aljaz/DALLE2-pytorch
1
1
Fork 0
mirror of https://github.com/lucidrains/DALLE2-pytorch.git synced 2025-12-22 19:14:20 +01:00
Code Issues Packages Projects Releases Wiki Activity

Improved upsampler training (#181)

Browse Source 
Sampling is now possible without the first decoder unet

Non-training unets are deleted in the decoder trainer since they are never used and it is harder merge the models is they have keys in this state dict

Fixed a mistake where clip was not re-added after saving
This commit is contained in:
Aidan Dempster
2022-07-19 22:07:50 -04:00
committed by GitHub
parent 4b912a38c6
commit 4145474bab
6 changed files with 104 additions and 49 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
dalle2_pytorch/train_configs.py
View File

@@ -306,9 +306,11 @@ class DecoderTrainConfig(BaseModel):
max_grad_norm: SingularOrIterable(float) = 0.5
save_every_n_samples: int = 100000
n_sample_images: int = 6 # The number of example images to produce when sampling the train and test dataset
cond_scale: Union[float, List[float]] = 1.0
device: str = 'cuda:0'
epoch_samples: int = None # Limits the number of samples per epoch. None means no limit. Required if resample_train is true as otherwise the number of samples per epoch is infinite.
validation_samples: int = None # Same as above but for validation.
save_immediately: bool = False
use_ema: bool = True
ema_beta: float = 0.999
amp: bool = False