aljaz/DALLE2-pytorch
1
1
Fork 0
mirror of https://github.com/lucidrains/DALLE2-pytorch.git synced 2025-12-20 18:24:19 +01:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #37 from ProGamerGov/patch-1

Browse Source 
Fix spelling and grammatical errors
This commit is contained in:
Phil Wang
2022-04-30 08:19:07 -07:00
committed by GitHub
parent 20e7eb5a9b 63450b466d
commit 721a444686
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
README.md
View File

@@ -47,7 +47,7 @@ clip = CLIP(
use_all_token_embeds = True, # whether to use fine-grained contrastive learning (FILIP) use_all_token_embeds = True, # whether to use fine-grained contrastive learning (FILIP)
decoupled_contrastive_learning = True, # use decoupled contrastive learning (DCL) objective function, removing positive pairs from the denominator of the InfoNCE loss (CLOOB + DCL) decoupled_contrastive_learning = True, # use decoupled contrastive learning (DCL) objective function, removing positive pairs from the denominator of the InfoNCE loss (CLOOB + DCL)
extra_latent_projection = True, # whether to use separate projections for text-to-image vs image-to-text comparisons (CLOOB) extra_latent_projection = True, # whether to use separate projections for text-to-image vs image-to-text comparisons (CLOOB)
use_visual_ssl = True, # whether to do self supervised learning on iages use_visual_ssl = True, # whether to do self supervised learning on images
visual_ssl_type = 'simclr', # can be either 'simclr' or 'simsiam', depending on using DeCLIP or SLIP visual_ssl_type = 'simclr', # can be either 'simclr' or 'simsiam', depending on using DeCLIP or SLIP
use_mlm = False, # use masked language learning (MLM) on text (DeCLIP) use_mlm = False, # use masked language learning (MLM) on text (DeCLIP)
text_ssl_loss_weight = 0.05, # weight for text MLM loss text_ssl_loss_weight = 0.05, # weight for text MLM loss
@@ -616,7 +616,7 @@ clip = CLIP(
# 3 unets for the decoder (a la cascading DDPM) # 3 unets for the decoder (a la cascading DDPM)
# first two unets are doing latent diffusion # first two unets are doing latent diffusion
# vqgan-vae must be trained before hand # vqgan-vae must be trained beforehand
vae1 = VQGanVAE( vae1 = VQGanVAE(
dim = 32, dim = 32,