GitLab

Add a second expected_loss_weights function using an alternative expectation calculation compared to previous. Integrate this op into ssd_meta_arch and losses builder. Affects files that use losses_builder.build to handle the returning of an additional element.

PiperOrigin-RevId: 219190083

PiperOrigin-RevId: 218599670

PiperOrigin-RevId: 214714611

PiperOrigin-RevId: 213873057

PiperOrigin-RevId: 211907984

PiperOrigin-RevId: 207936241

Refactor ssd_meta_arch so that the target assigner instance is passed into the SSDMetaArch constructor rather than constructed inside.

PiperOrigin-RevId: 207787053

PiperOrigin-RevId: 217341274

PiperOrigin-RevId: 215014489

Add AstroWaveNet model, a generative model of astronomical light curves. AstroWaveNet's hidden states can be used in a semi-supervised fashion for downstream tasks like finding exoplanets.

PiperOrigin-RevId: 214073725

PiperOrigin-RevId: 214069349

PiperOrigin-RevId: 213963765

PiperOrigin-RevId: 213353962

PiperOrigin-RevId: 212909744

Factor out evaluate(), continuous_eval(), and continuous_train_and_eval() from estimator_util.py into estimator_runner.py.

PiperOrigin-RevId: 212903406

PiperOrigin-RevId: 211832751

1. reshard_arrays(xs, ys): Reshards arrays in xs to match the lengths of arrays in ys.
2. uniform_cadence_light_curve(): Combines data into a single light curve with uniform cadence numbers.

PiperOrigin-RevId: 211724321

Remove the constant LONG_CADENCE_TIME_DELTA_DAYS as this is not strictly constant between light curves (although it is very close).

PiperOrigin-RevId: 211153560

This applies mainly to scrambled data (NaN time values typically come with NaN flux values, which are removed anyway, but scrambing decouples NaN time values from NaN flux values).

PiperOrigin-RevId: 209029696

Update configurations with label mapping for simulated data and new batch_size and learning_rate from vizier studies.

PiperOrigin-RevId: 208902383

PiperOrigin-RevId: 208863882

PiperOrigin-RevId: 208862798

Ensure consistent argument order, change NaN processing to remove NaN times as well, and do so before scrambling

PiperOrigin-RevId: 207804986

Modify processing pipeline to enable generation of scrambled lightcurves. Fix bugs to enable generation of inverted lightcurves.

PiperOrigin-RevId: 207595688

Inversion should be done *after* fitting a normalization curve to the stellar variability and dividing it away. Doing it before normalizing may result in unintentionally reversing the inversion. Therefore we remove the option to do it at this point.

PiperOrigin-RevId: 207309650

PiperOrigin-RevId: 205427760

PiperOrigin-RevId: 205168785

fixed bug and introduced python3 compatability

Open source checkpoints for mobilenetv2_dm05_coco_voc_trainaug and mobilenetv2_dm05_coco_voc_trainval

Open-sourcing the checkpoint so that users could reproduce our PASCAL VOC 2012 validation set result when training on train_aug set.

PiperOrigin-RevId: 215004158

* Merged commit includes the following changes:
213899768  by Sergio Guadarrama:

    Fixes #3819.

--
213493831  by Sergio Guadarrama:

    Internal change

212057654  by Sergio Guadarrama:

    Internal change

210747685  by Sergio Guadarrama:

    For FPN, when use_depthwise is set to true, use slightly modified mobilenet v1 config.

--
210128931  by Sergio Guadarrama:

    Allow user-defined current_step in NASNet.

--
209092664  by Sergio Guadarrama:

    Add quantized fine-tuning / training / eval and export to slim image classifier binaries.

--
207651347  by Sergio Guadarrama:

    Update mobilenet v1 docs to include revised tflite models.

--
207165245  by Sergio Guadarrama:

    Internal change

207095064  by Sergio Guadarrama:

    Internal change

PiperOrigin-RevId: 213899768

* Update model_lib.py to fix eval_spec name issue.