Skip to content

Releases: juglab/FourierImageTransformer

v0.2.0

06 Apr 15:25
3f49266
Compare
Choose a tag to compare

Refactored code-base and updated jupyter examples.

v0.1.24_zero

19 Mar 13:26
3ba3041
Compare
Choose a tag to compare

This is the release with the final code version used for the manuscript.

v0.1.20

09 Mar 07:50
4a0fff1
Compare
Choose a tag to compare
  • Refactor SRes and add fast SRes prediction.
  • Change loss to use sum instead of product.
  • Add crop lodopab.

v0.1.19

01 Mar 16:04
25ec06f
Compare
Choose a tag to compare
  • Fix major bug in positional encoding
  • Add polar coordinate positional embedding

v0.1.18

05 Feb 12:35
aa6394e
Compare
Choose a tag to compare
Merge pull request #14 from juglab/merger

v0.1.18

v0.1.17

05 Feb 08:51
89dc8ec
Compare
Choose a tag to compare

Divide bin-factor by 2 instead of reducing it by 1.

v0.1.16

04 Feb 14:49
e8ef4c0
Compare
Choose a tag to compare
Merge pull request #12 from juglab/merger

v0.1.16

v0.1.10

18 Jan 19:45
6eaf6af
Compare
Choose a tag to compare

Compute amplitude-loss directly on network output i.e. do not denormalize it.

v0.1.9

17 Jan 17:06
d5a41a5
Compare
Choose a tag to compare

Add Baseline conv-block.

v0.1.8

17 Jan 17:05
Compare
Choose a tag to compare

Make first conv in conv-block have kernel size 3.