Skip to content
#

efficient

Here are 117 public repositories matching this topic...

RudyChin
RudyChin commented Jun 25, 2020

Hi Jiahui,

Thanks for the great work. I'm trying to reproduce AutoSlim for CIFAR-10 (Table 2).
Could you please provide a detailed hyperparameter you used for it?

I'm able to train the baseline MobileNetV2 1.0x to 7.9 Top-1 error using the following hyperparameters:

  • 0.1 initial learning rate
  • linear learning rate decay
  • 128 batch size
  • 300 epochs of training
  • 5e-4 weight decay
Byron
Byron commented Mar 15, 2020

Previously jwalk would follow symlinks, so we could not use it and instead implemented our own traversal.

Now with jwalk 0.5, this is supported and we can use our standard jwalker to do the job.

https://github.com/Byron/dua-cli/blob/543f7f3948c26250a8fc6ebf79a49f3ddfa3cb63/src/interactive/app/handlers.rs#L305-L340

The function above would have to change to use jwalk. It should be straight

Reference ImageNet implementation of SelecSLS CNN architecture proposed in the SIGGRAPH 2020 paper "XNect: Real-time Multi-Person 3D Motion Capture with a Single RGB Camera". The repository also includes code for pruning the model based on implicit sparsity emerging from adaptive gradient descent methods, as detailed in the CVPR 2019 paper "On implicit filter level sparsity in Convolutional Neural Networks".

  • Updated Jul 23, 2020
  • Python

Improve this page

Add a description, image, and links to the efficient topic page so that developers can more easily learn about it.

Curate this topic

Add this topic to your repo

To associate your repository with the efficient topic, visit your repo's landing page and select "manage topics."

Learn more

You can’t perform that action at this time.