summaryrefslogtreecommitdiffstats
path: root/train_ti.py
Commit message (Collapse)AuthorAgeFilesLines
* UpdateVolpeon2023-01-061-24/+17
|
* Use context manager for EMA, on_train/eval hooksVolpeon2023-01-061-54/+66
|
* Add contextmanager to EMAModel to apply weights temporarilyVolpeon2023-01-061-33/+24
|
* Log EMA decayVolpeon2023-01-051-1/+2
|
* Added EMA to TIVolpeon2023-01-051-1/+58
|
* UpdateVolpeon2023-01-051-7/+7
|
* FixVolpeon2023-01-051-8/+11
|
* Various cleanupsVolpeon2023-01-051-65/+21
|
* UpdateVolpeon2023-01-041-1/+1
|
* Various updatesVolpeon2023-01-041-0/+8
|
* Better eval generatorVolpeon2023-01-041-6/+6
|
* Fixed reproducibility, more consistant validationVolpeon2023-01-041-5/+19
|
* Don't use vector_dropout by defaultVolpeon2023-01-031-1/+1
|
* Added vector dropoutVolpeon2023-01-031-5/+19
|
* Fixed LR finderVolpeon2023-01-021-3/+3
|
* UpdateVolpeon2023-01-021-3/+12
|
* FixVolpeon2023-01-021-4/+2
|
* Save args before training, tooVolpeon2023-01-021-0/+4
|
* FixVolpeon2023-01-021-2/+1
|
* UpdateVolpeon2023-01-021-6/+6
|
* Improved one cycle schedulerVolpeon2023-01-021-1/+1
|
* UpdateVolpeon2023-01-011-1/+1
|
* UpdatesVolpeon2023-01-011-26/+25
|
* Fixed accuracy calc, other improvementsVolpeon2023-01-011-3/+33
|
* UpdateVolpeon2022-12-311-0/+1
|
* Simplified multi-vector embedding codeVolpeon2022-12-311-3/+2
|
* FixesVolpeon2022-12-311-2/+1
|
* Added multi-vector embeddingsVolpeon2022-12-311-44/+44
|
* Misc improvementsVolpeon2022-12-301-29/+18
|
* Training script improvementsVolpeon2022-12-301-5/+38
|
* Training improvementsVolpeon2022-12-291-6/+15
|
* Integrated updates from diffusersVolpeon2022-12-281-8/+13
|
* Improved learning rate finderVolpeon2022-12-271-7/+3
|
* Added validation phase to learn rate finderVolpeon2022-12-271-4/+8
|
* Added learning rate finderVolpeon2022-12-271-87/+87
|
* Set default dimensions to 768; add config inheritanceVolpeon2022-12-261-6/+5
|
* Code simplifications, avoid autocastVolpeon2022-12-251-1/+7
|
* Fixed Textual InversionVolpeon2022-12-241-2/+8
|
* Training updateVolpeon2022-12-241-6/+4
|
* UpdateVolpeon2022-12-241-1/+9
|
* Better dataset prompt handlingVolpeon2022-12-231-1/+1
|
* num_class_images is now class images per train imageVolpeon2022-12-231-1/+1
|
* Improved class prompt handlingVolpeon2022-12-231-20/+9
|
* FixVolpeon2022-12-231-3/+1
|
* Fixed Textual InversionVolpeon2022-12-221-5/+7
|
* Improved Textual Inversion: Completely exclude untrained embeddings from ↵Volpeon2022-12-221-18/+6
| | | | training
* Moved common training code into separate moduleVolpeon2022-12-211-120/+55
|
* Fix trainingVolpeon2022-12-201-3/+2
|
* Fix Textual Inversion dataset filteringVolpeon2022-12-201-1/+5
|
* Improved dataset prompt handling, fixedVolpeon2022-12-191-0/+1032