Comments (6)
These values are obtained after combining two factors:
- The flow value predicted by PWCNet is 20 times smaller than the original value.
- The stride of the layer where the flow is being used (how many times smaller the layer is, compared to the output).
So, the first value (0.625) is applied on a layer whose stride is 32. Since the flow needs to be increased by 20 times, to adapt the flow value to that layer, we need to multiply it by 20/32=0.625. The next layer has stride 16, so we use 20/16=1.25, and so on.
from pwc-net.
The stride of a layer is a scalar value which represents how many times smaller that layer is compared to the input image. For example, if the input image size was 512x512, and the current layer size is 64x64, then this layer has stride 8.
Looking at the code here https://github.com/NVlabs/PWC-Net/blob/master/PyTorch/models/PWCNet.py, we see that self.conv1x layers will have layer stride 2, self.conv2x will have layer stride 4, and so on. Following this logic, self.conv5x will have layer stride 32, so the flow value in this layer is multiplied by 0.625 as explained in my previous answer. In the next stage, we will be handling the self.conv4x features, which have layer stride 16, so we multiply the flow by 1.25.
from pwc-net.
I find that these values are multiplied by the upsampled optical flow.But I am not clear what's the meanning of these operations.Why the upsampled optical flow need to multiply corresponding float value?
I have the same question.Did you find its answer.
from pwc-net.
I'm sorry! I don't know yet. Maybe we can explore it together.
from pwc-net.
I'm sorry! I don't know yet. Maybe we can explore it together.
from pwc-net.
from pwc-net.
Related Issues (20)
- correlation-pytorch torch>=1.0 HOT 3
- Performance of pwc_net_chair.pth.tar on FlyingThings3D dataset
- How to realize the last item of loss
- Correlation - Python Implementation HOT 2
- Why mask is needed in warp function? HOT 1
- Question about large difference warping HOT 1
- forward warp
- about autoflow HOT 1
- Is there a cpu implementation of correlation module
- Disabling cost volume HOT 1
- Inference time on pytorch version HOT 6
- Running on Docker with the system requirements. HOT 1
- training data augmentations
- Optical flow for point cloud extraction
- Incorrect dimension when input image has shape `480 * 640` HOT 3
- Average EPE score with PyTorch implementation
- Trying to install dependencies using conda on Windows HOT 1
- Not Using the First Feature (c11 and c21) for the flow estimation; Upsampling not present in the shallowest flow estimation HOT 1
- CUDA error: the provided PTX was compiled with an unsupported toolchain.
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 pwc-net.