Comments (1)
For our foundation models, we normalize the images with ImageNet mean/std because the pre-trained encoder also normalize in this manner. As for the fine-tuned models, honestly, I did not specially take care of the mean and std. According to my experiments, both ImageNet mean/std and the 0.5
mean/std (by MiDaS and ZoeDepth) work well. The only important thing is using the same mean/std across training and inference.
from depth-anything.
Related Issues (20)
- Feature Request: Mask Support for Depth Estimation
- Whether the sky area is involved in the loss calculation? HOT 3
- Metric Depth Estimation model training HOT 1
- Train a custom unlabeled dataset on Metric depth estimation
- What are the units of depth values output by the model? HOT 1
- Training metric depth problem
- TypeError: "__init__()"miss 1 requirement positional argument:"config" HOT 2
- What is the difference between Depth-Anything and control_v11f1p_sd15_depth_fp16.safetensors?
- Want more detaile about training time and GPUs! HOT 1
- How to "not" resize image when inferencing metric depth? HOT 1
- Custom dataset training HOT 3
- How to calculate distance of the depth image ?
- How to ensure that the range of depth information obtained by the two different methods is consistent?
- mmseg::model registry error HOT 1
- train HOT 1
- How can calculate the actual depth value from the metric depth output of Depth Anything V2 ? What steps and conversions are necessary to obtain a precise and accurate depth calculation from the raw metric depth data(Depth Anything V2 output)?
- Infer relative depth
- Lfeat 损失没找到 HOT 1
- Feature alignment loss HOT 1
- Getting issue with (indoor)
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 depth-anything.