Comments (1)
@forestlin7
感谢您的关注
IVPS-TrainSet代表的是Image和Video数据集混合后的数据集,用于预训练阶段。由于Video数据和标注的获取往往需要很高的代价,这个阶段在VOS领域中同样应用广泛且是必要的,有助于提升网络学习到更多的视觉信息表征,防止网络的过拟合。
整个参数更新过程中需要保证测试集合是unseen的就可以了,数据集层面我们没有过多的处理,除了数据增强以外:
trsf_main = Compose_imglabel([
Resize(config.size[0], config.size[1]),
Random_crop_Resize(15),
Random_horizontal_flip(0.5),
toTensor(),
Normalize(statistics["mean"], statistics["std"])
])
注意:两个步骤需要紧密配合,预训练阶段需要训练直至收敛,视频数据集微调阶段也是如此。
祝好!
from pns-net.
Related Issues (19)
- 作者您好,问您一个问题 HOT 3
- Training Code? HOT 1
- 文件缺失 HOT 1
- Thanks for the excellent job! HOT 3
- Could you provide the training file? HOT 5
- 缺少文件 HOT 2
- 想问一下怎么提高代码cuda使用版本 HOT 6
- 从头训练没有达到论文中的精度 HOT 12
- ModuleNotFoundError: No module named 'self_cuda_backend' HOT 4
- ModuleNotFoundError: No module named 'self_cuda_backend' HOT 1
- Some questions about the NL module HOT 3
- 无法复现论文精度 HOT 5
- 训练技巧提问 HOT 2
- 提示缺少cuda.h如何解决 HOT 3
- Training problem HOT 1
- 关于训练模型的问题 HOT 11
- 数据集已经失效了 HOT 1
- 执行setup.py报错问题 HOT 5
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 pns-net.