Comments (5)
This is a little weird! Are you able to train the baseline without any regularization? Caffe is relatively old, and you should consider switch to others like pytorch.
from caffe.
Yeah that's really weird. Training without regularization leads to a useful loss and a kinda good accuracy (~90%). But I honestly don't understand why one of the normal regularization methods would cause this behavior. I am currently fine tuning this baseline with SSL and see where this goes. It also started with a really high loss (e+12) and is currently working its way down (e+10).
I know that caffe is getting old but I am currently working on my bachelor thesis where I am comparing interesting sparsification methods and I think SSL is a really interesting approach based on the fact that you don't need specialized hardware to get a acceleration from it.
from caffe.
@aradar Thanks for having interest in SSL. SSL can be easily applied to the frameworks supporting autograd, such as tensorflow and pytorch. You just need to add group Lasso regularization to the cross entropy and that's it. We have an RNN code for your reference.
from caffe.
Thank you for the reference code! I will look into implementing it myself for tensorflow.
But wouldn't I also have to implement sparse convolution ops for tensorflow to also get the speedup on a normal GPU and CPU?
from caffe.
@aradar if you remove structures (such as filters and channels), then you won't have to. You will just need to create a smaller DNN with the learned structures (such as fewer filters and channels) and initialize them by non-zeros.
from caffe.
Related Issues (20)
- Training on ImageNet using ResNet-18 and not convergence. HOT 8
- One trivial modification, save my training HOT 3
- Improve efficiency for group lasso HOT 1
- how to get speedup on GPU using conv_mode: LOWERED_CCNMM HOT 2
- How to make ? HOT 1
- hi, what 'convq_layer' means in net_pruner.py and net_skipper.py? HOT 4
- I have a problem about make runtest HOT 1
- I have some problem about code HOT 3
- where to get lenet_0.9917.caffemodel.h5? bvlc_alexnet.caffemodel.h5? HOT 1
- where cifar10_full_train_test_kernel_shape.prototxt ? HOT 1
- How to see the speed up on GPU? HOT 5
- File "python/resnet_generator.py", line 21, in add_conv_layer conv_layer.bottom._values.append(bottom) AttributeError: 'google.protobuf.pyext._message.RepeatedScalarConta' object has no attribute '_values' HOT 3
- additional details on ResNet20 (low rank) HOT 4
- Getting Error While trying to convert to sparse Matrix HOT 1
- How to prune the zero-weights
- CSRMM Not Implemented yet HOT 3
- Error while converting caffemodel to HDF5 HOT 1
- SCNN can't run for the errors of compute_shape
- A pytorch re-implementation of Structured Sparsity Learning HOT 5
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 caffe.