Comments (3)
Hi, yes this is normal. The losses are not averaged by tensor size, and that's why the large numbers. Also this is the reason that we use a very small learning rate.
from osvos-pytorch.
Thank you very much for your reply. I still have two questions:
- In the case of a large loss, how should I judge that the model has completed network training,since I don't know if the loss of the model has converged. How many epoch should I train?
- Will you post code with instance segmentation(combine with the mask rcnn)?
Looking forward to your reply, thank you again!
from osvos-pytorch.
Hello,
To answer your questions:
-
For the parent network, we did not optimize on the training iterations. For online training, once the training loss does not decrease, you could stop training. We found out that approx. 2000 iterations are optimal for a sequence of DAVIS.
-
We are planning to, but this requires merging with the new Mask RCNN PyTorch version and re-running all experiments, so it will take some time before we release it. Sorry.
from osvos-pytorch.
Related Issues (20)
- Code HOT 1
- class_balanced_cross_entropy_loss HOT 1
- Confused by " inputs.requires_grad_()" HOT 3
- online training HOT 1
- Implement three measures HOT 3
- Why total iterations are different to them in the paper? HOT 1
- official measure code HOT 7
- How to add Mask Input? HOT 1
- Can you deliver a pretrain .pth model file of the final model HOT 1
- i can't find where you use finetuning on first frame in your code-pytorch HOT 5
- can you help me, how to use this code on Davis 2017 HOT 2
- train_online RuntimeError HOT 1
- The code of contour snap HOT 1
- Optimizer learning rates HOT 1
- Question about evaluation result HOT 1
- an error occurred when running train_parent.py HOT 6
- How to Evaluate the model? HOT 1
- Can it be used in images? HOT 1
- Emergency!
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 osvos-pytorch.