Comments (4)
@hjwdzh
I believe you should check how to train FCN network from this. For example, https://gist.github.com/shelhamer/80667189b218ad570e82
To train our network, just append the multistagemeanfield layer at the bottom of a train.prototxt:
'''
layer { type: "Deconvolution" name: 'upsample-8' bottom: 'score-fr' top: 'bigscore' param { lr_mult: 0 } convolution_param { bias_term: false num_output: 21 kernel_size: 16 stride: 8 } }
layer { type: "Split" name: 'splitting' bottom: 'bigscore' top: 'unary' top: 'Q0' }
layer { name: "inference1" type: "MultiStageMeanfield" bottom: "unary" bottom: "Q0" bottom: "datamf" top: "upscore" param { lr_mult: 10000 } param { lr_mult: 10000 } param { lr_mult: 1000 } multi_stage_meanfield_param { num_iterations: 5 compatibility_mode: POTTS threshold: 2 theta_alpha: 160 theta_beta: 3 theta_gamma: 3 spatial_filter_weight: 3 bilateral_filter_weight: 5 } }
layer { name: "loss" type: "SoftmaxWithLoss" bottom: "upscore" bottom: "label" top: "loss" loss_param { ignore_label: 255 normalize: false } include: { phase: TRAIN } }
'''
from crfasrnn.
I have a question related to learning rate inside of MultiStageMeanfield. In TVG_CRFRNN_COCO_VOC.prototxt you specify learning rates with values 0.001, 0.001 and 0.01. However, here you posted much higher learning rates 10000, 10000 and 1000. Using higher values I am able to achieve better results, however, I am still wondering which one did you use for training with base learning rate 1e-13 which is mentioned in paper.
from crfasrnn.
Glad to hear that you get better performance.
Setting up learning rate higher for this last layer , e.g. 1000 or 10000
helps to get top performance, within our end to end framework and base lr
at 1e-13.
For other purpose like that you might want to fine tune the network a bit
more within crf-rnn, in which case you can set them to 0.001 or some small
number.
On Thu, 25 Feb 2016 at 05:57, Martin Keršner [email protected]
wrote:
I have a question related to learning rate inside of MultiStageMeanfield.
In TVG_CRFRNN_COCO_VOC.prototxt you specify learning rates with values
0.001, 0.001 and 0.01. However, here you posted much higher learning rates
10000, 10000 and 1000. Using higher values I am able to achieve better
results, however, I am still wondering which one did you use for training
with base learning rate 1e-13 which is mentioned in paper.—
Reply to this email directly or view it on GitHub
#28 (comment).
from crfasrnn.
Closing old issues with no recent activity.
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.