Comments (1)
Since the GT of validation set is not public, we have to submit the .json file of validation set to the official web of Codelab to test the performance of models. It is very inconvenient. We, therefore, divide the train set of train.json into train_sub.json (top nine tenths) and valid_sub.json (the last tenth), hoping to make it more convenient to verify some ideas.
But for all reported results, we keep same settings with other methods. We train STMask on all train set after 12 epochs for YT and 20 epochs for OVIS. Because the more data, the better the result.
from stmask.
Related Issues (9)
- NameError: name 'spatial_correlation_sample' is not defined HOT 1
- How to evaluate the results? HOT 5
- g++ 's error HOT 2
- Error from Youtube 2019 Evaluation HOT 4
- Confuse about batchsize and total iterations HOT 3
- RuntimeError: CUDA error: invalid device function 段错误 (核心已转储)
- weights link HOT 1
- After pip install spatial-correlation-sampler , run train.py error!!
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 stmask.