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

2
library/sdxl_train_util.py
View File

@@ -51,8 +51,6 @@ def load_target_model(args, accelerator, model_version: str, weight_dtype):
torch.cuda.empty_cache()
accelerator.wait_for_everyone()
text_encoder1, text_encoder2, unet = train_util.transform_models_if_DDP([text_encoder1, text_encoder2, unet])
return load_stable_diffusion_format, text_encoder1, text_encoder2, vae, unet, logit_scale, ckpt_info

13
library/train_util.py
View File

@@ -3914,17 +3914,6 @@ def _load_target_model(args: argparse.Namespace, weight_dtype, device="cpu", une
return text_encoder, vae, unet, load_stable_diffusion_format
# TODO remove this function in the future
def transform_if_model_is_DDP(text_encoder, unet, network=None):
# Transform text_encoder, unet and network from DistributedDataParallel
return (model.module if type(model) == DDP else model for model in [text_encoder, unet, network] if model is not None)
def transform_models_if_DDP(models):
# Transform text_encoder, unet and network from DistributedDataParallel
return [model.module if type(model) == DDP else model for model in models if model is not None]
def load_target_model(args, weight_dtype, accelerator, unet_use_linear_projection_in_v2=False):
# load models for each process
for pi in range(accelerator.state.num_processes):
@@ -3948,8 +3937,6 @@ def load_target_model(args, weight_dtype, accelerator, unet_use_linear_projectio
torch.cuda.empty_cache()
accelerator.wait_for_everyone()
text_encoder, unet = transform_if_model_is_DDP(text_encoder, unet)
return text_encoder, vae, unet, load_stable_diffusion_format