Comments (11)
Sorry for the late reply.
CondenseNet^{light} refers to the network that simply applies learned group convolution to the original DenseNet network, and CondenseNet further introduces two architecture changes: full dense connection and increasing growth rate. The legend of Figure 6 in the paper explains these in a more intuitive way.
For the network configurations, CondenseNet^{light} always has 3x2xN+4
layers, where N is the number of densenet layers (one 1x1 conv plus on 3x3 conv), 3 corresponds to the three dense blocks, and 2 corresponds to the 2 conv layers in each densenet layer. The number 4 counts the very first conv layer, the two transition layers, and the final FC layer. CondenseNet always has 3x2xN+2
layers, because it does not have the two transition layers. The growth rate for these networks are set differently, such that the resulting network has comparable parameters or flops as some of the baseline networks. I paste the command lines to reproduce the reported results below (please correct me if I'm wrong @ShichenLiu ):
CondenseNet-86
python main.py --model condensenet -b 64 -j 2 cifar10 --epochs 300 --stages 14-14-14 --growth 8-16-32
CondenseNet-182*
python main.py --model condensenet -b 64 -j 2 cifar10 --epochs 600 --stages 30-30-30 --growth 12-24-48
CondenseNet-light-94
python main.py --model densenet -b 64 -j 2 cifar10 --epochs 300 --stages 15-15-15 --growth 16-16-16
CondenseNet-light-160*
python main.py --model densenet -b 64 -j 2 cifar10 --epochs 600 --stages 26-26-26 --growth 32-32-32
from condensenet.
Sorry for the late reply. The command that could reproduce the results are:
CondenseNet-86
python main.py --model condensenet -b 64 -j 2 cifar10 --epochs 300 --stages 14-14-14 --growth 8-16-32
CondenseNet-182*
python main.py --model condensenet -b 64 -j 2 cifar10 --epochs 600 --stages 30-30-30 --growth 12-24-48
CondenseNet-light-94
python main.py --model densenet_LGC -b 64 -j 2 cifar10 --epochs 300 --stages 15-15-15 --growth 16-16-16
CondenseNet-light-160*
python main.py --model densenet_LGC -b 64 -j 2 cifar10 --epochs 600 --stages 26-26-26 --growth 32-32-32
from condensenet.
@ShichenLiu : Thanks for your great work. would you please have a look here and help us with the architectures? its greatly appreciated
from condensenet.
@gaohuang and @ShichenLiu : Thank you very much, guys. its really appreciated ;)
from condensenet.
Hi, @ShichenLiu did you set group-lasso-lambda to 1e-5 on cifar100 dataset
the paper noted group-lasso-lambda=1e-5 on ImageNet Dataset
the default value for the parameter is 0.
Looking forward to your reply
from condensenet.
Hi,
The group-lasso-lambda makes no conspicuous difference on CIFAR dataset. However, we set it to 1e-5 on ImageNet dataset.
from condensenet.
@ShichenLiu Hi, does group lasso make any difference on ImageNet. Since the paper seems only gives the results with group lasso on ImageNet, right? What is the result if not including this term? Thanks
from condensenet.
What is the converted model for densenet_LGC?
from condensenet.
What is the specific network structure configuration of Condensenetv2 on the CIFAR dataset of Condensenetv2-110 and Condensenetv2-146
from condensenet.
hi @xiaohe725 , this repository does not contain models for CondenseNet v2.
from condensenet.
Yes, but I haven't seen it in the paper and code of CondensenetV2 either
from condensenet.
Related Issues (20)
- Training Time issue when training Condensenet-light on cifar100 HOT 3
- the version of pytorch HOT 1
- cuda runtime error (11) : invalid argument at /pytorch/aten/src/THC/THCGeneral.cpp:383 I have only one 2080ti,but I encounter this bug, could you give me some suggestions,please? HOT 1
- Question on CondensingConv from layers.py HOT 1
- Question on dropping function HOT 3
- Question on clamp HOT 2
- is_best defining problem
- CondeseNet-182* on Cifar100 validation 1 error rate is 19.73% where in paper is 18.47% HOT 6
- Group lasso regularization effect for ImageNet HOT 2
- dropout before convolution layer HOT 2
- condensenet-86 parameters number different from torchsummary HOT 2
- Question on CondensingLinear HOT 1
- How to run Condensenet without GPU?
- +FDC (full dense connectivity) version
- Request to update to PyTorch Version 1.6.0 (Latest) HOT 2
- Testing on ARM without CUDA and GPU
- What are the Training Arguments for ImageNet Pre-Trained Model? HOT 5
- Questions on implementation of dropping
- Issues with PyTorch 1.9.0
- RuntimeError: INDICES element is out of DATA bounds
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 condensenet.