Comments (4)
Actually, I think this is caused by that input X(t) have more information than h(t-1), c(t-1), thus the model tend to forecast a similar image with X(t) (i.e., true image of previous timestep). When we turn train mode to inference mode, the forecasting steps doesn't have corresponding true images from previous timesteps, thus they tend to forecast a similar images as prediction image of previous timestep. [This is define as difficulty in learning long-term dynamic problem in your paper].
Can you give me some suggestion?
Thanks!
from predrnn-pytorch.
Hi, thanks for your interest.
(1) I think your case is quite difficult for prediction since the inputs show an accumulation trend (right-top) while the future tends to dissipate.
(2) To emphasis the motion, I think predicting the change between two adjacent frames might be helpful, that is X_{t}-X_{t-1}
.
(3) Since this problem is quite challenging, maybe you can change the schedule sampling strategy as the input mask start from a high value, such as 0.8. This will not bring too much difficulty for prediction and still force the model to learn the long-term dependecies.
from predrnn-pytorch.
Thanks for your insightful suggestion!
from predrnn-pytorch.
Hello, I'm facing the same problem (I'm using meteorological images), but I could not understand exactly which parameters to change.
I'm using the "moving mnist" predrnn_v2_mnist_train.sh as starting point, can you give me some hints on which parameters to change (and which values)?
Thank you!
from predrnn-pytorch.
Related Issues (20)
- The traffic4cast model
- Inconsistent dataset of Moving_MNIST in the paper and code? HOT 1
- Whether the Moving_MNIST dataset volume in PredRNN++ is the same as the code repo? HOT 3
- What's the validation dataset for KTH_action, TaxiBJ, and Human3.6M? HOT 2
- Random output images HOT 2
- misconfigured parameter `num_action_ch` for `action_cond_predrnn_v2` HOT 2
- when i use CIKM_predrnn.py ,it run wrong HOT 1
- Guidance for custom dataset HOT 1
- Pretrained model-Unexpected key HOT 1
- Generate a new Moving-MNIST dataset HOT 1
- Generate new Mnist dataset HOT 3
- Radar echo dataset HOT 3
- FileNotFoundError: [Errno 2] No such file or directory HOT 2
- radar echo dataset HOT 1
- Kth dataset: inf error HOT 2
- link of pretrained models from Tsinghua Cloud need to update
- A list of dependencies
- Problem with hidden layers HOT 1
- Why is MSE calculated with "sum" instead of "mean"? HOT 1
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 predrnn-pytorch.