Comments (2)
Hi, thanks for appreciating our work!
For metric fine-tuning, We use 4 NVIDIA A100 GPUs for training our largest model (BEiT-L). Training time on NYU (~25k samples, 5 epochs) on 4 A100s (40GB) is less than 2 hours.
Relative pre-training on 12 datasets (M12 from the paper) takes around 3-5 days on 8 RTX A6000-like GPUs. This gives us the MiDaS v3.1 models. Please refer to midas repo for more details.
from zoedepth.
Brilliant, thanks for the quick response. It's great to hear that the training time is quick.
I'll create another issue if I have any more questions, but this is resolved, so I'm closing the issue.
from zoedepth.
Related Issues (20)
- ZoeDepth model related questions HOT 2
- Changing models
- how to export as onnx file? HOT 1
- Depth Map to Metric Depth Values
- max_depth in config_zoedepth_nk.json
- how 2 get actual distance under zoom conditions HOT 1
- Hello ZoeDepth what video card or processor are you using?
- Hello ZoeDepth it won't start for me I have it on my PC Intel(R) Core(TM) i5-10400 NVIDIA GeForce GTX 1060
- Questions about kitti_eigen_train_files_with_gt.txt HOT 1
- save depth maps first, and then validate metrics on NYUv2, got rmse of 0.375, but rmse in paper is 0.27 HOT 1
- problem with wanb: api_key not configured HOT 2
- NYU test set download HOT 1
- RuntimeError: PytorchStreamReader failed reading zip archive: failed finding central directory
- setup.py requirement HOT 1
- Changing relative depth estimation model
- run with video
- IndexError: too many indices for tensor of dimension 4
- Getting RuntimeError: Error(s) in loading state_dict for ZoeDepth: HOT 11
- A question about the Demo
- Quick question about modifying the loss function
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 zoedepth.