Release Notes

v1.0.0: foxglove 1.0.0

Released on 2024-12-09 - GitHub - PyPI

What's Changed

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

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

The full list of other improvements and fixes is:

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

New Contributors

@laurilaatu made their first contribution in #856
@dgburnette made their first contribution in #956
@sei-rquartiano made their first contribution in #1045
@jurevreca12 made their first contribution in #1132

Full Changelog: v0.8.1...v1.0.0

v0.8.1: edelweiss 0.8.1

Released on 2023-12-19 - GitHub - PyPI

What's Changed

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

New Contributors

@schsu made their first contribution in #941
@Landay7 made their first contribution in #940

Full Changelog: v0.8.0...v0.8.1

v0.8.0: edelweiss 0.8.0

Released on 2023-11-16 - GitHub - PyPI

What's Changed

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

New Contributors

@pre-commit-ci made their first contribution in #796
@joshlerner made their first contribution in #827
@qberthet made their first contribution in #891

Full Changelog: v0.7.1...v0.8.0

v0.8.0rc1: edelweiss 0.8.0rc1

Released on 2023-11-08 - GitHub - PyPI

What's Changed

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

New Contributors

@pre-commit-ci made their first contribution in #796
@joshlerner made their first contribution in #827
@qberthet made their first contribution in #891

Full Changelog: v0.7.1...v0.8.0rc1

v0.7.1: delphinium 0.7.1

Released on 2023-05-13 - GitHub - PyPI

What's Changed

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

Full Changelog: v0.7.0...v0.7.1

v0.7.0: delphinium

Released on 2023-04-26 - GitHub - PyPI

What's Changed

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

New Contributors

@siorpaes made their first contribution in #424
@nemerchiedde made their first contribution in #527
@ChiRuiChen made their first contribution in #520
@bo3z made their first contribution in #523
@bkmgit made their first contribution in #519
@apfusco made their first contribution in #487
@pitmonticone made their first contribution in #467
@JochiSt made their first contribution in #537
@selwyn96 made their first contribution in #552
@Jonathan-Shoemaker made their first contribution in #635
@calad0i made their first contribution in #664
@cgutsche made their first contribution in #688
@dependabot made their first contribution in #748
@JanFSchulte made their first contribution in #757

Full Changelog: v0.6.0...v0.7.0

v0.7.0rc1: delphinium rc1

Released on 2023-04-15 - GitHub - PyPI

What's Changed

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

New Contributors

@siorpaes made their first contribution in #424
@nemerchiedde made their first contribution in #527
@ChiRuiChen made their first contribution in #520
@bo3z made their first contribution in #523
@bkmgit made their first contribution in #519
@apfusco made their first contribution in #487
@pitmonticone made their first contribution in #467
@JochiSt made their first contribution in #537
@selwyn96 made their first contribution in #552
@Jonathan-Shoemaker made their first contribution in #635
@calad0i made their first contribution in #664
@cgutsche made their first contribution in #688
@dependabot made their first contribution in #748
@JanFSchulte made their first contribution in #757

Full Changelog: v0.6.0...v0.7.0rc1

v0.6.0: coris

Released on 2021-11-12 - GitHub - PyPI

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 #424
@jmitrevs made their first contribution in #403
@anders-wind made their first contribution in #302
@KOVI89alipes made their first contribution in #318
@maksgraczyk made their first contribution in #323
@Keb-L made their first contribution in #332
@ConsVin made their first contribution in #307
@nicologhielmetti made their first contribution in #298

Full Changelog: v0.5.0...v0.6.0

v0.5.0: bartsia

Released on 2021-03-05 - GitHub - PyPI

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

v0.5.0-beta

Released on 2021-01-18 - GitHub - PyPI

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

v0.4.0: aster

Released on 2020-10-30 - GitHub - PyPI

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

v0.3.0

Released on 2020-07-31 - GitHub - PyPI

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

v0.2.0

Released on 2020-03-31 - GitHub - PyPI

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

v0.1.6

Released on 2020-02-10 - GitHub - PyPI

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

v0.1.5

Released on 2019-08-02 - GitHub - PyPI

v0.1.2

Released on 2018-03-20 - GitHub - PyPI

Update license

v0.1.1

Released on 2018-03-16 - GitHub - PyPI

second beta version: fixed README