Added error trap if attempting to use a non-contiguous NumPy array to copy tensors off the device.
Added support for negative axes to the
Added support for steps > 1 and steps < -1 to the
Added support to the
Resizeop for both scales and sizes inputs (one of the two tensors is empty).
Added float16 support to
Added support for custom transforms (experimental).
Fixed potential hang in device detach.
Load Poplar executable files lazily if they are named with a hash.
popart::PopOpxclass has been marked as deprecated. Please change your custom ops to inherit from
popart::PopOpxclass will likely be removed in the next release.
Add support for scatterreduce with max and min reductions providing additional operation coverage.
Support Nesterov momentum for SGD providing additional optimiser functionality.
Add multi reducescatter and allgather to support merged collectives.
For more details refer to
Add batchnorm with unbiased variance for PopTorch.
Merge PopART User Guide and API documentation documentation.
Improvements to PopART User Guide including sections for:
converting ONNX models
Improvements to printing tensors. The output of C++
PrintTensorOpor Python printtensor is automatically summarized and aligned, making it easier to read. New formatting options have also been added to allow configuration of the output.