorch_model() missing 1 required positional argument: 'input_shape' Would you...

> @lloo099 Hello, I used (channels, height, width) in the lines: > > > config = hls4ml.utils.config_from_pytorch_model(model, granularity='model') > > hlsmodel = hls4ml.converters.convert_from_pytorch_model(model, (1, 90,160), hls_config=config) Thanks a lot. But...

Hi @LordScarface , thanks for your post. Do you have padding in your conv2d in the Resnet model? Would you mind provide your model file also, thanks

Thanks, I am not sure the 'same' padding means 0 padding in your models. Normally, conv2d of hls4ml has zero padding but can configure it. I suggest you test a...

> As far as I know, the resource strategy is not available now. In this way, it mainly supports the latency strategy. If you want to get a good balance...

> The Resource Strategy has worked for me in the past, I saw that in #534 you were able to get past synthesis with the VGG-16 model, when choosing the...