This repository has been archived by the owner on Oct 23, 2023. It is now read-only.
Releases: Xilinx/finn-base
Releases · Xilinx/finn-base
finn-base v0.0.3
Highlights:
- New high-level quantization ops for expressing quantized networks more flexibly in the QONNX format
- Inference cost (MACs at particular precision + memory) estimation
DataTypesystem refactoring to allow flexible arbitrary-precision integers and fixed-point types
Merged PRs:
- #36 Copied platforms from finn-experimental and made pre-commit conform
- #37 Added support for cost estimation for upsampling
- #41 Add support for Bipolar and Binary FINN datatype for Quant op.
- #42 #43 Updates to inference cost computation (Upsample and binary quantization)
- #44 chore: Add message to AssertionError
- #45 Various fixes from multi-headed net testing
- #46 Pull upstream changes into qonnx_quant_op
- #47 rtlsim improvements
- #48 Support and tests for unsetting FINN data types.
- #50 DataType system refactoring and fixed-point types
- #51 Faster&smaller shape inference
- #52 QONNX ops and new general transformations
finn-base v0.0.2b
Highlights:
- Generic partitioning + ExtendPartition transformations for working with large models
- Fast-mode data packing for binary values
- Changes to support non-equal image dimensions / kernel / stride / .. for convolutions
PRs:
- Add ZCU111 board to part map #32 by fpjentzsch
- Support infer_datatype for flatten layer #30 by fpjentzsch
- Changes for supporting non-equal dilation #29 by mmrahorovic
- Changes for supporting vitis_hls #28 by maltanar
- Added ExtendPartition transformation #27 by mmrahorovic
- Remove redundant output value_info entries #26 by mmrahorovic
- Added support for non-equal strides along different axes #25 by mmrahorovic
- Experimental: fast_mode data packing for binary #24 by maltanar
- Generic partitioning feature #23 by fpjentzsch
- Update quantavgpool2d.py #22 by jalezeta
- Changed how the epsilon value is set #21 by mmrahorovic
- Support for non-square input images and kernels for im2col node #20 by mmrahorovic
- Added 3D to 4D (tensor) transformation #19 by mmrahorovic
- Modified set_nodeattr to allow using it on repeated fields #18 by mmrahorovic
- Added support for dilation value = 2 for 1D and 2D images/kernels #17 by mmrahorovic
- Support for non-square input images and kernels in LowerConvsToMatMul transformation #16 by mmrahorovic