Comments (2)
Hi, many thanks for your interest in our work!
-
As we haven't run such an experiment, I'm not sure if it's OK to only finetune the replicated network layers. Intuitively, I think we should at least finetune some of the shared backbone layers. Otherwise, the intermediate features can not be updated to simultaneously output aligned RGB, depth, and normal.
-
There are certain ways to decrease the computational cost for your information. For example, a) change into a smaller backbone to trade-off the performance and memory cost, e.g., Small SD and Tiny SD. b) Use the efficient parameter finetuning techniques like LoRA, or just finetune some certain layers in the shared backbone. c) common engineering tricks to reduce memory consumption as used in diffusers, e.g., gradient checkpointing, gradient accumulation w/ smaller batch size, deepspeed model parallelism, lower fp precision like fp16, efficient_xformers, etc.
Best
from hyperhuman.
Thanks a lot for your comments.
from hyperhuman.
Related Issues (11)
- Thanks for the great work! Will the training dataset or the sub one be open source? HOT 3
- Will the MSCOCO 2014 Human Validation set be released soon?
- skeleton pose
- Will there be opensource code? HOT 4
- Why body skeleton is required as input for the first stage structure model? HOT 3
- Questions with "Replicate" Layers HOT 7
- Question about depth map HOT 2
- Will there be opensource code?
- There is something confusing in section 3.3 about the network archetectrue?
- Why not use openpose-style skeleton.
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 hyperhuman.