New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Architecture of CondenseNet{light-160*, 182*, light-94, 84} #11
Comments
@ShichenLiu : Thanks for your great work. would you please have a look here and help us with the architectures? its greatly appreciated |
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 CondenseNet-86 CondenseNet-182* CondenseNet-light-94 CondenseNet-light-160* |
Sorry for the late reply. The command that could reproduce the results are: CondenseNet-86 CondenseNet-182* CondenseNet-light-94 CondenseNet-light-160* |
@gaohuang and @ShichenLiu : Thank you very much, guys. its really appreciated ;) |
Hi, @ShichenLiu did you set group-lasso-lambda to 1e-5 on cifar100 dataset Looking forward to your reply |
Hi, The group-lasso-lambda makes no conspicuous difference on CIFAR dataset. However, we set it to 1e-5 on ImageNet dataset. |
@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 |
* [ShichenLiu#11] Add n_params in args * [ShichenLiu#11] Add ltdn in densenet, densenet_lgc, condensenet_converted * [ShichenLiu#11] Add execute command * [ShichenLiu#11] Fix to evaluate models in main
What is the converted model for densenet_LGC? |
What is the specific network structure configuration of Condensenetv2 on the CIFAR dataset of Condensenetv2-110 and Condensenetv2-146 |
hi @xiaohe725 , this repository does not contain models for CondenseNet v2. |
Yes, but I haven't seen it in the paper and code of CondensenetV2 either |
Hi,
The paper mentions CondenseNet{light-160*, 182*, light-94, 84} for CIFAR, though is not clear about the details of the architecture. Could you share the architectures and how those results can be reproduced?
The text was updated successfully, but these errors were encountered: