- Added support for InstanceNormalization on 5D tensors
- Added library only build target #659
- Added support for negative gather indices #681
- Added support for
DOUBLE
-typed inputs and weights through downcast to float #674 - Added support for optional plugin fields in FallbackPlugin path #676
- Updated license #657
- Fixed index offset calculation in GatherElements #675
- Clarified dynamic shape support for ReverseSequence
- Added opset13 support for
SoftMax
,LogSoftmax
,Squeeze
, andUnsqueeze
- Added support for the
EyeLike
operator - Added support for the
GatherElements
operator
- Added support for the
ReverseSequence
operator #590 - Updated
parse()
andsupportsModel()
API calls with an optionalmodel_path
parameter to support models with external weights #621 - Added support for the
Celu
operator - Added support for the
CumSum
operator - Added support for the
LessOrEqual
operator - Added support for the
LpNormalization
operator - Added support for the
LpPool
operator - Added support for the
GreaterOrEqual
operator - Added support for dynamic inputs in
onnx_tensorrt
python backend - Added FAQ section for commonly asked questions
- Fixed relative path imports for models with external weights [#619]onnx#619
- Fixed importing loops operators with no loop-carried depedencies #619
- Worked around unsupported BOOL concats through casting #620
- Fixed compilation error with GCC9 #568
- Removed
onnx_tensorrt/config.py
as it is no longer needed
- Added
setup.py
to properly installonnx_tensorrt
python backend - Added 4D transpose for ONNX weights #557
- Fixed slice computations for large slices #558
- Added support for parsing large models with external data
- Added API for interfacing with TensorRT's refit feature
- Updated
onnx_tensorrt
backend to support dynamic shapes - Added support for 3D instance normalizations #515
- Improved clarity on the resize modes TRT supports #512
- Added Changelog
- Unified docker usage between ONNX-TensorRT and TensorRT.
- Removed deprecated docker files.
- Removed deprecated
setup.py
.