Comments (3)
It seems @deepglugs has got somewhere with his own training
https://github.com/deepglugs/dalle / there's specific helpful training instructions (requires tags / image foo.txt foo.png ) tags file format. (should be a pull request) maybe @lucidrains this is helpful?
python3 dalle.py --source path/to/images/and/tags/ \
--vocab curated_512.vocab \
--vae vae.pt \
--train_dalle \
--dalle dalle.pt \
--batch_size=16 \
--samples_out samples/dalle/ \
--epochs=2
There's a ticket related to training sets -
#7
Looking at @josephcappadona sample 50mb file - there's the following format.
1166-004-E9B61A49.jpg
1166-004-E9B61A49.txt
The basic design of Hawaii's state seal has been in use since 1894, but the legend now reads “State of Hawaii” rather than “Republic of Hawaii.” The Hawaiian coat of arms is supported by Kamehameha I and the goddess of liberty, with a rising sun behind. The motto “Ua Mau ke Ea o ka Aina i ka Pono” (The Life of the Land Is Perpetuated in Righteousness) is along the bottom edge. Below the shield are various symbols: a phoenix rising from flames, taro leaves, banana foliage, and maidenhair ferns.
I'm thinking the tag format by @deepglugs may yield better results initially on smaller datasets??
1girl, white_swimsuit, red_hair
There seems to be some guidance around vocab tokens (.vocab file) ~ 512 tags which would help things converge, right?
I'd also consider we could use an google /aws image recognition software to find tags on a large image dataset.
from dalle-pytorch.
+1
Am also confused on how to use this. Even with existing data... How do I enter input and get a visual output?
from dalle-pytorch.
@lucidrains any help on this one? Would love to get started but confused just like this other guy :)
from dalle-pytorch.
Related Issues (20)
- What is the image input for inference? HOT 1
- TypeError: forward() got an unexpected keyword argument 'mask' when training DALL-e through rainbow_dalle notebook HOT 3
- VQGanVAE resolution and channels hard coded HOT 3
- dvae training resulting in an irregular latent space
- batchsize affects the quality of reconstructed images when training dvae HOT 1
- Text transformers HOT 1
- About Openai DALL-E
- DALLE trained on FashionGen Dataset RESULTS 💯 HOT 9
- Why No Softmax?
- Pretrained text encoder HOT 2
- Anyone has problem with Discord? HOT 1
- about model
- Cant run example models in colab due to lightning error HOT 4
- Inquiry about the layout dataset link, which is mentioned in the readme
- King HOT 2
- 'NoneType' object has no attribute 'opt' Error, for testing
- Installation Problems. HOT 1
- AssertionError: torch version must be <= 1.10 in order to use OpenAI discrete vae
- Custom Dalle-2 trained decoder generating random noise HOT 1
- creacion de harina de arroz HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from dalle-pytorch.