Vladimir
Vladimir
# Description This is the refined version of a Conv1D/2D implementation that urolls the input feature matrix of im2col algorithm for the `io_parallel` implementation. The general idea is to generate...
# Description An initial attempt at supporting Vitis HLS. Introduces a new backend (`Vitis`) that takes most of the stuff over from `Vivado` backend and changes things a little. I...
This is already possible through the API, but we should also expose it through `hls4ml` tool. So the user would specify his implementation of a layer, a config and function...
# Description This PR adds the ability to generate HLS code to evaluate symbolic expressions in hls4ml for people wanting to play with symbolic regression. It is very simple, it...
**Describe the bug** Can't use latest TFMOT 0.8.0 with the latest TF 2.15.0.post1 on a fresh install because of missing `tf_keras` dependency. This complicates installations of downstream packages that depend...
# Description Support for parsing `Upsample` layers that was started in #951. This one is more robust, supports 2d tensors and includes a test case. ## Type of change -...
# Description This introduces the ability to specify `auto` as a precision string, that implies hls4ml should infer the precision in some way. This is not exposed by default via...
# Description The current channels_last converter inserts a transpose node after the "flatten" layer to ensure the order is correct for the subsequent fully connected layer. This isn't strictly required...
## Quick summary While a bit nonsensical, QKeras layers without quantizers are legal. For example `QDense(n_units)` (without `kernel_quantizer=something`) fails conversion since we expect the quantizers to be present in the...
# Description Changing configuration in hls4ml requires deep understanding of the conversion process in order to be successful. New layers can be introduced, which pick up default precision definition causing...