Comments (7)
I do not think it matters with "lr_mult".
As far as I know, for new prototxt, it might worthwhile to check if the weights for deconvolution layers are initialized properly. If you change the name of deconvolution layer, the weights might just initialize to zero. In new code base, you can set the weight initialization for deconvolution layer, but it does not exist in the previous code base.
from crfasrnn.
@bittnt Thank you for your answer. I just want to train a new model without any restoring, and all the convolutional / deconvolutional parameters are initialized with xavier method. If "lr_mult" is non-zero, all the backward blobs become zeros. It seems strange.
from crfasrnn.
@bittnt I am sorry that I have merged your caffe version to the latest caffe before your granting and published CRFasRNN-merge. If you are not satisfy with this, I will remove the repository as soon as possible.
from crfasrnn.
I rebuild the caffe, and it works right now. I think there is some other error, not lr_mult.
from crfasrnn.
deconvolutional parameters should be initialized with bilinear weights. e.g.
layer {
name: "upsample_example"
type: "Deconvolution"
bottom: "upscore2"
top: "upscore4"
param {
lr_mult: 0
}
convolution_param{
bias_term: false
num_output: 21
kernel_size: 4
stride: 2
pad: 1
weight_filler: { type: "bilinear" }
}
}
from crfasrnn.
It is great to hear that you successfully merged the code with caffe upstream.
I have also done a version in crfrnn branch of our caffe fork.
from crfasrnn.
Wow, bilinear should be better than xavier for expanding. I will try this. Thank you
from crfasrnn.
Related Issues (20)
- Cannot align apparently disconnected blobs. HOT 1
- Dense InfogainLoss Function
- Feature extraction from CRF-RNN vs FCN8s
- CRFasRNN output vs score_final (FCN)
- Identify only small set of classes
- cuDNN compile error on Tesla K80 GPU - error: too few arguments to function
- Mean vector
- Python demo script on Ubuntu 14.04: "Check failed: *ptr host allocation of size 282240000 failed" HOT 1
- This implementation has not been tested batch size > 1 HOT 2
- Error while building the custom caffe repo HOT 1
- Performance!!!
- Training with my own data : Multiple problems arising HOT 1
- Training on Pascal VOC
- Processing multiple images in parallel
- How to select the theta_alpha, theta_beta and theta_gamma?
- AttributeError: 'dict' object has no attribute 'itervalues' in /caffe/python/caffe/pycaffe.py line 260 HOT 1
- how to change the image size? HOT 1
- prototext sample- weight initialization HOT 1
- eltwise_layer.cpp:34] Check failed: bottom[0]->shape() == bottom[i]->shape() bottom[0]: 1 21 333 500 (3496500), bottom[1]: 1 21 375 500 (3937500) HOT 2
- FCN pretrained weights on COCO data
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 crfasrnn.