Comments (3)
Hi @JiamingSuen ,
thanks for checking out our training code!
-
At the moment we use the hyperparameters as in the training code.
There is probably a lot of room for improving these parameters.
The losses will eventually converge if you train for a very long time, but it does not improve the testing performance. -
v2 is an attempt to create a version of our network that can be trained easily with tensorflow.
It is meant as a basis for future experiments to improve the architecture.
First steps towards a better architecture are already inblocks.py
.
We share it because we hope it will be useful to other researchers. -
As you probably have noticed, the training procedure is quite complex and the training losses can be difficult to understand on first glance.
One important remaining task is to provide easy to use evaluation code to better assess the network performance.
Thanks for this amazing work!
Thank you!
from demon.
Thanks for the reply. I tried to initialize weights with tf.contrib.layers.variance_scaling_initializer(factor=2.0)
, which is the "MSRA-initialization" described in this paper, while it's not helping a lot.
- What initialization did you use in the original Caffe implementation?
- Is it because the input data is quite noisy? I'm thinking about adding batch normalization layer, do you think it's a good idea? Or just start the training with synthetic dataset..
Will keep update my progress here.
from demon.
Asking myself the same thing ... thought Totalloss should go down after a while.
But it does not really look good (+160k iterations) :
https://tensorboard.dev/experiment/aay2ZG8aRUaZM1EwML3jPA/#scalars&run=0_flow1%2Ftrainlogs&_smoothingWeight=0.989
Edit:
Guess i would need a total loss that does not include the *_sig (and instead include the *_sig_unscaled losses) to have a nice looking graph.
Atleast i now understand why total loss does not decrease much while training itself actually does improve.
from demon.
Related Issues (20)
- AttributeError: module 'lmbspecialops' has no attribute 'leaky_relu' HOT 2
- Train error (different shapes) HOT 2
- lmbspecialops make error HOT 5
- Not loading created datasets HOT 1
- Cant install 'minieigen' HOT 2
- make error tensorflow/correlation/op.h
- create dataset HOT 1
- question about training datasets
- undefined symbol: _ZN10tensorflow7strings6StrCatERKNS0_8AlphaNumES3_S3_S3_ HOT 2
- make error:has no member named ‘starts_with’ HOT 2
- documentation for generating "depthTSDF" folder
- Error importing lmbspecialops HOT 1
- Sample for google colab notebook HOT 1
- Bad accuracy at black/white images HOT 2
- Performance issues in the program HOT 1
- Performance issues in /examples/evaluation.py (by P3) HOT 1
- scaleinvariantgradient_cuda.cu - cannot compile
- the minus values depth map gt
- pytorch implementation
- Scenes11 dataset
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 demon.