Comments (2)
Thank you for submitting an issue. I looked into it, and I believe the current implementation is correct. Let me know if you feel I misunderstood your point.
The idea is that you want to predict k={1,...,K} steps into the future. Now, for skipping the first k, we add skip_step=1 to each k, resulting in k={2,...,K+1} (and thus skipping k=1). As far as I understand, your proposed solution would result in k={2,2,...,K} instead - this will lead to a smaller loss during training (since predicting smaller k's is easier), but will probably harm downstream performance.
from greedy_infomax.
Sorry, everything you have said is correct, accidental miscomprehension on my part.
Although it is curious that for the task I applied it on accidentally doing k={2,2,...,K} increased downstream classification performance. Possibly predictions too far away detract from performance, or increased weighting for closer predictions increases downstream performance. Regardless, there is no issue.
from greedy_infomax.
Related Issues (14)
- Code for Vision Experiment HOT 1
- CUDNN_STATUS_NOT_SUPPORTED error caused by non-contiguous variable HOT 1
- Same permutation for all audio samples? HOT 2
- Audio training time HOT 2
- Failure to compute gradient HOT 2
- Resnet Encoder Layer Numbers HOT 1
- Is any Guide , that i can use InfoNCE_Loss in my custom model ? HOT 3
- The following problem occurred when I was building the model following the READme.md file. Is there any problem with the function InfoNCE_Loss? HOT 1
- Question on parallel training HOT 2
- Pre-trained vision model? HOT 4
- Training time and memory usage HOT 1
- i have a problem HOT 2
- How to speed up training 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 greedy_infomax.