This repository has been archived by the owner on Oct 23, 2023. It is now read-only.
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
QONNX ops and new general transformations (#52)
* [Op] add skeleton for Quant custom op * [Op] more comments on Quant op * [InferDT] add MaxPool to list of identity ops for datatype inf. * [Transform] temporarily exclude Quant ops from const folding * [Analysis] add skeleton for inference_cost, limited conv support * [Analysis] support inference_cost_matmul * [Deps] add clize * [Util] add inference_cost util with entrypoint * [Docker] add clize * [Infra] add entrypoint for inference_cost * Preliminary implementation of quant operation * Fixed wrong numpy type in quant op * Made Quant pre-commit compatible * Changed docker base image to PyTorch and added Brevitas dockerfile and entrypoint * Implemented preliminary test for Quant operation * Reworked comments for Quant operation * Readability improvements for Quant operation * Created preliminary Quant op documentation * Move Quant op documentation * Made documentation of quant attributes more precise. * Created skeleton for Trunc QNNX operation * [DataType] add experimental SCALED(U)INT DataTypes * [Quant] use new scaled int dtypes for dt inference * [TypInf] use non-integer instead of float check in dt inference * [ConstFold] make op exclusion optional * [Analysis] deal with dyn matmul, add some zero-cost op types * [Analysis] make inference_cost optionally sparse-weights-aware * [Util] pass sparsity option to analysis pass, kwargs only for clize * [Analysis] add more free ops to inference_cost * [Quant] fallback to float32 for failed dtype inference * Inference cost: JSON export, parameter for output onnx * Removed FINN dependency from documentation * Added support for executing qonnx custom_ops. * Add support for Bipolar and Binary FINN datatype for Quant op. (#41) * Add support for Bipolar and Binary FINN datatype for Quant op. * [Quant] custom qnt execution for bipolar until Brevitas bug resolved Co-authored-by: Yaman Umuroglu <yamanu@xilinx.com> * Added support for cost estimation for upsampling (#37) * Update AUTHORS.rst * Create python-publish.yml * Add ZCU111 board to part map (#32) * Update AUTHORS.rst * GHA for PyPI, sdist only (#35) * finn-base v0.0.2 (#34) * Modified set_nodeattr to allow using it on repeated fields (#18) * [base]: changed how the floats, ints, strings, tensors, graphs and sparse_tensors field of AttributeProto is set. * [Core] restrict attributes to tested types Co-authored-by: Yaman Umuroglu <yamanu@xilinx.com> * Support for non-square input images and kernels for im2col node (#20) * [im2col.py]: support for non-square input images and kernels, [test_im2col]: added/modified several test cases for (non-)square images and kernels * [im2col]: support for non-square input images and kernels, [test_im2col]: added/modified several test cases for (non-)square images and kernels * [test_general_transformation]: changed kernel_size attribute to list instead of integer as required by im2col node * [base]: changed how the "ints" field of AttributeProto set. [test_general_transformation]: changed the type of the kernel_size attribute to list of integers * removed unused import * [base]: added support for writing repeated fields in AttributeProto * minor style changes * [im2col, test_im2col]: added support for non-equal padding * [lower_convs_to_matmul]: added support for non-square input images and kernels and non-equal padding. [test_conv_lowering]: added/modified test cases for non-equal padding, depthwise convolution and 'standard' convolution. * [test_conv_lowering]: included 1D depthwise and regular convolutions in tests * Revert "[test_conv_lowering]: included 1D depthwise and regular convolutions in tests" This reverts commit 3ff449c * Revert "[lower_convs_to_matmul]: added support for non-square input images and kernels and non-equal padding." This reverts commit 15e34ed. * Revert "[im2col, test_im2col]: added support for non-equal padding" This reverts commit c524020. * [im2col]: changed how a square kernel is instantiated. [lower_convs_to_matmul]: changed how the kernel size attribute is read (based on how a square kernel is instantiated). * [im2col]: minor change in style. * [Im2Col] style fixes and comments Co-authored-by: Yaman Umuroglu <yamanu@xilinx.com> * Update AUTHORS.rst * Support for non-square input images and kernels in LowerConvsToMatMul transformation (#16) * [im2col.py]: support for non-square input images and kernels, [test_im2col]: added/modified several test cases for (non-)square images and kernels * [im2col]: support for non-square input images and kernels, [test_im2col]: added/modified several test cases for (non-)square images and kernels * [test_general_transformation]: changed kernel_size attribute to list instead of integer as required by im2col node * [base]: changed how the "ints" field of AttributeProto set. [test_general_transformation]: changed the type of the kernel_size attribute to list of integers * removed unused import * [base]: added support for writing repeated fields in AttributeProto * minor style changes * [im2col, test_im2col]: added support for non-equal padding * [lower_convs_to_matmul]: added support for non-square input images and kernels and non-equal padding. [test_conv_lowering]: added/modified test cases for non-equal padding, depthwise convolution and 'standard' convolution. * [test_conv_lowering]: included 1D depthwise and regular convolutions in tests * Revert "[test_conv_lowering]: included 1D depthwise and regular convolutions in tests" This reverts commit 3ff449c * Revert "[lower_convs_to_matmul]: added support for non-square input images and kernels and non-equal padding." This reverts commit 15e34ed. * Revert "[im2col, test_im2col]: added support for non-equal padding" This reverts commit c524020. * [im2col] function compute_conv_output_dim can now be called in case non-equal and equal padding is assumed. [test_im2col] changed function call to compute_conv_output_dim. [test_conv_lowering] changed function call to compute_conv_output_dim. [lower_convs_to_matmul] removed old assertion. * [im2col]: changed how a square kernel is instantiated. [lower_convs_to_matmul]: changed how the kernel size attribute is read (based on how a square kernel is instantiated). * [im2col]: changed how a square kernel is instantiated. [lower_convs_to_matmul]: changed how the kernel size attribute is read (based on how a square kernel is instantiated). * [im2col]: minor change in style. * [test_conv_lowering]: minor fix for test case depthwise and regular convolutions * Support for non-square input images and kernels for im2col node (#20) * [im2col.py]: support for non-square input images and kernels, [test_im2col]: added/modified several test cases for (non-)square images and kernels * [im2col]: support for non-square input images and kernels, [test_im2col]: added/modified several test cases for (non-)square images and kernels * [test_general_transformation]: changed kernel_size attribute to list instead of integer as required by im2col node * [base]: changed how the "ints" field of AttributeProto set. [test_general_transformation]: changed the type of the kernel_size attribute to list of integers * removed unused import * [base]: added support for writing repeated fields in AttributeProto * minor style changes * [im2col, test_im2col]: added support for non-equal padding * [lower_convs_to_matmul]: added support for non-square input images and kernels and non-equal padding. [test_conv_lowering]: added/modified test cases for non-equal padding, depthwise convolution and 'standard' convolution. * [test_conv_lowering]: included 1D depthwise and regular convolutions in tests * Revert "[test_conv_lowering]: included 1D depthwise and regular convolutions in tests" This reverts commit 3ff449c * Revert "[lower_convs_to_matmul]: added support for non-square input images and kernels and non-equal padding." This reverts commit 15e34ed. * Revert "[im2col, test_im2col]: added support for non-equal padding" This reverts commit c524020. * [im2col]: changed how a square kernel is instantiated. [lower_convs_to_matmul]: changed how the kernel size attribute is read (based on how a square kernel is instantiated). * [im2col]: minor change in style. * [Im2Col] style fixes and comments Co-authored-by: Yaman Umuroglu <yamanu@xilinx.com> * Update AUTHORS.rst Co-authored-by: Yaman Umuroglu <yamanu@xilinx.com> * Added support for dilation value = 2 for 1D and 2D images/kernels (#17) * [im2col.py]: support for non-square input images and kernels, [test_im2col]: added/modified several test cases for (non-)square images and kernels * [im2col]: support for non-square input images and kernels, [test_im2col]: added/modified several test cases for (non-)square images and kernels * [test_general_transformation]: changed kernel_size attribute to list instead of integer as required by im2col node * [base]: changed how the "ints" field of AttributeProto set. [test_general_transformation]: changed the type of the kernel_size attribute to list of integers * removed unused import * [base]: added support for writing repeated fields in AttributeProto * minor style changes * [im2col, test_im2col]: added support for non-equal padding * [lower_convs_to_matmul]: added support for non-square input images and kernels and non-equal padding. [test_conv_lowering]: added/modified test cases for non-equal padding, depthwise convolution and 'standard' convolution. * [test_conv_lowering]: included 1D depthwise and regular convolutions in tests * Revert "[test_conv_lowering]: included 1D depthwise and regular convolutions in tests" This reverts commit 3ff449c * Revert "[lower_convs_to_matmul]: added support for non-square input images and kernels and non-equal padding." This reverts commit 15e34ed. * Revert "[im2col, test_im2col]: added support for non-equal padding" This reverts commit c524020. * [im2col] added support for dilations = 2 for 2D and 1D images. Dilation value must be equal along each axis. [test_im2col] added several test cases in case dilations = 2 (a.o. cases where image and kernel are 2D and 1D, with and without padding, and with stride = 2). [lower_convs_to_matmul] added support for dilation value. Dilation value must be equal along each axis. [test_conv_lowering] added test case for dilations = 2 for 2D and 1D images and kernels, with and without padding, and with stride = 2. * [lower_convs_to_matmul] removed old assertion [test_conv_lowering] added more dilation values to test cases. Dilation values of {1, 2, 3, 4} are tested. * [im2col] function compute_conv_output_dim can now be called in case non-equal and equal padding is assumed. [test_im2col] changed function call to compute_conv_output_dim [test_conv_lowering] changed function call to compute_conv_output_dim * [im2col] function compute_conv_output_dim can now be called in case non-equal and equal padding is assumed. [test_im2col] changed function call to compute_conv_output_dim. [test_conv_lowering] changed function call to compute_conv_output_dim. [lower_convs_to_matmul] removed old assertion. * [im2col]: changed how a square kernel is instantiated. [lower_convs_to_matmul]: changed how the kernel size attribute is read (based on how a square kernel is instantiated). * [im2col]: changed how a square kernel is instantiated. [lower_convs_to_matmul]: changed how the kernel size attribute is read (based on how a square kernel is instantiated). * [im2col]: changed how a square kernel is instantiated. [lower_convs_to_matmul]: changed how the kernel size attribute is read (based on how a square kernel is instantiated). * [im2col]: minor change in style. * [test_conv_lowering]: minor fix for test case depthwise and regular convolutions * [im2col]: minor style adjustment. [test_conv_lowering]: merged test functions into one test function. * Support for non-square input images and kernels for im2col node (#20) * [im2col.py]: support for non-square input images and kernels, [test_im2col]: added/modified several test cases for (non-)square images and kernels * [im2col]: support for non-square input images and kernels, [test_im2col]: added/modified several test cases for (non-)square images and kernels * [test_general_transformation]: changed kernel_size attribute to list instead of integer as required by im2col node * [base]: changed how the "ints" field of AttributeProto set. [test_general_transformation]: changed the type of the kernel_size attribute to list of integers * removed unused import * [base]: added support for writing repeated fields in AttributeProto * minor style changes * [im2col, test_im2col]: added support for non-equal padding * [lower_convs_to_matmul]: added support for non-square input images and kernels and non-equal padding. [test_conv_lowering]: added/modified test cases for non-equal padding, depthwise convolution and 'standard' convolution. * [test_conv_lowering]: included 1D depthwise and regular convolutions in tests * Revert "[test_conv_lowering]: included 1D depthwise and regular convolutions in tests" This reverts commit 3ff449c * Revert "[lower_convs_to_matmul]: added support for non-square input images and kernels and non-equal padding." This reverts commit 15e34ed. * Revert "[im2col, test_im2col]: added support for non-equal padding" This reverts commit c524020. * [im2col]: changed how a square kernel is instantiated. [lower_convs_to_matmul]: changed how the kernel size attribute is read (based on how a square kernel is instantiated). * [im2col]: minor change in style. * [Im2Col] style fixes and comments Co-authored-by: Yaman Umuroglu <yamanu@xilinx.com> * Update AUTHORS.rst * Support for non-square input images and kernels in LowerConvsToMatMul transformation (#16) * [im2col.py]: support for non-square input images and kernels, [test_im2col]: added/modified several test cases for (non-)square images and kernels * [im2col]: support for non-square input images and kernels, [test_im2col]: added/modified several test cases for (non-)square images and kernels * [test_general_transformation]: changed kernel_size attribute to list instead of integer as required by im2col node * [base]: changed how the "ints" field of AttributeProto set. [test_general_transformation]: changed the type of the kernel_size attribute to list of integers * removed unused import * [base]: added support for writing repeated fields in AttributeProto * minor style changes * [im2col, test_im2col]: added support for non-equal padding * [lower_convs_to_matmul]: added support for non-square input images and kernels and non-equal padding. [test_conv_lowering]: added/modified test cases for non-equal padding, depthwise convolution and 'standard' convolution. * [test_conv_lowering]: included 1D depthwise and regular convolutions in tests * Revert "[test_conv_lowering]: included 1D depthwise and regular convolutions in tests" This reverts commit 3ff449c * Revert "[lower_convs_to_matmul]: added support for non-square input images and kernels and non-equal padding." This reverts commit 15e34ed. * Revert "[im2col, test_im2col]: added support for non-equal padding" This reverts commit c524020. * [im2col] function compute_conv_output_dim can now be called in case non-equal and equal padding is assumed. [test_im2col] changed function call to compute_conv_output_dim. [test_conv_lowering] changed function call to compute_conv_output_dim. [lower_convs_to_matmul] removed old assertion. * [im2col]: changed how a square kernel is instantiated. [lower_convs_to_matmul]: changed how the kernel size attribute is read (based on how a square kernel is instantiated). * [im2col]: changed how a square kernel is instantiated. [lower_convs_to_matmul]: changed how the kernel size attribute is read (based on how a square kernel is instantiated). * [im2col]: minor change in style. * [test_conv_lowering]: minor fix for test case depthwise and regular convolutions * Support for non-square input images and kernels for im2col node (#20) * [im2col.py]: support for non-square input images and kernels, [test_im2col]: added/modified several test cases for (non-)square images and kernels * [im2col]: support for non-square input images and kernels, [test_im2col]: added/modified several test cases for (non-)square images and kernels * [test_general_transformation]: changed kernel_size attribute to list instead of integer as required by im2col node * [base]: changed how the "ints" field of AttributeProto set. [test_general_transformation]: changed the type of the kernel_size attribute to list of integers * removed unused import * [base]: added support for writing repeated fields in AttributeProto * minor style changes * [im2col, test_im2col]: added support for non-equal padding * [lower_convs_to_matmul]: added support for non-square input images and kernels and non-equal padding. [test_conv_lowering]: added/modified test cases for non-equal padding, depthwise convolution and 'standard' convolution. * [test_conv_lowering]: included 1D depthwise and regular convolutions in tests * Revert "[test_conv_lowering]: included 1D depthwise and regular convolutions in tests" This reverts commit 3ff449c * Revert "[lower_convs_to_matmul]: added support for non-square input images and kernels and non-equal padding." This reverts commit 15e34ed. * Revert "[im2col, test_im2col]: added support for non-equal padding" This reverts commit c524020. * [im2col]: changed how a square kernel is instantiated. [lower_convs_to_matmul]: changed how the kernel size attribute is read (based on how a square kernel is instantiated). * [im2col]: minor change in style. * [Im2Col] style fixes and comments Co-authored-by: Yaman Umuroglu <yamanu@xilinx.com> * Update AUTHORS.rst Co-authored-by: Yaman Umuroglu <yamanu@xilinx.com> Co-authored-by: Yaman Umuroglu <yamanu@xilinx.com> * Update quantavgpool2d.py (#22) Add "Copyright (c) 2021 Xilinx, Inc" heather * [batchnorm_to_affine]: epsilon value is now read out from the attributes. (#21) [test_batchnorm_to_affine]: added a test case for various epsilon values. * Added 3D to 4D (tensor) transformation (#19) * [im2col.py]: support for non-square input images and kernels, [test_im2col]: added/modified several test cases for (non-)square images and kernels * [im2col]: support for non-square input images and kernels, [test_im2col]: added/modified several test cases for (non-)square images and kernels * [test_general_transformation]: changed kernel_size attribute to list instead of integer as required by im2col node * [base]: changed how the "ints" field of AttributeProto set. [test_general_transformation]: changed the type of the kernel_size attribute to list of integers * removed unused import * [base]: added support for writing repeated fields in AttributeProto * minor style changes * [im2col, test_im2col]: added support for non-equal padding * [lower_convs_to_matmul]: added support for non-square input images and kernels and non-equal padding. [test_conv_lowering]: added/modified test cases for non-equal padding, depthwise convolution and 'standard' convolution. * [test_conv_lowering]: included 1D depthwise and regular convolutions in tests * Revert "[test_conv_lowering]: included 1D depthwise and regular convolutions in tests" This reverts commit 3ff449c * Revert "[lower_convs_to_matmul]: added support for non-square input images and kernels and non-equal padding." This reverts commit 15e34ed. * Revert "[im2col, test_im2col]: added support for non-equal padding" This reverts commit c524020. * [im2col] added support for dilations = 2 for 2D and 1D images. Dilation value must be equal along each axis. [test_im2col] added several test cases in case dilations = 2 (a.o. cases where image and kernel are 2D and 1D, with and without padding, and with stride = 2). [lower_convs_to_matmul] added support for dilation value. Dilation value must be equal along each axis. [test_conv_lowering] added test case for dilations = 2 for 2D and 1D images and kernels, with and without padding, and with stride = 2. * [lower_convs_to_matmul] removed old assertion [test_conv_lowering] added more dilation values to test cases. Dilation values of {1, 2, 3, 4} are tested. * [im2col] function compute_conv_output_dim can now be called in case non-equal and equal padding is assumed. [test_im2col] changed function call to compute_conv_output_dim [test_conv_lowering] changed function call to compute_conv_output_dim * [im2col] function compute_conv_output_dim can now be called in case non-equal and equal padding is assumed. [test_im2col] changed function call to compute_conv_output_dim. [test_conv_lowering] changed function call to compute_conv_output_dim. [lower_convs_to_matmul] removed old assertion. * [im2col]: minor fix with assumption on kernel dimension [lower_convs_to_matmul]: minor fix with assumption on kernel dimension * [change_3d_tensors_to_4d]: added new transformation that transforms 3D tensors to 4D and changes the nodes accordingly [test_4d_conversion]: test function for 3D to 4D tensor transformation * [change_3d_tensors_to_4d]: added new transformation that changes 3D tensors to 4D. [test_4d_conversion]: added a test case for the 3D to 4D transformation. * [change_3d_tensors_to_4d]: added 3D to 4D transformation (for QuartzNet). [test_4d_conversion]: added test case for 3D to 4D transform. * [change_3d_tensors_to_4d]: changed how an invalid graph is handled. [test_4d_conversion]: changed the test case for an invalid graph. * [im2col]: changed how a square kernel is instantiated. [lower_convs_to_matmul]: changed how the kernel size attribute is read (based on how a square kernel is instantiated). * [im2col]: changed how a square kernel is instantiated. [lower_convs_to_matmul]: changed how the kernel size attribute is read (based on how a square kernel is instantiated). * [im2col]: changed how a square kernel is instantiated. [lower_convs_to_matmul]: changed how the kernel size attribute is read (based on how a square kernel is instantiated). * [im2col]: minor change in style. * [im2col]: minor style change and changed the way how a square kernel is instantiated. * [test_conv_lowering]: merged tests for depthwise and standard convolutions. * [test_conv_lowering]: minor fix for test case depthwise and regular convolutions * [im2col]: minor style adjustment. [test_conv_lowering]: merged test functions into one test function. * [change_3d_tensors_to_4d]: style fixes and comments. [test_4d_converions]: rearranged code. * [Transform] check invalid node list length * [change_3d_tensors_to_4d]: rearranged the code to make it more readable. Co-authored-by: Yaman Umuroglu <yamanu@xilinx.com> * [Docs] update tutorials * [Util] experimental: fast_mode data packing for binary (#24) * Generic partitioning feature (#23) * Add basic partitioning functionality * Mount build dir within docker container * Support for non-linear models and multi in/out partitions * Remove dataflowpartition custom op from finn-base * Fix temporary build dir for CI * Fix docstring * [create_generic_partitions]: minor modification, removed redundant output value_info entries. (#26) * [extend_partition]: added a new transformation ExtendPartition. (#27) [test_extend_partition]: added a test case for the new transformation. * Added support for non-equal strides along different axes (#25) * [im2col]: added support for non-equal strides along different axes and cleaned up the code. [lower_convs_to_matmul]: added support for non-equal strides along different axes and cleaned up the code. [test_conv_lowering]: added test case for non-equal strides along different axes. * [im2col]: minor fix. [test_im2col]: added test case for non-equal strides along different axes. * Changes for supporting vitis_hls (#28) * [Refactor] split up RTL/HLS-related utils * [Util] rename to CallHLS and allow specifying vivado_hls/vitis_hls * [Util] more flexible stream naming in rtlsim_multi_io * Changes for supporting non-equal dilation (#29) * added support for non-equal dilation value along (H, W) dimension * added test cases for non-equal dilation configurations * appending dilation value along dummy dimension correctly (i.e. with a '1') * changed tensor sparsity annotation for consistency * Support infer_datatype for flatten layer (#30) * Support infer_datatype for flatten layer * [InferDT] add more identity op types for datatype inference * [Lint] fix linting issues Co-authored-by: Yaman Umuroglu <maltanar@gmail.com> * Update AUTHORS.rst * Create python-publish.yml * Add ZCU111 board to part map (#32) * Update AUTHORS.rst Co-authored-by: Mirza Mrahorovic <34712307+mmrahorovic@users.noreply.github.com> Co-authored-by: jalezeta <51440887+jalezeta@users.noreply.github.com> Co-authored-by: Felix Jentzsch <45395194+fpjentzsch@users.noreply.github.com> * Update python-publish.yml * Update python-publish.yml * Lint Co-authored-by: Mirza Mrahorovic <34712307+mmrahorovic@users.noreply.github.com> Co-authored-by: jalezeta <51440887+jalezeta@users.noreply.github.com> Co-authored-by: Felix Jentzsch <45395194+fpjentzsch@users.noreply.github.com> * Inference cost: JSON export, parameter for output onnx * Added support for cost estimation for upsampling Co-authored-by: Yaman Umuroglu <yamanu@xilinx.com> Co-authored-by: Felix Jentzsch <45395194+fpjentzsch@users.noreply.github.com> Co-authored-by: Mirza Mrahorovic <34712307+mmrahorovic@users.noreply.github.com> Co-authored-by: jalezeta <51440887+jalezeta@users.noreply.github.com> Co-authored-by: Felix Jentzsch <fepaje@mail.upb.de> * [Quant] fix edge case for 0d input array execution * Added trunc support for MobileNet, needs some fixing. * Made trunc datatype inference pass-through. * Addressed numpy deprecation warning in Truc op exectution. * Updated Quant op to support rounding mode. * Added support for new Trunc op. * Added support for static datatype inference to the Trunc op. * Resolved left over ToDo in Trunc op. * Remove scaledInt from Trunc op and replace with float32. * Moved RemoveIdentityOps transformation from FINN to finn-base. * Fixed a bug in RemoveIdentityOps, where an identity op would not get removed if it was preceded by another identity op. * Moved GemmToMatMul from FINN to finn-base. * Added support for recognizing MultiThreshold node in sign discovery. * Moved RemoveEmptyPadding transformation from finn to finn-base. * Updated Quant op documentation to add the rounding_mode attribute. * Added documentation for trunc op and small adjustments for Quant op documentation. * Added preliminary support for BinaryQuant node. * Updated datatype inference for Quant and BinaryQuant to remove scaledInt types. * Fixed bug in datatype inference for Quant node. * Added support for merging into non-linear graphs for _remove_node_and_rewire function. * Added another op to sign_preserving_ops. * Updated Trunc op documentation. * Extended graph based signed inference to more quantization nodes. * Renamed BinaryQuant to BipolarQuant. * Renamed BinaryQuant to BipolarQuant for Trunc op Signed inference. * Updated BipolarQuant op documentation and moved documentation of QONNX ops into their own folder. * Made remove_node_and_rewire function part of the publicly facing api. * Adapt test_remove_identity_ops to new datatype system. * Made padding removal more reliable. * Moved ExtractBiasFromConv transformation from FINN to finn-base. * Fixed changed import for test_remove_identity_ops test. * Extended MultiThreshold data type inference to adjust for float scale/bias. * Removed test_brevitas_quant_onnx_export_and_exec test, since test_QONNX_to_FINN in FINN already tests for the same. * Fixed spelling typos in QONNX op documentation. * Specified rounding operation in Quant and Trunc documentation. * Updated version description for QONNX ops documentation. * Removed dependency on onnxoptimizer. * Refactored check for float. * Refactored get_internal_dtype to get_integer_datatype. * Disabled constant folding for Quant and BipolarQuant by default. * Added a warning if an unsupported ONNX version is encountered during the GemmToMatMul transformation. * Moved functionality of RemoveEmptyPadding into RemoveIdentityOps. * Made float32 default output for Trunc node and removed #ference from node. Co-authored-by: Yaman Umuroglu <maltanar@gmail.com> Co-authored-by: Yaman Umuroglu <yamanu@xilinx.com> Co-authored-by: Felix Jentzsch <fepaje@mail.upb.de> Co-authored-by: Felix Jentzsch <45395194+fpjentzsch@users.noreply.github.com> Co-authored-by: Mirza Mrahorovic <34712307+mmrahorovic@users.noreply.github.com> Co-authored-by: jalezeta <51440887+jalezeta@users.noreply.github.com>
- Loading branch information
7 people
authored
Nov 1, 2021
1 parent
7c2603a
commit 71ed2e0