Felix Jentzsch

Hi, your model is not directly compatible with the series of transformations applied by the default build_dataflow_cfg flow. For example, your model contains depthwise-conv layers, which require the `InferVVAU()` transformation...

Hi, dataflow partitioning fails because not all nodes were converted to their respective HLS Custom Op in the prior steps. Specifically, the MatMul nodes should have been converted to StreamingFCLayer_Batch...

Hi @preusser, @maltanar, @auphelia, as discussed, I moved the development of the dynamic FM sizing and parallel implementation mode to different branches for now so we can merge this part...

Hi @preusser, @maltanar, thanks for your comments and tips! I incorporated them in above commit and marked those that should not require further discussion as resolved.

Hi @mgehre-amd, thanks, I plan to (re-)generate some experiments for a comprehensive HLS/RTL comparison once I find some time. I'll get back to you and link the results here.

This is likely related to some residual connection (join node) in your graph. I assume you are experimenting with the work-in-progress Resnet-50 example?

Hi @kf7lsu , I found 2 separate problems that cause the erroneous behavior: 1. The driver is initialized with the wrong input shapes. With the current folding config, it should...

I see, then you ran into a bug in the driver generation that we recently fixed in #301. In the current dev branch the driver should correctly infer the shapes....

Hi, for 1) you'll have to dig deeper into the logs to find the cause. For example in "finn_zynq_link.runs/impl_1/runme.log" or the Vivado HLS logs inside the "code_gen_ipgen_..." temporary folders of...

Hi, this error usually indicates that your graph contains incompatible nodes that FINN could not convert to HLS backend nodes. If any such node remains in the graph, dataflow partitioning...