Comments (5)
Hi,
Thanks for your attention to our work.
We are planing to extend this work to journal version, and thus, the training code will be public in a near future. Besides, what's your problem encountered?
Best regards,
Ge-Peng.
from pns-net.
from pns-net.
Hi,
We use this loss function in our implementation:
class CrossEntropyLoss(nn.Module):
def __init__(self):
super(CrossEntropyLoss, self).__init__()
def forward(self, *inputs):
pred, target = tuple(inputs)
total_loss = F.binary_cross_entropy(pred.squeeze(), target.squeeze().float())
return total_loss
In my own experience, you can turn down the learning rate in the fine-tuning phase. The different tasks may incur different problems, but I think this core module could also work well in the video shadow segmentation task. Thus, you can make many attempts on tuning the hyper-parameters. If it still does not work, I recommend you can freeze or slow down the feature extraction layers.
Best regards,
Ge-Peng.
from pns-net.
from pns-net.
UR welcome. Keep in touch with me if you have any progress on it.
I will close this issue temporally.
Best regards,
Ge-Peng.
from pns-net.
Related Issues (19)
- 作者您好,问您一个问题 HOT 3
- 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
- Training Code? HOT 1
- 文件缺失 HOT 1
- Thanks for the excellent job! HOT 3
- 训练技巧和数据集的分配 HOT 1
- 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
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.