miraiaroha / acan Goto Github PK
View Code? Open in Web Editor NEWAttention-based Context Aggregation Network for Monocular Depth Estimation
License: MIT License
Attention-based Context Aggregation Network for Monocular Depth Estimation
License: MIT License
How to use the Get_Dataset.m to produce the nyu dataset? How to set the path of CLIPS_DIR? I set the path as the NYU folder path, but it doesn't work. Thanks.
Hello,in your code the α-att is setted to 0, you haven't use the attention loss to train the network?
How to choose the value of the α-att?
When i set it equals 0.1,the total loss won't decrease when i train the net. So, could you please give me some tutorial?
Can you provide a training model? thanks
Thank you for your excellent work. When I utilize your network code, I find the output's shape of your network is [batch, 80, height, width]. However, Figure 1 of your paper shows the final depth map whose shape should be [batch, 1, height, width]. As mentioned above, how do I get the final depth map? Thank you !!!
Best wishes
Thank you for your work. I'm very interested in it. But when I train with the dataset you provided, the loss is Nan or 0. What's the problem?
Holle,
It seems do not visit "kitti_path_txt" folder, its appear 404. Where can I get the KITTI dataset used for your network.
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.