allevitan
d8fade9f32
Update the amplitude MSE and intensity MSE loss to act equivalently - currently, the intensity MSE loss was by default a mean, but amplitude was by default a sum. Both functions now have a flag, use_sum=False, which is False by default. This changes the default behavior of amplitude_mse. All models, including the tutorial version of simple_ptycho, are updated accordingly and test coverage was added.
2026-04-13 14:34:23 +02:00
allevitan and Claude Sonnet 4.6
d644782e94
Update poisson_nll test to match sum-based implementation
...
poisson_nll now returns a sum rather than a mean, consistent with the
normalizer pattern. Remove the per-pixel divisions from the numpy
reference calculations accordingly.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com >
2026-04-03 18:44:04 +02:00
gnzng
65e83753a8
linting test_interactions.py, test_losses.py, and test_measurements.py
2025-07-07 14:58:11 -07:00
Abe Levitan
883ac0175a
Changed module name no lowercase because that's really how it should be
2022-06-08 12:52:33 -07:00
Abe Levitan
3e6072acb7
Finally remove the scourge of from __future__ import ... and remove any lingering suggestion that this code is python 2 compatible
2021-08-05 11:08:13 -04:00
Abe Levitan
e7d7323e50
Added a polarization dependent ptychography dataset class so we can save and load data!
2021-07-26 14:46:02 -04:00
Abe Levitan
c2b8f2fe1b
Bring all the tools to the point where they pass the tests
2021-06-18 14:01:39 -04:00
Abe Levitan
a3765e9097
remove all reference to cmath, get code and tests to the point where they run at least.
2021-06-17 16:47:24 -04:00
Abe Levitan
32a8a8179d
Fix an issue with the test for the poisson NLL function
2020-12-28 21:45:01 -05:00
Abe Levitan
69be77cc09
Update installation instructions for simplicity and also fix the tests to reflect new usage
2019-10-02 15:56:48 -04:00
Abe Levitan
f08a77d6da
Finish the tests for the losses
2019-03-22 22:33:52 -04:00
Abe Levitan
595e84cd01
Start putting together the losses
2019-03-22 19:59:40 -04:00
allevitan