Comments (3)
Hello, thanks for interests in my code.
PowerFile layer is to read some values from the file and perform the shifts to the bottom data (thetas in this case). The reason to shift the thetas is to initialize the thetas to a location at the very beginning according to some prior knowledge. For example, we hope the crop to focus on the head of the bird while another crop focus on the tail, etc.
The objective of using LocLoss layer is totally not related with the usage of PowerFile layer. LocLoss layer, as I said in the README, is designed as a loss function to make the crop not fall too far from the central location of the image space. They are totally two unrelated layers.
Sorry that I cannot find my crop_init_1.txt, but I guess it should be something like 0.5, 0 or -0.5, 0 to make the initial crops to focus on the left part and the right part on the original image.
Ask more if you are still confusing. Hope my implementation helps you with your research projects.
from spatialtransformerlayer.
Ok, I see. I wanted to use the LocLoss layer so the crop does not fall too far as you said, but the problem is that in my case it focuses too much so my net is not learning anything. I understand that there's no way to limit this minimum value (minimum threshold), am I right?
Instead of that I also tried to use the STLoss layer, but I wanted to fix some theta values, for example 2 of them to avoid rotation (in the same way that it's possible for the LocLoss layer). The problem is that the STLoss layer needs 6 input parameters, so I cannot fix 2 thetas in the SpatialTransformer layer and then set the number of outputs of the layer previous to the STLoss to 4. Is there any way? Thank you!!
from spatialtransformerlayer.
First of all, sorry that I may release too many confusing layers. They are the helper layers I added when I did the experiments. But finally when I got everything correct (learning something useful), I didn't activate any of these layers. The difficulty of training the networks with STLayer is that it's hard to fine-tune for the learning rates for the layers. Notice that finally when my trainings work out, my learning rate for the small net (localization net) is very small (like 1e-5) while the rates for other layers are much bigger (like 1e-2). So, please do not rely too much on my helper layers.
Besides, you can edit STLossLayer as your need. Sorry that I didn't do the work.
from spatialtransformerlayer.
Related Issues (20)
- How you prevent from update theta that we don't want to update HOT 1
- Update + whole caffe HOT 1
- Would you share some pretrained model for transfer learning? HOT 1
- How to chose the threshold for LocLoss? HOT 6
- Gradient test case may fail in GPU single precision mode HOT 4
- Bug (?) when normalising coordinates HOT 2
- .caffemodel for initialisation HOT 3
- PowerFile error! HOT 2
- Rotation
- Play with the theta parameters? HOT 1
- Add the stn after the data layer . HOT 2
- ST layer scales down input and produces wrong output during random iterations HOT 3
- Weight initialized from the Inception pretrained on ImageNet HOT 1
- What does this layer mean?
- Why the results is worse than the paper's? HOT 7
- CUB_200_2011 result? HOT 1
- how to use STN layer directly after imagedata layer for CUB
- dtheta update issue? transforming dtheta for getting theta? HOT 1
- cannot understand the initialization method of "output_grid" in st_layer.cpp 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 spatialtransformerlayer.