Comments (3)
Normalization can sometimes be problematic for regression tasks like optical flow, which is why normalization is not included in the GRU updates.
Instance normalization in the feature encoder makes the network more robust to domain changes (ie cross dataset generalization) because normalizing across the spatial dimensions reduces appearance changes. I didn't find the type of normalization used in the context encoder to be that important, I found batch norm can be removed without hurting performance.
from raft.
I also have similar questions.
I noticed that you used instance norm, which is popular used in style transfer. Is it according to experiment result or some theories ?
Also, you multiplied 8 in unfold in raft.py, why ?
up_flow = F.unfold(8 * flow, [3,3], padding=1)
I really appreciate you talking about them.
from raft.
Hi, the optical flow magnitude should be scaled up according to the upsampling factor. Here, the flow is upsampled by three pyramids, so 2**3 = 8.
About BatchNorm, I am also interested in the author's explaination. In my experience, PWCNet and some other monodepth works also do not have BatchNorm layers. I guess since the output distribution is not "gaussian", BatchNorm is not needed?
from raft.
Related Issues (20)
- Google authenticator installation
- SmartVectors / stmaps
- load image problem
- RuntimeError: GET was unable to find an engine to execute this computation HOT 2
- Raft Optical Flow does not look correct HOT 1
- How to finetune pretrained mdoel on custom dataset to predict relative transformation of poses?
- wget doesn't work for me HOT 2
- Flow initialization question
- CUDA 11 support for RTX 3080/3090
- IndexError: list index out of range
- ModuleNotFoundError: No module named 'utils.utils' HOT 2
- Relationship between Real Image size and Crop Size parameter?
- `augmentor.resize_sparse_flow_map` does not work for non-sparse flow-maps
- can not create environment
- Error when running on 2 GPUs
- RuntimeError: CUDA out of memory HOT 3
- How to train my own dataset HOT 5
- How to calc optical flow score
- About Applications
- which is better ? raft or deepflow/dis ?
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 raft.