Comments (6)
- It depends on your training splits/datasets. You should follow the data preprocessing guide, then specify the dataset_dir as the formatted data;
- In the first stage (train_rigid mode), your saved model should include both depthnet & posenet. Thus you only need to specify one ckpt.
from geonet.
- Does formatted data contain both datasets under directory and main.py understand which one is depth and pose?
from geonet.
I'm not sure what you mean. The dataset simply contains image sequences and intrinsic matrices. The depth and pose should be trained in a joint way on the same formatted dataset.
from geonet.
So, you are saying that I can choose depth or pose(single one is enough) for training at first stage? If not, how to deal with the train.txt and val.txt comes from both of them?
Then, train in train flow mode with only flow formatted data?
The best explanation would be giving abstract directory sample though, by giving random directory names.
from geonet.
As described in the paper, for different tasks we have different training/test splits, which is handled by our data preparation script data/prepare_train_data.py.
For instance, if we want to replicate the flow result, we should prepare the data according to kitti_raw_stereo
split. Then all our experiments should be conducted on the same formatted dataset. As a result, the trained model should be evaluated only for the flow task.
You could read the experiment part of our paper more thoroughly for details.
from geonet.
Thanks a lot. I could not get the logic from paper, it is very clear now.
from geonet.
Related Issues (20)
- Flag add_flownet not recognized by Tensorflow HOT 1
- Output problem HOT 5
- training problem HOT 1
- How to use optical flow model to test my videos? HOT 1
- Error while camera pose testing HOT 11
- Version of GeoNet HOT 2
- pretrained model problems HOT 1
- about flow_test. HOT 1
- Creating ORB-SLAM (full) snippets HOT 4
- Hello, author. Some problems about generating training model.
- Upgrading tf.contrib.slim to tf 2.0 HOT 2
- How to get depth ground-truth HOT 3
- Loss and training of the Rigid Structure Reconstructor HOT 3
- About FLOPs and parameters HOT 1
- No response in training process HOT 4
- ckpt file problem HOT 2
- How are target and source frames selected? HOT 1
- Draw trajectory HOT 1
- Could you provide the fps of your model?
- is:issue is:open How do I view the loss curve and why there is no loss output?thanks.
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 geonet.