Comments (1)
Hi,
I am trying to get familliar with the code too. I came to similar questions. I think you can find your lambda in the GradientScaler layers that implement the GRL's. They scale the gradient with a factor -0.1, which effectively results in the right gradient, at least for the FRCNN-part of the network. The DA-part has a loss of (L_img + L_ins + L_cst), without minius, and without factor lambda. I think this is desirable for the training of the adversarial (DA) part.
However, what I just said is not consistent with the rest of the code, because the L_ins has a gradient scaling factor in the GRL of -0.1, ánd a loss weight of 0.1 at the dc_loss output. I think the latter factor 0.1 is cancelled out by the learning rate multipliers in the corresponding layers in between. But anyway, when its gradient is mixed with the FRCNN loss, it thus seems to only be weighed in with a factor 0.01.
About the L_cst, I have not found any code for that in this repository. I think you will need to use the caffe2 implementation for that, see #4
from da-faster-rcnn.
Related Issues (20)
- How to download foggy image set? HOT 2
- How do you select the ROIS for unlabeled images from target domain ? HOT 1
- Details of source target setting for KITTI to Cityscapes and Cityscapes to KITTI HOT 1
- I can't download left8Img_trainvaltest_foggy.zip HOT 5
- I can't run the prepare_data.m HOT 1
- Is "need_backprop" used in the "GradientSilent" layer?
- cannot reproduce DA results from Table I in the paper HOT 2
- problem about prepare_data.m HOT 1
- question about anchor scales HOT 3
- Is there a tensorflow version about da-faster-rcnn?
- Few questions for adaptation strategy. HOT 1
- Run prepare_data.m error HOT 1
- Questions
- Experimental detail HOT 1
- what should I do if I want use 2 or more gpus?
- why target-domain pictures for training also need annotations? HOT 2
- Hi, the missing code GIO_DA
- propossal_target_layer.py HOT 1
- training problem
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 da-faster-rcnn.