Comments (4)
I cannot really answer with certainty regarding what goes wrong in your experiments, sorry. The whole setup is very different, including a re-implementation in caffe, fewer samples and the depth ground truth in log scale. All these could be possible issues.
Also the batch size sounds rather strange as this model shouldn't need that much space. I could easily fit a batch of 8 images in a 4GB GPU during training, for example.
from fcrn-depthprediction.
@iro-cp
Thanks for your reply. In the last two day, I did more experiments and got better result. As you said, using more data, or a more reliable loss function may achieve even better result.
About the memory, it's my mistake. It does not cost that much.
Thanks again.
from fcrn-depthprediction.
@xhwang @iro-cp Hi, facing the similar issue of blurred predictions while training the model(even train images output is blurred ... )
decoder- random initialisation
encoder - fcrn pre-trained weights
batchsize - 10
learning_rate - 0.005
momentum - 0.9
augmentation - same as fcrn
what did you change to get the better results.
from fcrn-depthprediction.
@Flying-Sailor Hi I am facing the same problem as you said. Have solved it?
from fcrn-depthprediction.
Related Issues (20)
- NYU Depth results link not working
- make3d
- Output upsampling to original resolution HOT 1
- Question about the evaluation method
- Could not find Implementation of its Application for SLAM??
- units for the depth map HOT 1
- Model transfer
- Can this code be used to obtain depth from kitti images? HOT 1
- training code for tensorflow
- Tensorflow model for Make3D? HOT 1
- Output of predict.py HOT 1
- Not getting good result after training HOT 2
- Got a core dumped issue
- How to make ground truth
- How should the input size be filled
- what can the depth esitimation picture do? HOT 4
- Matlab; invalid input syntax HOT 3
- Running predict.py on multiple images
- Why loss the link of .ckpt file ? HOT 1
- CKPT url not working 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 fcrn-depthprediction.