------------------------------------------------------------------------
Release date: 2022-11-12.
`Full commit changelog <https://github.com/DeepSenseCA/echofilter/compare/1.0.2...1.1.0>`__.
.. _v1.1.0 Changed:
Changed
~~~~~~~
.. _v1.1.0 Changed Inference:
Inference
^^^^^^^^^
- Disable logit smoothing by default. The previous behaviour can be restored
by setting ``--logit-smoothing-sigma=1`` at the CLI.
(`293 <https://github.com/DeepSenseCA/echofilter/pull/293>`__)
.. _v1.1.0 Fixed:
Fixed
~~~~~
.. _v1.1.0 Fixed Inference:
Inference
^^^^^^^^^
- Fix bug where joined segments of data would have their first ping dropped.
(`272 <https://github.com/DeepSenseCA/echofilter/pull/272>`__)
.. _v1.1.0 Fixed Training:
Training
^^^^^^^^
- Make the number of channels in the first block respect the ``initial_channels`` argument.
(`271 <https://github.com/DeepSenseCA/echofilter/pull/271>`__)
.. _v1.1.0 Fixed Miscellaneous:
Miscellaneous
^^^^^^^^^^^^^
- Fix unseen internal bugs, including in ``generate_shards``.
(`283 <https://github.com/DeepSenseCA/echofilter/pull/283>`__)
.. _v1.1.0 Added:
Added
~~~~~
.. _v1.1.0 Added Inference:
Inference
^^^^^^^^^
- Add support for using a config file to provide arguments to the CLI.
(`294 <https://github.com/DeepSenseCA/echofilter/pull/294>`__)
- Add ``--continue-on-error`` argument to inference routine, which will
capture an error when processing an individual file and continue running
the rest.
(`245 <https://github.com/DeepSenseCA/echofilter/pull/245>`__)
- Break up large files into more manageable chunks of at most 1280 pings,
to reduce out-of-memory errors.
(`245 <https://github.com/DeepSenseCA/echofilter/pull/245>`__)
- Reduce GPU memory consumption during inference by moving outputs to CPU
memory sooner.
(`245 <https://github.com/DeepSenseCA/echofilter/pull/245>`__)
- Fill in missing values in the input file through 2d linear interpolation.
(`246 <https://github.com/DeepSenseCA/echofilter/pull/246>`__)
- Pad Sv data in timestamp dimension during inference to ensure the data is fully within the network's effective receptive field.
(`277 <https://github.com/DeepSenseCA/echofilter/pull/277>`__)
- Add ``--prenorm-nan-value`` and ``--postnorm-nan-value`` options to control what value NaN values in the input are mapped to.
(`274 <https://github.com/DeepSenseCA/echofilter/pull/274>`__)
- Add support for providing a single path as a string to the run_inference API.
(Note that the CLI already supported this and so is unchanged).
(`288 <https://github.com/DeepSenseCA/echofilter/pull/288>`__)
- Add more verbosity messages.
(`276 <https://github.com/DeepSenseCA/echofilter/pull/276>`__,
`278 <https://github.com/DeepSenseCA/echofilter/pull/278>`__,
`292 <https://github.com/DeepSenseCA/echofilter/pull/292>`__)
.. _v1.1.0 Added ev2csv:
ev2csv
^^^^^^
- Add ``--keep-thresholds`` option which allow for exporting Sv data with thresholds and exclusions enabled (set as they currently are in the EV file).
The default behaviour is still to export raw Sv data (disabling all thresholds).
The default file name for the CSV file depends on whether the export is of raw or thresholded data.
(`275 <https://github.com/DeepSenseCA/echofilter/pull/275>`__)
- Add ``--keep-ext`` argument to ev2csv, which allows the existing
extension on the input path to be kept preceding the new file extension.
(`242 <https://github.com/DeepSenseCA/echofilter/pull/242>`__)
.. _v1.1.0 Added Tests:
Tests
^^^^^
- Add tests which check that inference commands run, whether checking their outputs.
(`289 <https://github.com/DeepSenseCA/echofilter/pull/289>`__)
.. _v1.1.0 Added Internal:
Internal
^^^^^^^^
- Add EVR reader ``echofilter.raw.loader.evr_reader``.
(`280 <https://github.com/DeepSenseCA/echofilter/pull/280>`__)