Data

Tools

Indexes

Applications

Experiments

Open Source Science

Recent Releases of hls4ml

hls4ml - gladiolus 1.1.0

What's Changed

The major changes compared to v1.0.0 are:

  • A new FIFO depth optimizer for the Vitis backend by @steltze in https://github.com/fastmachinelearning/hls4ml/pull/1037
  • Expansion of the oneAPI backend by adding depthwise convolution and RNN State and Activation Quantizers by @laurilaatu in https://github.com/fastmachinelearning/hls4ml/pull/1131 and https://github.com/fastmachinelearning/hls4ml/pull/1195
  • A new general transpose implementation for vivado/vitis by @calad0i in https://github.com/fastmachinelearning/hls4ml/pull/1124, adapted for oneAPI by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/1165
  • New depthwise 1D and 2D implementations for the resource strategy for io_stream by @steltze in https://github.com/fastmachinelearning/hls4ml/pull/1079

The full list of changes is:

  • Don't overwrite already set accum_t, fix pointwise output resolution by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/1146
  • Split hgq tests and isolate qkeras tests to make tests run in under 1h by @JanFSchulte in https://github.com/fastmachinelearning/hls4ml/pull/1153
  • Depthwise convolution for oneAPI by @laurilaatu in https://github.com/fastmachinelearning/hls4ml/pull/1131
  • [pre-commit.ci] pre-commit autoupdate by @pre-commit-ci in https://github.com/fastmachinelearning/hls4ml/pull/1159
  • Fix Vivado Accelerator missing partition factor variable by @bo3z in https://github.com/fastmachinelearning/hls4ml/pull/1160
  • Bug fixes for channel-last conversions in pytorch by @JanFSchulte in https://github.com/fastmachinelearning/hls4ml/pull/1161
  • Support Constant nodes in pytorch parser by @JanFSchulte in https://github.com/fastmachinelearning/hls4ml/pull/1123
  • oneAPI 2025.0 include changes by @laurilaatu in https://github.com/fastmachinelearning/hls4ml/pull/1149
  • Update Torch profiler by @jicampos in https://github.com/fastmachinelearning/hls4ml/pull/1156
  • Add general transpose for vivado/vitis by @calad0i in https://github.com/fastmachinelearning/hls4ml/pull/1124
  • remove np.float_ (deprecated in numpy>=2.0) by @calad0i in https://github.com/fastmachinelearning/hls4ml/pull/1172
  • add check for no inputs in insert_node by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/1170
  • added check for conv implementation by @jicampos in https://github.com/fastmachinelearning/hls4ml/pull/1155
  • Lazy converter imports and migrate to pyproject.toml by @calad0i in https://github.com/fastmachinelearning/hls4ml/pull/1094
  • Fix pytorch upsample parsing by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/1186
  • [pre-commit.ci] pre-commit autoupdate by @pre-commit-ci in https://github.com/fastmachinelearning/hls4ml/pull/1182
  • Fixes for quantised RNNs in data type inconsistencies by @bo3z in https://github.com/fastmachinelearning/hls4ml/pull/1171
  • Support multiple outputs in pytorch parser by @JanFSchulte in https://github.com/fastmachinelearning/hls4ml/pull/1151
  • general transpose for oneAPI by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/1165
  • add option to not write tar.gz for oneAPI and Quartus by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/1189
  • Fix paths to weights in build_lib.sh for VivadoAccelator backend by @JanFSchulte in https://github.com/fastmachinelearning/hls4ml/pull/1198
  • Fix link to FAQ in README.md by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/1201
  • Update pull request template by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/1202
  • [pre-commit.ci] pre-commit autoupdate by @pre-commit-ci in https://github.com/fastmachinelearning/hls4ml/pull/1199
  • oneAPI RNN State and Activation Quantizers by @laurilaatu in https://github.com/fastmachinelearning/hls4ml/pull/1195
  • put code_gen.h in custom namespace by @calad0i in https://github.com/fastmachinelearning/hls4ml/pull/1104
  • Fix typo in pyproject.toml by @JanFSchulte in https://github.com/fastmachinelearning/hls4ml/pull/1204
  • Adjust model output if last node is removed by @JanFSchulte in https://github.com/fastmachinelearning/hls4ml/pull/1205
  • remove old variables when moving of scales by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/1206
  • Initial values for the hidden/cell state for LSTM and GRU models in Pytorch by @JanFSchulte in https://github.com/fastmachinelearning/hls4ml/pull/1120
  • Depthwise 1D and 2D Resource strategy for io_stream by @steltze in https://github.com/fastmachinelearning/hls4ml/pull/1079
  • make test_activations less sensitive to random seed values by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/1211
  • FIFO depth optimizer for Vitis backend by @steltze in https://github.com/fastmachinelearning/hls4ml/pull/1037
  • update sympy version by @marco66colombo in https://github.com/fastmachinelearning/hls4ml/pull/1214
  • Add precisoin bits to recurrent pytorch pytest by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/1215
  • trigger GitLab CI for debugging new CI image by @marco66colombo in https://github.com/fastmachinelearning/hls4ml/pull/1200
  • [pre-commit.ci] pre-commit autoupdate by @pre-commit-ci in https://github.com/fastmachinelearning/hls4ml/pull/1213
  • remove test skip since problem fixed in qonnx by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/1152
  • Unify handling of remove-node when ouput is in outputs by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/1226
  • Remove dependence of profiling tools on torch by @JanFSchulte in https://github.com/fastmachinelearning/hls4ml/pull/1233

New Contributors

  • @jicampos made their first contribution in https://github.com/fastmachinelearning/hls4ml/pull/1156
  • @steltze made their first contribution in https://github.com/fastmachinelearning/hls4ml/pull/1079
  • @marco66colombo made their first contribution in https://github.com/fastmachinelearning/hls4ml/pull/1214

Full Changelog: https://github.com/fastmachinelearning/hls4ml/compare/v1.0.0...v1.1.0

- Python
Published by JanFSchulte 11 months ago

hls4ml - foxglove 1.0.0

What's Changed

hls4ml v1.0.0 "foxglove" introduces several significant improvements:

  • A new QONNX frontend by @jmitrevs introduced in https://github.com/fastmachinelearning/hls4ml/pull/979
  • The ability for hls4ml to automatically infer the precision of data types by @vloncar introduced in https://github.com/fastmachinelearning/hls4ml/pull/855
  • The addition of an experimental backend for Intel oneAPI by @jmitrevs introduced in https://github.com/fastmachinelearning/hls4ml/pull/955
  • The addition of a backend for Siemens Catapult by @dgburnette in https://github.com/fastmachinelearning/hls4ml/pull/956
  • Added support for HGQ proxy models by @calad0i in https://github.com/fastmachinelearning/hls4ml/pull/914
  • An API for hardware-aware optimization by @bo3z in https://github.com/fastmachinelearning/hls4ml/pull/768 and https://github.com/fastmachinelearning/hls4ml/pull/809

The full list of other improvements and fixes is: * [pre-commit.ci] pre-commit autoupdate by @pre-commit-ci in https://github.com/fastmachinelearning/hls4ml/pull/949 * [pre-commit.ci] pre-commit autoupdate by @pre-commit-ci in https://github.com/fastmachinelearning/hls4ml/pull/953 * hls4ml Optimization API [Part 1] by @bo3z in https://github.com/fastmachinelearning/hls4ml/pull/768 * QKeras support for RNN layers by @laurilaatu in https://github.com/fastmachinelearning/hls4ml/pull/856 * [pre-commit.ci] pre-commit autoupdate by @pre-commit-ci in https://github.com/fastmachinelearning/hls4ml/pull/962 * Try to fix sphinx problem by restricting tensorflow-model-optimization by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/967 * Bump pre-commit/action from 3.0.0 to 3.0.1 by @dependabot in https://github.com/fastmachinelearning/hls4ml/pull/968 * Change fractional (and others) to be a property, move quantizers by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/964 * [pre-commit.ci] pre-commit autoupdate by @pre-commit-ci in https://github.com/fastmachinelearning/hls4ml/pull/969 * [pre-commit.ci] pre-commit autoupdate by @pre-commit-ci in https://github.com/fastmachinelearning/hls4ml/pull/971 * vitis backend tarball fix by @calad0i in https://github.com/fastmachinelearning/hls4ml/pull/972 * remove special vitis version of nnetdenseresource.h by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/975 * Allow Vitis synthesis tests by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/927 * Fix cleanup of synthesis tests (leftover from 927) by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/989 * Fix sphinx by pinning tensorflow<=2.15 by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/992 * [pre-commit.ci] pre-commit autoupdate by @pre-commit-ci in https://github.com/fastmachinelearning/hls4ml/pull/984 * add clock uncertainty configuration option by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/870 * Stage initial set of changes for the Catapult backend by @dgburnette in https://github.com/fastmachinelearning/hls4ml/pull/956 * [pre-commit.ci] pre-commit autoupdate by @pre-commit-ci in https://github.com/fastmachinelearning/hls4ml/pull/999 * fix unwanted tested file change in #956 by @calad0i in https://github.com/fastmachinelearning/hls4ml/pull/1000 * Fix SR backend synth missing variables by @bo3z in https://github.com/fastmachinelearning/hls4ml/pull/993 * Upsampling support for PyTorch models by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/977 * Split fpgatypes into separate files by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/998 * Support negativeslope in quantizedrelu by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/987 * Group more tests per YAML to reduce the number of envs created by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/996 * Automatic precision inference by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/855 * Remove unnecessary transposes related to conversion to channelslast format by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/976 * Update pytest docker image to 0.5.4 by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/1005 * Fix pre-commit warning and change '.h5' to '.keras' for written output by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/1006 * Fix extension test for Keras v3 by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/1009 * [pre-commit.ci] pre-commit autoupdate by @pre-commit-ci in https://github.com/fastmachinelearning/hls4ml/pull/1007 * updated pytest docker image by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/1017 * SepConv1d/2d for ioparallel with Latency strategy by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/1012 * [pre-commit.ci] pre-commit autoupdate by @pre-commit-ci in https://github.com/fastmachinelearning/hls4ml/pull/1021 * [pre-commit.ci] pre-commit autoupdate by @pre-commit-ci in https://github.com/fastmachinelearning/hls4ml/pull/1023 * Latency Pooling Header Updates by @calad0i in https://github.com/fastmachinelearning/hls4ml/pull/973 * Make im2col default option for quartus by @calad0i in https://github.com/fastmachinelearning/hls4ml/pull/1010 * add protection for when kernelquantizer is None by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/997 * prevent test directory overwrites for activation by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/1031 * Update Jenkinsfile to use new Docker image and Python 3.10 environment by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/1033 * clean-up test ci yaml generater by @calad0i in https://github.com/fastmachinelearning/hls4ml/pull/1036 * Add View to layer name map for pytorch parser by @JanFSchulte in https://github.com/fastmachinelearning/hls4ml/pull/1039 * Add RNN support for Pytorch by @JanFSchulte in https://github.com/fastmachinelearning/hls4ml/pull/850 * Add Vitis to pytorch API tests by @JanFSchulte in https://github.com/fastmachinelearning/hls4ml/pull/1040 * clean up mult-dimensional dense by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/1042 * Add namespaces and optional writer config by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/986 * [pre-commit.ci] pre-commit autoupdate by @pre-commit-ci in https://github.com/fastmachinelearning/hls4ml/pull/1044 * Add support for HGQ proxy model by @calad0i in https://github.com/fastmachinelearning/hls4ml/pull/914 * Bug Fix for Operand Shape Mismatch in BatchNorm Fusion (PyTorch) by @sei-rquartiano in https://github.com/fastmachinelearning/hls4ml/pull/1045 * remove precision settings that make pytest for batchnorm in pytorch fail by @JanFSchulte in https://github.com/fastmachinelearning/hls4ml/pull/1053 * [pre-commit.ci] pre-commit autoupdate by @pre-commit-ci in https://github.com/fastmachinelearning/hls4ml/pull/1047 * rm slow mnist training in test by @calad0i in https://github.com/fastmachinelearning/hls4ml/pull/1018 * Add an optimizer to replace SeparableConv by Depthwise + Conv (pointwise) by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/1022 * Add functionality to use granularity option also for pytorch models by @JanFSchulte in https://github.com/fastmachinelearning/hls4ml/pull/1051 * Update pooling logic for Vivado, Vitis, and Catapult backends by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/1056 * remove padding attribute by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/1061 * Run long-running pytests out of the batch by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/1062 * Fix tanh activiation in pytorch parser by @JanFSchulte in https://github.com/fastmachinelearning/hls4ml/pull/1055 * make auto the default for layer config by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/1016 * remove checks on 'padding' that were missed in previous PR by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/1064 * Remove extras flow by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/1067 * Expose alpha and theta type for parametrized activations by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/1069 * Raise exception on compile errors by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/1068 * update qkeras in Jenkinsfile by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/1072 * [pre-commit.ci] pre-commit autoupdate by @pre-commit-ci in https://github.com/fastmachinelearning/hls4ml/pull/1075 * hls4ml Optimization API [Part 2] by @bo3z in https://github.com/fastmachinelearning/hls4ml/pull/809 * Hardcore weight txt path by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/1089 * quote the ${WEIGHTDIR} to handle special characters by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/1091 * Beginnings of the oneAPI backend by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/955 * update keras activation parsing, especially leaky relu by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/1085 * Fix softmax parsing in pytorch and add test by @JanFSchulte in https://github.com/fastmachinelearning/hls4ml/pull/1086 * [pre-commit.ci] pre-commit autoupdate by @pre-commit-ci in https://github.com/fastmachinelearning/hls4ml/pull/1098 * Change indexing in filling result for ioparallel convolutions, Vitis by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/1102 * Update QONNX parsing for 1.0 by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/979 * remove incorrect input from Constant nodes by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/1119 * add maxprecision to onnx parser by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/1113 * Add RF to config templates for "Merge" layers by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/1121 * Add doc for HGQ by @calad0i in https://github.com/fastmachinelearning/hls4ml/pull/1117 * Multi output fix 2 by @calad0i in https://github.com/fastmachinelearning/hls4ml/pull/1103 * Make auto default precision for pytorch parser by @JanFSchulte in https://github.com/fastmachinelearning/hls4ml/pull/1112 * remove incorrect setting of resultt by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/1130 * Fix problem with scale being a multidimensional array. by @jurevreca12 in https://github.com/fastmachinelearning/hls4ml/pull/1132 * Added support for QONNX Resize node ingestion and tested with tiny UNet model by @nghielme in https://github.com/fastmachinelearning/hls4ml/pull/1122 * Update install_requires for 1.0.0 by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/1136 * Pointwise Conv1D with code generation for "Latency" strategy (update of #811) by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/881 * Introduce optional description to layer attributes by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/1127 * Qonnx warnings by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/1142 * Fixes to parsing of pytorch models when using torch functionals by @JanFSchulte in https://github.com/fastmachinelearning/hls4ml/pull/1143 * Update README.md for v1.0.0 by @bo3z in https://github.com/fastmachinelearning/hls4ml/pull/1100 * Temporary workaround for QKeras installation by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/1145

New Contributors

  • @laurilaatu made their first contribution in https://github.com/fastmachinelearning/hls4ml/pull/856
  • @dgburnette made their first contribution in https://github.com/fastmachinelearning/hls4ml/pull/956
  • @sei-rquartiano made their first contribution in https://github.com/fastmachinelearning/hls4ml/pull/1045
  • @jurevreca12 made their first contribution in https://github.com/fastmachinelearning/hls4ml/pull/1132

Full Changelog: https://github.com/fastmachinelearning/hls4ml/compare/v0.8.1...v1.0.0

- Python
Published by JanFSchulte about 1 year ago

hls4ml - edelweiss 0.8.1

What's Changed

  • Fix for #905 by @calad0i in https://github.com/fastmachinelearning/hls4ml/pull/906
  • [pre-commit.ci] pre-commit autoupdate by @pre-commit-ci in https://github.com/fastmachinelearning/hls4ml/pull/921
  • Fix logos in README.md by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/930
  • Fix writer precision when fp bits >= 14 by @calad0i in https://github.com/fastmachinelearning/hls4ml/pull/909
  • Let repack_stream optimizer inheirt original precision by @calad0i in https://github.com/fastmachinelearning/hls4ml/pull/907
  • Update A3D3 grant no. by @schsu in https://github.com/fastmachinelearning/hls4ml/pull/941
  • Add precision inherition for when generating stream clone by @calad0i in https://github.com/fastmachinelearning/hls4ml/pull/911
  • [pre-commit.ci] pre-commit autoupdate by @pre-commit-ci in https://github.com/fastmachinelearning/hls4ml/pull/942
  • Quartus multi out with stream fix by @calad0i in https://github.com/fastmachinelearning/hls4ml/pull/908
  • Fix profiling for Keras LSTM layers. by @Landay7 in https://github.com/fastmachinelearning/hls4ml/pull/940
  • Fix for multiple inputs that may get out of order by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/937
  • [pre-commit.ci] pre-commit autoupdate by @pre-commit-ci in https://github.com/fastmachinelearning/hls4ml/pull/944
  • Bump actions/upload-artifact from 3 to 4 by @dependabot in https://github.com/fastmachinelearning/hls4ml/pull/943
  • better repalce_node fn by @calad0i in https://github.com/fastmachinelearning/hls4ml/pull/934
  • bump to 0.8.1 by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/945

New Contributors

  • @schsu made their first contribution in https://github.com/fastmachinelearning/hls4ml/pull/941
  • @Landay7 made their first contribution in https://github.com/fastmachinelearning/hls4ml/pull/940

Full Changelog: https://github.com/fastmachinelearning/hls4ml/compare/v0.8.0...v0.8.1

- Python
Published by jmitrevs about 2 years ago

hls4ml - edelweiss 0.8.0

What's Changed

  • Decouple pipeline style from strategy by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/781
  • Don't use reader in ModelGraph and layers by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/770
  • Remove tftohls by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/795
  • [pre-commit.ci] pre-commit autoupdate by @pre-commit-ci in https://github.com/fastmachinelearning/hls4ml/pull/796
  • Fix parsing of QConv2DBatchnorm weights by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/802
  • [pre-commit.ci] pre-commit autoupdate by @pre-commit-ci in https://github.com/fastmachinelearning/hls4ml/pull/801
  • Discussion - Inlined Conv slows down latency significantly (up to x15 - x20) by @bo3z in https://github.com/fastmachinelearning/hls4ml/pull/800
  • [pre-commit.ci] pre-commit autoupdate by @pre-commit-ci in https://github.com/fastmachinelearning/hls4ml/pull/807
  • Fix over-allocation of bits for quantised po2 by @bo3z in https://github.com/fastmachinelearning/hls4ml/pull/806
  • Propagate zeros from Conv layers to multiplication config by @bo3z in https://github.com/fastmachinelearning/hls4ml/pull/797
  • Fix Vitis Conv1D/2D latency strategy by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/815
  • Improved parsing of pytorch models using torch.FX - Clean by @JanFSchulte in https://github.com/fastmachinelearning/hls4ml/pull/799
  • [pre-commit.ci] pre-commit autoupdate by @pre-commit-ci in https://github.com/fastmachinelearning/hls4ml/pull/816
  • Support for parsing nested models by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/794
  • Fix loading weights in n-dim dense -> 1x1 conv by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/821
  • [pre-commit.ci] pre-commit autoupdate by @pre-commit-ci in https://github.com/fastmachinelearning/hls4ml/pull/828
  • Fix loading weights in GarNetStacked and GarNet internal array precisions by @joshlerner in https://github.com/fastmachinelearning/hls4ml/pull/827
  • [pre-commit.ci] pre-commit autoupdate by @pre-commit-ci in https://github.com/fastmachinelearning/hls4ml/pull/830
  • Fix profiling for GRU/LSTM by @drankincms in https://github.com/fastmachinelearning/hls4ml/pull/833
  • [pre-commit.ci] pre-commit autoupdate by @pre-commit-ci in https://github.com/fastmachinelearning/hls4ml/pull/835
  • remove obsolete and unused docker directory by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/836
  • [pre-commit.ci] pre-commit autoupdate by @pre-commit-ci in https://github.com/fastmachinelearning/hls4ml/pull/842
  • Remove obsolete parameter mapping between pytorch and keras by @JanFSchulte in https://github.com/fastmachinelearning/hls4ml/pull/847
  • Make binary CNN match between Keras and hls4ml by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/804
  • No longer make ExponentPrecisionType and XnorPrecisionType inherit from IntegerPrecisionType by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/845
  • Add support for flattening to the pytorch parser by @JanFSchulte in https://github.com/fastmachinelearning/hls4ml/pull/852
  • Add option to configure IP version by @AdrianAlan in https://github.com/fastmachinelearning/hls4ml/pull/851
  • Bug fix for named nn.Sequential in pytorch parser by @JanFSchulte in https://github.com/fastmachinelearning/hls4ml/pull/848
  • Add QDepthwiseConv2D, DepthwiseConv2D, DepthwiseConv1D support by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/834
  • Symbolic expressions in hls4ml by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/660
  • Update dependencies, add testing extras by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/837
  • Bump actions/checkout from 3 to 4 by @dependabot in https://github.com/fastmachinelearning/hls4ml/pull/866
  • [pre-commit.ci] pre-commit autoupdate by @pre-commit-ci in https://github.com/fastmachinelearning/hls4ml/pull/869
  • try to use new runners for gitlab CI by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/879
  • [pre-commit.ci] pre-commit autoupdate by @pre-commit-ci in https://github.com/fastmachinelearning/hls4ml/pull/880
  • Fix weight precision format string by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/877
  • add acknowledgments by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/862
  • Support for quantized SeparableConv1D/2D by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/861
  • Speed up Keras profiling by @AdrianAlan in https://github.com/fastmachinelearning/hls4ml/pull/863
  • [pre-commit.ci] pre-commit autoupdate by @pre-commit-ci in https://github.com/fastmachinelearning/hls4ml/pull/882
  • Fix profiling SeparableConv1D and SeparableConv2D by @qberthet in https://github.com/fastmachinelearning/hls4ml/pull/891
  • Add support for filt_height==1 for streaming quartus conv2d by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/886
  • Fix config structure name in pragma for SeparableConv1D by @qberthet in https://github.com/fastmachinelearning/hls4ml/pull/884
  • [pre-commit.ci] pre-commit autoupdate by @pre-commit-ci in https://github.com/fastmachinelearning/hls4ml/pull/895
  • Fix bit overflow with softmax by @calad0i in https://github.com/fastmachinelearning/hls4ml/pull/887
  • bump 0.8.0rc1 by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/915
  • [pre-commit.ci] pre-commit autoupdate by @pre-commit-ci in https://github.com/fastmachinelearning/hls4ml/pull/902
  • Add funding acknowledgements by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/918
  • Fix fetching models from example-models repo by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/919
  • add blank line to make rst format correct by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/923
  • Update default FPGA part number from KU115 to VU13P by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/924
  • update to 0.8.0 by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/925

New Contributors

  • @pre-commit-ci made their first contribution in https://github.com/fastmachinelearning/hls4ml/pull/796
  • @joshlerner made their first contribution in https://github.com/fastmachinelearning/hls4ml/pull/827
  • @qberthet made their first contribution in https://github.com/fastmachinelearning/hls4ml/pull/891

Full Changelog: https://github.com/fastmachinelearning/hls4ml/compare/v0.7.1...v0.8.0

- Python
Published by jmitrevs over 2 years ago

hls4ml - edelweiss 0.8.0rc1

What's Changed

  • Decouple pipeline style from strategy by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/781
  • Don't use reader in ModelGraph and layers by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/770
  • Remove tftohls by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/795
  • [pre-commit.ci] pre-commit autoupdate by @pre-commit-ci in https://github.com/fastmachinelearning/hls4ml/pull/796
  • Fix parsing of QConv2DBatchnorm weights by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/802
  • [pre-commit.ci] pre-commit autoupdate by @pre-commit-ci in https://github.com/fastmachinelearning/hls4ml/pull/801
  • Discussion - Inlined Conv slows down latency significantly (up to x15 - x20) by @bo3z in https://github.com/fastmachinelearning/hls4ml/pull/800
  • [pre-commit.ci] pre-commit autoupdate by @pre-commit-ci in https://github.com/fastmachinelearning/hls4ml/pull/807
  • Fix over-allocation of bits for quantised po2 by @bo3z in https://github.com/fastmachinelearning/hls4ml/pull/806
  • Propagate zeros from Conv layers to multiplication config by @bo3z in https://github.com/fastmachinelearning/hls4ml/pull/797
  • Fix Vitis Conv1D/2D latency strategy by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/815
  • Improved parsing of pytorch models using torch.FX - Clean by @JanFSchulte in https://github.com/fastmachinelearning/hls4ml/pull/799
  • [pre-commit.ci] pre-commit autoupdate by @pre-commit-ci in https://github.com/fastmachinelearning/hls4ml/pull/816
  • Support for parsing nested models by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/794
  • Fix loading weights in n-dim dense -> 1x1 conv by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/821
  • [pre-commit.ci] pre-commit autoupdate by @pre-commit-ci in https://github.com/fastmachinelearning/hls4ml/pull/828
  • Fix loading weights in GarNetStacked and GarNet internal array precisions by @joshlerner in https://github.com/fastmachinelearning/hls4ml/pull/827
  • [pre-commit.ci] pre-commit autoupdate by @pre-commit-ci in https://github.com/fastmachinelearning/hls4ml/pull/830
  • Fix profiling for GRU/LSTM by @drankincms in https://github.com/fastmachinelearning/hls4ml/pull/833
  • [pre-commit.ci] pre-commit autoupdate by @pre-commit-ci in https://github.com/fastmachinelearning/hls4ml/pull/835
  • remove obsolete and unused docker directory by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/836
  • [pre-commit.ci] pre-commit autoupdate by @pre-commit-ci in https://github.com/fastmachinelearning/hls4ml/pull/842
  • Remove obsolete parameter mapping between pytorch and keras by @JanFSchulte in https://github.com/fastmachinelearning/hls4ml/pull/847
  • Make binary CNN match between Keras and hls4ml by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/804
  • No longer make ExponentPrecisionType and XnorPrecisionType inherit from IntegerPrecisionType by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/845
  • Add support for flattening to the pytorch parser by @JanFSchulte in https://github.com/fastmachinelearning/hls4ml/pull/852
  • Add option to configure IP version by @AdrianAlan in https://github.com/fastmachinelearning/hls4ml/pull/851
  • Bug fix for named nn.Sequential in pytorch parser by @JanFSchulte in https://github.com/fastmachinelearning/hls4ml/pull/848
  • Add QDepthwiseConv2D, DepthwiseConv2D, DepthwiseConv1D support by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/834
  • Symbolic expressions in hls4ml by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/660
  • Update dependencies, add testing extras by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/837
  • Bump actions/checkout from 3 to 4 by @dependabot in https://github.com/fastmachinelearning/hls4ml/pull/866
  • [pre-commit.ci] pre-commit autoupdate by @pre-commit-ci in https://github.com/fastmachinelearning/hls4ml/pull/869
  • try to use new runners for gitlab CI by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/879
  • [pre-commit.ci] pre-commit autoupdate by @pre-commit-ci in https://github.com/fastmachinelearning/hls4ml/pull/880
  • Fix weight precision format string by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/877
  • add acknowledgments by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/862
  • Support for quantized SeparableConv1D/2D by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/861
  • Speed up Keras profiling by @AdrianAlan in https://github.com/fastmachinelearning/hls4ml/pull/863
  • [pre-commit.ci] pre-commit autoupdate by @pre-commit-ci in https://github.com/fastmachinelearning/hls4ml/pull/882
  • Fix profiling SeparableConv1D and SeparableConv2D by @qberthet in https://github.com/fastmachinelearning/hls4ml/pull/891
  • Add support for filt_height==1 for streaming quartus conv2d by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/886
  • Fix config structure name in pragma for SeparableConv1D by @qberthet in https://github.com/fastmachinelearning/hls4ml/pull/884
  • [pre-commit.ci] pre-commit autoupdate by @pre-commit-ci in https://github.com/fastmachinelearning/hls4ml/pull/895
  • Fix bit overflow with softmax by @calad0i in https://github.com/fastmachinelearning/hls4ml/pull/887
  • bump 0.8.0rc1 by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/915

New Contributors

  • @pre-commit-ci made their first contribution in https://github.com/fastmachinelearning/hls4ml/pull/796
  • @joshlerner made their first contribution in https://github.com/fastmachinelearning/hls4ml/pull/827
  • @qberthet made their first contribution in https://github.com/fastmachinelearning/hls4ml/pull/891

Full Changelog: https://github.com/fastmachinelearning/hls4ml/compare/v0.7.1...v0.8.0rc1

- Python
Published by jmitrevs over 2 years ago

hls4ml - delphinium 0.7.1

What's Changed

  • bump version to v0.7.0 by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/778
  • Fix for 2D conv layers in the special case of io_parallel with full parallelization by @drankincms in https://github.com/fastmachinelearning/hls4ml/pull/760
  • Fix RNN layers when strategy=resource by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/780
  • Update Jenkins test environment to avoid dependency hell by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/786
  • Explicitly set strategy for pointwise conv by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/785
  • Minor docs fixes for 0.7.1 by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/788
  • bump 0.7.1 by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/791

Full Changelog: https://github.com/fastmachinelearning/hls4ml/compare/v0.7.0...v0.7.1

- Python
Published by jmitrevs almost 3 years ago

hls4ml - delphinium

What's Changed

  • fix conv1d io_parallel resource by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/403
  • Speed up CI tests by @thesps in https://github.com/fastmachinelearning/hls4ml/pull/407
  • Fix GlobalPooling1D Layers by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/399
  • Fix batched multiple inputs by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/414
  • Fixed 'qkerasmnistdense' example build problem #423 by @siorpaes in https://github.com/fastmachinelearning/hls4ml/pull/424
  • Update for pyyaml 6.0 by @thesps in https://github.com/fastmachinelearning/hls4ml/pull/435
  • axi_stream_driver update by @nicologhielmetti in https://github.com/fastmachinelearning/hls4ml/pull/420
  • Reshape fixes: don't repack stream for flatten; remove final reshape by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/443
  • Fix Conv2D with io_type = io_parallel & Strategy: Resource by @thesps in https://github.com/fastmachinelearning/hls4ml/pull/448
  • Support applying Softmax over multidimensional tensors by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/384
  • Disable some unsupported layers by @thesps in https://github.com/fastmachinelearning/hls4ml/pull/447
  • Fixes: quantized_relu & unsigned profiling part II by @thesps in https://github.com/fastmachinelearning/hls4ml/pull/441
  • GarNet and GarNetStack in config.py by @yiiyama in https://github.com/fastmachinelearning/hls4ml/pull/344
  • support ZeroPadding layers by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/480
  • New backend development framework by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/395
  • Register ApplyAlpha layer templates by @thesps in https://github.com/fastmachinelearning/hls4ml/pull/499
  • Parsing extended by @nicologhielmetti in https://github.com/fastmachinelearning/hls4ml/pull/501
  • Remove intermediate casting in product by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/490
  • Add QKeras as a package dependency by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/511
  • Copy flows from config by @thesps in https://github.com/fastmachinelearning/hls4ml/pull/510
  • VivadoAccelerator backend updates by @thesps in https://github.com/fastmachinelearning/hls4ml/pull/508
  • Optimized look-up table by @nemerchiedde in https://github.com/fastmachinelearning/hls4ml/pull/527
  • Upsampling2D test case by @ChiRuiChen in https://github.com/fastmachinelearning/hls4ml/pull/520
  • Support UpSampling1D by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/475
  • RNN support (part 1) by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/521
  • Quartus Custom Matrix Multiplication & Quantization by @bo3z in https://github.com/fastmachinelearning/hls4ml/pull/523
  • Vivado-equivalent implementation of Softmax on Quartus by @bo3z in https://github.com/fastmachinelearning/hls4ml/pull/540
  • Ensure 2 bits for scale in po2 quantizers by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/531
  • Link update by @bkmgit in https://github.com/fastmachinelearning/hls4ml/pull/519
  • Fix removal of nodes ingested by multiple downstream nodes by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/544
  • Enable SeparableConv2d by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/547
  • Extension API by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/528
  • change string ReuseFactor to int by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/416
  • Make the size of bn scale and bias what they really are by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/532
  • Raise runtime error when a layer is named input by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/482
  • fix insertion before a node with multiple inputs + support additional broadcasting by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/551
  • Pointwise conv1d/2d resource by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/471
  • Quartus Embedding Layer by @bo3z in https://github.com/fastmachinelearning/hls4ml/pull/548
  • Fix for QActivations passed as an argument by @AdrianAlan in https://github.com/fastmachinelearning/hls4ml/pull/553
  • Don't override precision directly in the QKeras optimizer by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/567
  • Remove the in/out size from top function by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/559
  • Transpose2d, Concatenate2d, and up to 3 Clones for io_stream by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/402
  • Remove ioserial as iostream and add some more info in docs. by @Duchstf in https://github.com/fastmachinelearning/hls4ml/pull/334
  • Update docs for v0.6.0 by @thesps in https://github.com/fastmachinelearning/hls4ml/pull/453
  • Use correct number of args for multiple outputs by @apfusco in https://github.com/fastmachinelearning/hls4ml/pull/487
  • Fixed a few typos in the documentation by @pitmonticone in https://github.com/fastmachinelearning/hls4ml/pull/467
  • returning integer from computen_samples by @JochiSt in https://github.com/fastmachinelearning/hls4ml/pull/537
  • Providing support for Alveo boards by @selwyn96 in https://github.com/fastmachinelearning/hls4ml/pull/552
  • Make layer names case sensitive in config. by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/577
  • Add issue and PR templates by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/582
  • Vivado Backend GRU/LSTM support by @drankincms in https://github.com/fastmachinelearning/hls4ml/pull/560
  • Update CI template syntax by @thesps in https://github.com/fastmachinelearning/hls4ml/pull/593
  • Update flow dependencies by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/588
  • Fix parsing of ZeroPadding layers by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/595
  • remove cppname by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/562
  • Remove email helpline from the docs by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/601
  • Fixes for GRU/LSTM in Vivado backend by @drankincms in https://github.com/fastmachinelearning/hls4ml/pull/598
  • Remove io_serial by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/609
  • Fix test_graph by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/611
  • Override parent backend optimizer passes with derived backend passes by @thesps in https://github.com/fastmachinelearning/hls4ml/pull/597
  • Enforce function pipelining when using io_parallel with Resource strategy by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/605
  • FIFO depth optimization by @nicologhielmetti in https://github.com/fastmachinelearning/hls4ml/pull/509
  • Add tracing support for the quartus backend by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/583
  • Quartus streaming support for Activations, Dense & Batch Normalization by @bo3z in https://github.com/fastmachinelearning/hls4ml/pull/557
  • QConv alpha != 1 bug fix by @bo3z in https://github.com/fastmachinelearning/hls4ml/pull/612
  • Quartus Stream Embedding by @bo3z in https://github.com/fastmachinelearning/hls4ml/pull/625
  • change master to main by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/602
  • Edit order of the optimizers in the flow so that BramFactor is followed by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/621
  • Softmax LUT Optimization by @bo3z in https://github.com/fastmachinelearning/hls4ml/pull/570
  • Quartus Synthesis Flow Improvement by @bo3z in https://github.com/fastmachinelearning/hls4ml/pull/618
  • Quartus Extensions by @bo3z in https://github.com/fastmachinelearning/hls4ml/pull/628
  • Quartus GRU by @bo3z in https://github.com/fastmachinelearning/hls4ml/pull/596
  • Quartus Merge layers by @bo3z in https://github.com/fastmachinelearning/hls4ml/pull/634
  • fix nondefault project name handling by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/626
  • Fix parsing of logic synthesis reports by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/639
  • Fix conv1d stream implementation hls directives by @Jonathan-Shoemaker in https://github.com/fastmachinelearning/hls4ml/pull/635
  • Implementation and optimizations linked to Simple-RNN and LSTM for qu… by @nemerchiedde in https://github.com/fastmachinelearning/hls4ml/pull/575
  • Softsign optimization by @nemerchiedde in https://github.com/fastmachinelearning/hls4ml/pull/585
  • Parallel CNNs, Pooling & Image Layers for Quartus Backend by @bo3z in https://github.com/fastmachinelearning/hls4ml/pull/561
  • Quartus Streaming Softsign (PR #585 contd.) by @bo3z in https://github.com/fastmachinelearning/hls4ml/pull/655
  • Remove final reshapes even for Quartus by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/661
  • Unrolled CNN implementation by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/600
  • the strategy was not propagated in the pytest by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/663
  • Fix keras model loading issue with loading model with KerasH5 by @calad0i in https://github.com/fastmachinelearning/hls4ml/pull/664
  • append applied_flows container before filling instead of after by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/641
  • set version using setuptools_scm by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/479
  • Argmax Softmax by @bo3z in https://github.com/fastmachinelearning/hls4ml/pull/627
  • Fix version extraction in Sphinx config by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/669
  • Add requested citations to README by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/615
  • skip BatchNorm fusion when input/output is used multiple times by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/481
  • Use wider accum_t for (average) pooling by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/681
  • Quartus Streaming Conv, Pooling & Image layers by @bo3z in https://github.com/fastmachinelearning/hls4ml/pull/656
  • Create branch on PR by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/636
  • Delete example-prjs directory by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/682
  • Adiabatically turn on pre-commit by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/678
  • Add causal padding by @cgutsche in https://github.com/fastmachinelearning/hls4ml/pull/688
  • Update pre-commit GitHub Action by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/689
  • New configfromkeras_model by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/690
  • remove obsolete np.int and np.float by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/703
  • Update p-clang-format to work on mac by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/704
  • Fix function call in Alveo tcl script by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/694
  • add readme for contrib by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/706
  • WIP Add custom KL loss layer HLS implementation by @katyagovorkova in https://github.com/fastmachinelearning/hls4ml/pull/606
  • Fix incorrectly linted build() command by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/709
  • For encoded convolution, add check for when minwidth would have been larger than inwidth by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/610
  • fifodepthoptimization flow require ip, not writer, before running by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/642
  • update isort to fix pre-commit by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/719
  • Fixed sign parsing for acfixed and acint by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/727
  • Correctly expand dims of pointwise layer by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/715
  • Support keepdims in GlobalPooling layers by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/716
  • Register layer attributes in VivadoAccelerator backend by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/724
  • Add quantized sigmoid, fix quantized tanh for QKeras by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/569
  • printvivadoreport function for nicer reports by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/730
  • Quartus bram factor by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/700
  • Fix inplace variables by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/714
  • Fix for cloned stream that is subsequently flattened by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/708
  • Vitis HLS backend by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/629
  • Update documentation for v0.7.0 release by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/710
  • Fix release notes + version in docs by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/742
  • Fix precommits by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/741
  • mv dependabot.yml by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/743
  • Bump actions/setup-python from 2 to 4 by @dependabot in https://github.com/fastmachinelearning/hls4ml/pull/748
  • fix Vitis pragmas messed up by pre-commit by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/751
  • Additional cleanup of the codebase by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/750
  • Fix for BatchNormalization layers with center=False or scale=False by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/754
  • Remove references to GPL since we now use a different license by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/761
  • Fix pooling layers when padding is applied from the left/top by @JanFSchulte in https://github.com/fastmachinelearning/hls4ml/pull/757
  • Further update documentation for 0.7.0 by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/744
  • Update pypi-publish.yml by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/763
  • Fix pypi version by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/766
  • add a default weight_size by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/772
  • CNNs with binary inputs and weights need fixes by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/749
  • Minor documentation updates by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/774

New Contributors

  • @siorpaes made their first contribution in https://github.com/fastmachinelearning/hls4ml/pull/424
  • @nemerchiedde made their first contribution in https://github.com/fastmachinelearning/hls4ml/pull/527
  • @ChiRuiChen made their first contribution in https://github.com/fastmachinelearning/hls4ml/pull/520
  • @bo3z made their first contribution in https://github.com/fastmachinelearning/hls4ml/pull/523
  • @bkmgit made their first contribution in https://github.com/fastmachinelearning/hls4ml/pull/519
  • @apfusco made their first contribution in https://github.com/fastmachinelearning/hls4ml/pull/487
  • @pitmonticone made their first contribution in https://github.com/fastmachinelearning/hls4ml/pull/467
  • @JochiSt made their first contribution in https://github.com/fastmachinelearning/hls4ml/pull/537
  • @selwyn96 made their first contribution in https://github.com/fastmachinelearning/hls4ml/pull/552
  • @Jonathan-Shoemaker made their first contribution in https://github.com/fastmachinelearning/hls4ml/pull/635
  • @calad0i made their first contribution in https://github.com/fastmachinelearning/hls4ml/pull/664
  • @cgutsche made their first contribution in https://github.com/fastmachinelearning/hls4ml/pull/688
  • @dependabot made their first contribution in https://github.com/fastmachinelearning/hls4ml/pull/748
  • @JanFSchulte made their first contribution in https://github.com/fastmachinelearning/hls4ml/pull/757

Full Changelog: https://github.com/fastmachinelearning/hls4ml/compare/v0.6.0...v0.7.0

- Python
Published by jmitrevs almost 3 years ago

hls4ml - delphinium rc1

What's Changed

  • fix conv1d io_parallel resource by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/403
  • Speed up CI tests by @thesps in https://github.com/fastmachinelearning/hls4ml/pull/407
  • Fix GlobalPooling1D Layers by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/399
  • Fix batched multiple inputs by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/414
  • Fixed 'qkerasmnistdense' example build problem #423 by @siorpaes in https://github.com/fastmachinelearning/hls4ml/pull/424
  • Update for pyyaml 6.0 by @thesps in https://github.com/fastmachinelearning/hls4ml/pull/435
  • axi_stream_driver update by @nicologhielmetti in https://github.com/fastmachinelearning/hls4ml/pull/420
  • Reshape fixes: don't repack stream for flatten; remove final reshape by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/443
  • Fix Conv2D with io_type = io_parallel & Strategy: Resource by @thesps in https://github.com/fastmachinelearning/hls4ml/pull/448
  • Support applying Softmax over multidimensional tensors by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/384
  • Disable some unsupported layers by @thesps in https://github.com/fastmachinelearning/hls4ml/pull/447
  • Fixes: quantized_relu & unsigned profiling part II by @thesps in https://github.com/fastmachinelearning/hls4ml/pull/441
  • GarNet and GarNetStack in config.py by @yiiyama in https://github.com/fastmachinelearning/hls4ml/pull/344
  • support ZeroPadding layers by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/480
  • New backend development framework by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/395
  • Register ApplyAlpha layer templates by @thesps in https://github.com/fastmachinelearning/hls4ml/pull/499
  • Parsing extended by @nicologhielmetti in https://github.com/fastmachinelearning/hls4ml/pull/501
  • Remove intermediate casting in product by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/490
  • Add QKeras as a package dependency by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/511
  • Copy flows from config by @thesps in https://github.com/fastmachinelearning/hls4ml/pull/510
  • VivadoAccelerator backend updates by @thesps in https://github.com/fastmachinelearning/hls4ml/pull/508
  • Optimized look-up table by @nemerchiedde in https://github.com/fastmachinelearning/hls4ml/pull/527
  • Upsampling2D test case by @ChiRuiChen in https://github.com/fastmachinelearning/hls4ml/pull/520
  • Support UpSampling1D by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/475
  • RNN support (part 1) by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/521
  • Quartus Custom Matrix Multiplication & Quantization by @bo3z in https://github.com/fastmachinelearning/hls4ml/pull/523
  • Vivado-equivalent implementation of Softmax on Quartus by @bo3z in https://github.com/fastmachinelearning/hls4ml/pull/540
  • Ensure 2 bits for scale in po2 quantizers by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/531
  • Link update by @bkmgit in https://github.com/fastmachinelearning/hls4ml/pull/519
  • Fix removal of nodes ingested by multiple downstream nodes by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/544
  • Enable SeparableConv2d by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/547
  • Extension API by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/528
  • change string ReuseFactor to int by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/416
  • Make the size of bn scale and bias what they really are by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/532
  • Raise runtime error when a layer is named input by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/482
  • fix insertion before a node with multiple inputs + support additional broadcasting by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/551
  • Pointwise conv1d/2d resource by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/471
  • Quartus Embedding Layer by @bo3z in https://github.com/fastmachinelearning/hls4ml/pull/548
  • Fix for QActivations passed as an argument by @AdrianAlan in https://github.com/fastmachinelearning/hls4ml/pull/553
  • Don't override precision directly in the QKeras optimizer by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/567
  • Remove the in/out size from top function by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/559
  • Transpose2d, Concatenate2d, and up to 3 Clones for io_stream by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/402
  • Remove ioserial as iostream and add some more info in docs. by @Duchstf in https://github.com/fastmachinelearning/hls4ml/pull/334
  • Update docs for v0.6.0 by @thesps in https://github.com/fastmachinelearning/hls4ml/pull/453
  • Use correct number of args for multiple outputs by @apfusco in https://github.com/fastmachinelearning/hls4ml/pull/487
  • Fixed a few typos in the documentation by @pitmonticone in https://github.com/fastmachinelearning/hls4ml/pull/467
  • returning integer from computen_samples by @JochiSt in https://github.com/fastmachinelearning/hls4ml/pull/537
  • Providing support for Alveo boards by @selwyn96 in https://github.com/fastmachinelearning/hls4ml/pull/552
  • Make layer names case sensitive in config. by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/577
  • Add issue and PR templates by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/582
  • Vivado Backend GRU/LSTM support by @drankincms in https://github.com/fastmachinelearning/hls4ml/pull/560
  • Update CI template syntax by @thesps in https://github.com/fastmachinelearning/hls4ml/pull/593
  • Update flow dependencies by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/588
  • Fix parsing of ZeroPadding layers by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/595
  • remove cppname by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/562
  • Remove email helpline from the docs by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/601
  • Fixes for GRU/LSTM in Vivado backend by @drankincms in https://github.com/fastmachinelearning/hls4ml/pull/598
  • Remove io_serial by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/609
  • Fix test_graph by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/611
  • Override parent backend optimizer passes with derived backend passes by @thesps in https://github.com/fastmachinelearning/hls4ml/pull/597
  • Enforce function pipelining when using io_parallel with Resource strategy by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/605
  • FIFO depth optimization by @nicologhielmetti in https://github.com/fastmachinelearning/hls4ml/pull/509
  • Add tracing support for the quartus backend by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/583
  • Quartus streaming support for Activations, Dense & Batch Normalization by @bo3z in https://github.com/fastmachinelearning/hls4ml/pull/557
  • QConv alpha != 1 bug fix by @bo3z in https://github.com/fastmachinelearning/hls4ml/pull/612
  • Quartus Stream Embedding by @bo3z in https://github.com/fastmachinelearning/hls4ml/pull/625
  • change master to main by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/602
  • Edit order of the optimizers in the flow so that BramFactor is followed by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/621
  • Softmax LUT Optimization by @bo3z in https://github.com/fastmachinelearning/hls4ml/pull/570
  • Quartus Synthesis Flow Improvement by @bo3z in https://github.com/fastmachinelearning/hls4ml/pull/618
  • Quartus Extensions by @bo3z in https://github.com/fastmachinelearning/hls4ml/pull/628
  • Quartus GRU by @bo3z in https://github.com/fastmachinelearning/hls4ml/pull/596
  • Quartus Merge layers by @bo3z in https://github.com/fastmachinelearning/hls4ml/pull/634
  • fix nondefault project name handling by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/626
  • Fix parsing of logic synthesis reports by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/639
  • Fix conv1d stream implementation hls directives by @Jonathan-Shoemaker in https://github.com/fastmachinelearning/hls4ml/pull/635
  • Implementation and optimizations linked to Simple-RNN and LSTM for qu… by @nemerchiedde in https://github.com/fastmachinelearning/hls4ml/pull/575
  • Softsign optimization by @nemerchiedde in https://github.com/fastmachinelearning/hls4ml/pull/585
  • Parallel CNNs, Pooling & Image Layers for Quartus Backend by @bo3z in https://github.com/fastmachinelearning/hls4ml/pull/561
  • Quartus Streaming Softsign (PR #585 contd.) by @bo3z in https://github.com/fastmachinelearning/hls4ml/pull/655
  • Remove final reshapes even for Quartus by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/661
  • Unrolled CNN implementation by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/600
  • the strategy was not propagated in the pytest by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/663
  • Fix keras model loading issue with loading model with KerasH5 by @calad0i in https://github.com/fastmachinelearning/hls4ml/pull/664
  • append applied_flows container before filling instead of after by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/641
  • set version using setuptools_scm by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/479
  • Argmax Softmax by @bo3z in https://github.com/fastmachinelearning/hls4ml/pull/627
  • Fix version extraction in Sphinx config by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/669
  • Add requested citations to README by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/615
  • skip BatchNorm fusion when input/output is used multiple times by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/481
  • Use wider accum_t for (average) pooling by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/681
  • Quartus Streaming Conv, Pooling & Image layers by @bo3z in https://github.com/fastmachinelearning/hls4ml/pull/656
  • Create branch on PR by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/636
  • Delete example-prjs directory by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/682
  • Adiabatically turn on pre-commit by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/678
  • Add causal padding by @cgutsche in https://github.com/fastmachinelearning/hls4ml/pull/688
  • Update pre-commit GitHub Action by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/689
  • New configfromkeras_model by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/690
  • remove obsolete np.int and np.float by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/703
  • Update p-clang-format to work on mac by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/704
  • Fix function call in Alveo tcl script by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/694
  • add readme for contrib by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/706
  • WIP Add custom KL loss layer HLS implementation by @katyagovorkova in https://github.com/fastmachinelearning/hls4ml/pull/606
  • Fix incorrectly linted build() command by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/709
  • For encoded convolution, add check for when minwidth would have been larger than inwidth by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/610
  • fifodepthoptimization flow require ip, not writer, before running by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/642
  • update isort to fix pre-commit by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/719
  • Fixed sign parsing for acfixed and acint by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/727
  • Correctly expand dims of pointwise layer by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/715
  • Support keepdims in GlobalPooling layers by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/716
  • Register layer attributes in VivadoAccelerator backend by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/724
  • Add quantized sigmoid, fix quantized tanh for QKeras by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/569
  • printvivadoreport function for nicer reports by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/730
  • Quartus bram factor by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/700
  • Fix inplace variables by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/714
  • Fix for cloned stream that is subsequently flattened by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/708
  • Vitis HLS backend by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/629
  • Update documentation for v0.7.0 release by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/710
  • Fix release notes + version in docs by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/742
  • Fix precommits by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/741
  • mv dependabot.yml by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/743
  • Bump actions/setup-python from 2 to 4 by @dependabot in https://github.com/fastmachinelearning/hls4ml/pull/748
  • fix Vitis pragmas messed up by pre-commit by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/751
  • Additional cleanup of the codebase by @vloncar in https://github.com/fastmachinelearning/hls4ml/pull/750
  • Fix for BatchNormalization layers with center=False or scale=False by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/754
  • Remove references to GPL since we now use a different license by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/761
  • Fix pooling layers when padding is applied from the left/top by @JanFSchulte in https://github.com/fastmachinelearning/hls4ml/pull/757
  • Further update documentation for 0.7.0 by @jmitrevs in https://github.com/fastmachinelearning/hls4ml/pull/744
  • Update pypi-publish.yml by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/763
  • Fix pypi version by @jmduarte in https://github.com/fastmachinelearning/hls4ml/pull/766

New Contributors

  • @siorpaes made their first contribution in https://github.com/fastmachinelearning/hls4ml/pull/424
  • @nemerchiedde made their first contribution in https://github.com/fastmachinelearning/hls4ml/pull/527
  • @ChiRuiChen made their first contribution in https://github.com/fastmachinelearning/hls4ml/pull/520
  • @bo3z made their first contribution in https://github.com/fastmachinelearning/hls4ml/pull/523
  • @bkmgit made their first contribution in https://github.com/fastmachinelearning/hls4ml/pull/519
  • @apfusco made their first contribution in https://github.com/fastmachinelearning/hls4ml/pull/487
  • @pitmonticone made their first contribution in https://github.com/fastmachinelearning/hls4ml/pull/467
  • @JochiSt made their first contribution in https://github.com/fastmachinelearning/hls4ml/pull/537
  • @selwyn96 made their first contribution in https://github.com/fastmachinelearning/hls4ml/pull/552
  • @Jonathan-Shoemaker made their first contribution in https://github.com/fastmachinelearning/hls4ml/pull/635
  • @calad0i made their first contribution in https://github.com/fastmachinelearning/hls4ml/pull/664
  • @cgutsche made their first contribution in https://github.com/fastmachinelearning/hls4ml/pull/688
  • @dependabot made their first contribution in https://github.com/fastmachinelearning/hls4ml/pull/748
  • @JanFSchulte made their first contribution in https://github.com/fastmachinelearning/hls4ml/pull/757

Full Changelog: https://github.com/fastmachinelearning/hls4ml/compare/v0.6.0...v0.7.0rc1

- Python
Published by jmduarte almost 3 years ago

hls4ml - coris

What's Changed

  • VivadoAccelerator backend: target pynq-z2 and zcu102 boards directly from hls4ml by @nicologhielmetti
  • Updated PyTorch and ONNX converters by @Duchstf
  • line_buffer Conv2D implementation for io_stream: reduced resource usage and latency by @Keb-L, @violatingcp, @vloncar
  • Support QConv2DBatchnorm layer from QKeras by @nicologhielmetti
  • Improved profiling plots - easier to compare original vs hls4ml converted models by @maksgraczyk
  • Better derivation of data types for QKeras models by @jmduarte, @thesps
  • Improved CI by @thesps
  • More support for models with branches, skip connections, Merge and Concatenate layers by @jmduarte, @vloncar
  • Support for Dense layers over multi-dimensional tensors by @vloncar
  • Overall improvements by @vloncar, @jmduarte, @thesps, @jmitrevs & others

New Contributors

  • @siorpaes made their first contribution in https://github.com/fastmachinelearning/hls4ml/pull/424
  • @jmitrevs made their first contribution in https://github.com/fastmachinelearning/hls4ml/pull/403
  • @anders-wind made their first contribution in https://github.com/fastmachinelearning/hls4ml/pull/302
  • @KOVI89alipes made their first contribution in https://github.com/fastmachinelearning/hls4ml/pull/318
  • @maksgraczyk made their first contribution in https://github.com/fastmachinelearning/hls4ml/pull/323
  • @Keb-L made their first contribution in https://github.com/fastmachinelearning/hls4ml/pull/332
  • @ConsVin made their first contribution in https://github.com/fastmachinelearning/hls4ml/pull/307
  • @nicologhielmetti made their first contribution in https://github.com/fastmachinelearning/hls4ml/pull/298

Full Changelog: https://github.com/fastmachinelearning/hls4ml/compare/v0.5.0...v0.6.0

- Python
Published by thesps over 4 years ago

hls4ml - bartsia

What's new: - Streaming IO layer implementations, especially of Convolutional layers, accessed through the config with IOType: io_stream. Scales CNN support to much larger models than previously possible (see arXiv:2101.05108) - New documentation and API reference - Further optimizations for QKeras / quantization aware training. A 'shift' operation is now used for po2 quantizers - Allow redefinition of weights directory for standalone project compilation - profiling for PyTorch models

Deprecated: - IOType : io_serial is deprecated, and superceded by new IOType: io_stream

Bugfixes: - Fix to Initiation Interval and different min/max latency for Strategy: Resource - Fix warnings in hls4ml command line script flow - Write yml config from Python API - for mixed API / command line flow

- Python
Published by thesps almost 5 years ago

hls4ml -

Pre-release of hls4ml version v0.5.0.

What's new: - Streaming IO layer implementations, especially of Convolutional layers, accessed through the config with io_type: io_stream. Scales CNN support to much larger models than previously possible (see paper) - New documentation and API reference - Further optimizations for QKeras / quantization aware training. A 'shift' operation is now used for po2 quantizers - Allow redefinition of weights directory for standalone project compilation

- Python
Published by thesps about 5 years ago

hls4ml - aster

What's new:

  • Support for GarNet layer (see paper)
  • Input layer precision added to config generator utility
  • New 'SkipOptimizers' config option. Now you can run all Optimizers by default (as in v0.3.0) but subtract any specified by 'SkipOptimizers' e.g. hls_config['SkipOptimizers'] = ['fuse_consecutive_batch_normalization']
  • Print out the latency report from Cosimulation

Bugfixes:

  • Fixes related to tensorflow 2.3: new Functional API, changes to handling of Input layer
  • Fix error with config generator utility and activation layers gor granularity='name'
  • Fix issue with reloading of emulation library after configuration change
  • Fix to handling of layers with use_bias=False and merged Dense and BatchNormalization

- Python
Published by thesps over 5 years ago

hls4ml - v0.3.0

What's new: - API expansion: - Create configuration dictionary from model object - Run 'C Simulation' from Python with hls_model.predict(X) - Trace model layer output with hls_model.trace(X) - Write HLS project, run synthesis flow from Python - QKeras support: convert models trained using layers and quantizers from QKeras - Example models moved to separate repo, added as a submodule with an API to retrieve them - New Softmax implementations - Minor fixes: weights exported at higher precision, concatenate layer shape corrected

- Python
Published by thesps over 5 years ago

hls4ml - v0.2.0

What's new: - tf_to_hls: convert tensorflow protobuf (.pb) models to HLS projects - Support for Keras model .h5 files (extending existing support for .json architecture + .h5 weights format) - Support larger Conv1D / 2D layers - Support for binary and ternary layers from QKeras - API enhancements for addition of custom layer and new backends - Keras and HLS model profiling tool - hls4ml report command to gather HLS build reports - hls4ml build -l command to run logic synthesis - Fused Batch Normalization and Dense layer optimization pass

- Python
Published by thesps almost 6 years ago

hls4ml - v0.1.6

  • Support for larger Dense layers (enabled with Strategy: Resource in the configuration file)
  • Binary/Ternary NN refinements
  • Built-in optimization framework
  • Optional C/RTL validation

- Python
Published by vloncar about 6 years ago

hls4ml - v0.1.5

- Python
Published by jmduarte over 6 years ago

hls4ml - v0.1.2

Update license

- Python
Published by benjaminkreis almost 8 years ago

hls4ml - v0.1.1

second beta version: fixed README

- Python
Published by jmduarte almost 8 years ago