Sioni Summers
Sioni Summers
I see you have `qconv2d_batchnorm` layer which folds the weights of the two layers and then quantizes. We're bringing support for that to[ hls4ml](https://github.com/fastmachinelearning/hls4ml/pull/298), and it should help us save...
Add to `model_quantize` the capability to accept an existing `qkeras` model and return a model with a different `quantizer_config`. This could be used, for example, to train at higher precision...
Many tests of single layer models to test the converters. The idea is to probe the correctness of the converters/layer handling just from observing the output of the hls4ml `predict`...
It could be useful to have a logging utility for a more verbose interaction with hls4ml. At the moment we print some information about the model during conversion, and some...
## Improper handling of PyTorch `Linear` layer with `bias=False` When a PyTorch model has a `Linear` layer with `bias=False`, conversion crashes out when trying to access the non-existent bias data...
Running through the hls4ml-tutorial using current hls4ml master branch, I see an issue in the numerical performance of the hls4ml evaluated accuracy of the QKeras model in part 4. The...
The profiling plots should include the distribution of the input layer / input data and the box for the input data type. Here's a profiling plot for a "good" version...
It would be nice to extend [vivado_report](https://github.com/fastmachinelearning/hls4ml/blob/master/hls4ml/report/vivado_report.py) utility to include in the extracted results: - per-layer resource & latency breakdown - Post logic synthesis resources
Thanks for the nice project! I'm trying to port some testbench simulations I have over to GHDL, and in doing so I hit this issue. **Description** Trying to read a...
Currently, AdaBoost models from scikit-learn [1] are implicitly ignored by conifer's sklearn converter [2]. Neither of the existing BDT or RF converter methods work "out of the box" for AdaBoostClassifier,...