levita_a
3252a0dd8f
Update SGD to allow per-parameter learning rates and add test coverage
2026-07-23 15:00:33 +02:00
levita_a
fcd0b31b2c
Fix a bug with the mask implementation for the normalizers conflicting with SimplePtycho, and update the thresholds to accomodate the new normalization with masks and for intensity_MSE
2026-04-13 15:44:52 +02:00
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
levita_a
3d10f36739
Fix a bug where the normalizers stopped the loss history from being saved as a numpy scalar, and added test coverage
2026-04-05 22:23:23 +02:00
allevitan and Claude Sonnet 4.6
3ccdc24d3f
Restructure loss coverage in reconstruction tests
...
- Revert test_Adam_gold_balls to default amplitude_mse
- Add new test_intensity_MSE test (gold balls + AdamReconstructor)
- Update near_field threshold to 17 (poisson_nll scale)
Thresholds for test_intensity_MSE to be tuned after GPU run.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com >
2026-04-03 18:46:27 +02:00
allevitan and Claude Sonnet 4.6
178e9a4e4e
Add loss function coverage to slow reconstruction tests
...
Use poisson_nll in test_near_field_ptycho and intensity_mse in
test_Adam_gold_balls to exercise these loss paths end-to-end.
Thresholds left as-is pending re-running on a GPU machine.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com >
2026-04-03 18:45:29 +02:00
levita_a
d2c09acd44
Get all tests passing by updating the loss thresholds for the new normalizations, and add the new normalization to all models
2026-04-03 18:38:11 +02:00
allevitan
ad2b09f2f0
Update the tests to work better when checking the model plotting, and make sure to cover panel_plot_mode=False
2026-03-24 16:19:26 +01:00
levita_a
7d39015719
response to dayne's review
2025-10-17 23:41:08 +02:00
levita_a
f022b5e2c4
Get the tests passing again after the change of the optimization functions in the model classes
2025-10-16 15:58:28 +02:00
yoshikisd
82ce845385
Changed the names of the reconstructors and updated the old optimizer class documentation
2025-08-04 16:51:24 +00:00
yoshikisd
1e7fe2eb5f
Added pytests for reconstructors
2025-08-01 22:31:40 +00:00
levita_a
allevitan