Comments (7)
We might release the training code in the future. For now, please refer to https://github.com/fangchangma/sparse-to-dense.pytorch for training.
from fast-depth.
Hey @fangchangma and @dwofk,
Great job on the paper! I tried to understand how to train the network based on the information in the link above, but I didn't understand if I need to provide depth data to train the model. (Sorry if this is obvious, but I've looked through the code and was unable to figure this out.)
Thanks!
from fast-depth.
Hi @Vivkr,
If you are referring to providing sparse depth data to train the model, then no, you do not need to provide that. You can use the 'rgb' modality. The sparsifier and number of sparse depth samples become irrelevant.
Models in this project support 'RGB' input, not 'RGBd' input.
from fast-depth.
Hi @dwofk and @fangchangma ,
I'm interested if I want to train my own dataset, is it possible to use the ground truth collected by ZED camera?
Thanks!
from fast-depth.
Hi,
I just want to make sure that the detailed training for all encoder and decoder permutations is based on the spare-to-dense paper, isn't it?
To be specific:
- The loss was the berHu loss (similar to Laina et al paper)
- Data augmented ...
- Init using ImageNet-pretrained models
- Initial lr = 0.01
- Train on 20 epochs
.
.
Additionally, this is a great work. Thanks!
from fast-depth.
Hi @HarryShen19950808
Model definitions are provided here. If you have your own dataset, you can try modifying the models as necessary and retraining for your particular dataset.
from fast-depth.
Hi @HuynhLam
Yes, the training for our models is based on the sparse-to-dense work.
- no, we use L1 loss (note that the cited sparse-to-dense work also uses L1 loss)
- yes, the data augmentation is the same
- yes, encoder weights are initialized using ImageNet-pretrained models
- yes, initial lr = 0.01
- yes, we train for 20 epochs
from fast-depth.
Related Issues (20)
- module **scipy.misc** has no attribute *imresize* HOT 1
- Strange Depth Output Image HOT 3
- Why did you do the processing in this way?
- train transform
- can't decompression model
- nyuv2 data problem
- Distance Calculation
- GPU compilation error
- Why you saved the entire model instead of state_dict .. ? HOT 1
- How to train models? HOT 3
- Is there any way to solve the problem?
- Memory Error
- I have problem with using models, AssertionError: => no model found at
- Can I use Sparse-to-dense on Jetson TX2? HOT 1
- How to inference trained model on local environment(ex.window or ubuntu)
- Is NYUv2 rectified?
- Pretrained model link is broken HOT 1
- NYUv2 preprocessed data link doesn't work HOT 2
- Weights
- weird result after running "Evaluation" HOT 1
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 fast-depth.