Comments (6)
The leaky clamp operation looks like this. As you see, the problem you described does not exist.
Personally, I prefer piece-wise linear activation functions, which is why I usually use leaky ReLU or leaky clamp. Since I use leaky clamp in the output layer (instead of sigmoid), there will be negative values in the outputs, therefore BCE cannot be applied.
from im-net-pytorch.
Oh, sorry~ I just confused loss and gradient.
The gradient may be greater when the prediction is closer to 1. Emm...It seems not a big problem, right?
Thanks for your reply.
from im-net-pytorch.
When computing the gradient, you need to consider the ground truth. The gradients you showed on the figure seem to assume the ground truth is 1.
It is actually better to consider the gradient as the product of the gradient from MSE and the constant gradient (1 or 0.01) from this piece-wise linear function.
from im-net-pytorch.
Yes, you'r right. Because negative samples are much more than the positive samples, I guess the network would struggle to learn the positive samples. So I discussed about the positive samples. And I wonder whether the imbalance between positive and negative samples is the main reason for which we need train the network so long.
from im-net-pytorch.
I would consider the network structure as the main reason, i.e., the continuity/smoothness of the functions represented by MLPs.
from im-net-pytorch.
Ok. Thanks for your patient :)
from im-net-pytorch.
Related Issues (20)
- Code for latent GAN HOT 1
- Reproducing for Point Cloud to Mesh Reconstruction HOT 2
- inconsistency with AE training config and data HOT 2
- Visualizing voxel grid HOT 2
- Question on data preprocessing step HOT 4
- Issues with reconstruction / Discrepancy in metric (CD) HOT 1
- Question on Inference HOT 3
- training loss keeps increasing for SVR task HOT 2
- About test HOT 8
- About testing HOT 9
- About the original voxel models from HSP HOT 2
- the training code of training font HOT 1
- Training with the ready-to-use data HOT 2
- I can't understand some codes HOT 2
- Have you released the interpolation of 2D Letters? HOT 2
- Train imnet using other data HOT 8
- The issue of infinite loop here HOT 2
- IM-GAN for pytorch version HOT 1
- About the data preprocess 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 im-net-pytorch.