VictorMylle/Kohya-ss-sd-scripts
1
0
Fork 1
mirror of https://github.com/kohya-ss/sd-scripts.git synced 2026-04-08 22:35:09 +00:00
Code Issues Packages Projects Releases Wiki Activity

Fix gradients synchronization for multi-GPUs training (#989)

Browse Source 
* delete DDP wrapper

* fix train_db vae and train_network

* fix train_db vae and train_network unwrap

* network grad sync

---------

Co-authored-by: Kohya S <52813779+kohya-ss@users.noreply.github.com>
This commit is contained in:
Isotr0py
2023-12-07 21:01:42 +08:00
committed by GitHub
parent 72bbaac96d
commit db84530074
10 changed files with 30 additions and 78 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
train_textual_inversion_XTI.py
View File

@@ -333,9 +333,6 @@ def train(args):
text_encoder, optimizer, train_dataloader, lr_scheduler
)
# transform DDP after prepare
text_encoder, unet = train_util.transform_if_model_is_DDP(text_encoder, unet)
index_no_updates = torch.arange(len(tokenizer)) < token_ids_XTI[0]
# print(len(index_no_updates), torch.sum(index_no_updates))
orig_embeds_params = accelerator.unwrap_model(text_encoder).get_input_embeddings().weight.data.detach().clone()