0.13.0
·
233 commits
to master
since this release
- major performance improvements by resizing net input canvases instead of tensors, which is much more performant and circumvents issue mentioned here
fixes:
- fixed post processing of 68 point face landmarks, which caused distortion of points at axes of minor dimension
breaking changes:
- removed managed flag and method from NetInput and related flag in toNetInput
- NetInput inputs are now left untouched, thus NetInput.inputs has been removed, NetInput.getInput(batchIdx) should be used instead
- NetInput and toNetInput do not accept tf.Tensor4D input with batchSize > 1 anymore, unstack batches instead and pass individual tensors as an array to create an equivalent batch input