Comments (6)
How long are your sequences ? 3frames ? 5 frames ?
from sfmlearner-pytorch.
for 3 frame long snippets, I get this output :
41866 samples found in 64 train scenes
2362 samples found in 8 valid scenes
from sfmlearner-pytorch.
3 frames...
-with-depth --with pose without static-frames
And how about Cityscapes? I have not got yet....
from sfmlearner-pytorch.
@ClementPinard and --static-frames=/the/file/you/provide/, the output is
43310 samples found in 64 train scenes
934 samples found in 8 valid scenes
from sfmlearner-pytorch.
The algorithm chooses 8 scenes at random to constitute the validation set, without looking at the number of frames in each scene, so it's competely normal to have different amount of samples.
However, the total amount of frames should be the same.
You can see that mine is not the same because I didn't use the static frames file that was originally provided by author, but the condition on car speed. (namely frame must be at the equivalent of 2 m.s apart, which means for 10fps a translation between frames of at least 20cm)
from sfmlearner-pytorch.
@ClementPinard Thanks for your detailed reply, I got it.
from sfmlearner-pytorch.
Related Issues (20)
- What happens if I use 3 or more frames? HOT 1
- train with my own video HOT 1
- what's the minimal files required to train depth only model HOT 1
- Query regarding depth map. HOT 2
- Large Errors on Pose Prediction Network HOT 3
- why the gpu memory cost of tensorflow version is larger than pytorch version HOT 2
- Weird results from pretrained model on KITTI images HOT 4
- Question about using oxts data HOT 1
- Cannot run `train.py` with nohup HOT 2
- imread during inference load the image as uint8 HOT 4
- How About the Flops, fps and parameter of this model? HOT 1
- regarding the predicted depth map during inverse warp HOT 2
- How to visualize the warped image (ref_img_wapred) HOT 2
- regarding inverse_warping HOT 10
- Is the image input of depth network fixed? HOT 2
- Question about diff
- How to load training dataset
- Regarding the depth used for generating target image HOT 5
- Question about the poses predicted by the posenet HOT 2
- about the pose scale HOT 2
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 sfmlearner-pytorch.