GitXplorerGitXplorer
l

Mixed-Depthwise-Convolutional-Kernels

public
62 stars
8 forks
3 issues

Commits

List of commits on branch master.
Unverified
a48baa2317340e08646ae70318de12ac5ddbf8d6

[Update] code refactoring

lleaderj1001 committed 5 years ago
Unverified
ff2e2b9453ed21ef475b899d34128edb7e2a00eb

[Update]

lleaderj1001 committed 5 years ago
Verified
80dc519c7952be26a22d1589ff4f918218a294d2

Update README.md

lleaderj1001 committed 5 years ago
Verified
d3563ada0bbc963d0890f024b8290a93b7dff1f6

Update README.md

lleaderj1001 committed 5 years ago
Verified
c9d059dd2c3cbd8590e45d068475c2866ff21deb

Update README.md

lleaderj1001 committed 5 years ago
Verified
835d8eb4e72235590417b625981137d9f5407863

Update README.md

lleaderj1001 committed 5 years ago

README

The README file for this repository.

Implementing Mixed-Depthwise-Convolutional-Kernels using Pytorch (22 Jul 2019)

  • Author:
    • Mingxing Tan (Google Brain)
    • Quoc V. Le (Google Brain)
  • Paper Link

Method

캡처

  • By using a multi scale kernel size, performance improvements and efficiency were obtained.
  • Each kernel size has a different receptive field, so we can get different feature maps for each kernel size.

Experiment

Datasets Model Acc1 Acc5 Parameters (My Model, Paper Model)
CIFAR-10 MixNet-s (WORK IN PROCESS) 92.82% 99.79% 2.6M, -
CIFAR-10 MixNet-m (WORK IN PROCESS) 92.52% 99.78% 3.5M, -
CIFAR-10 MixNet-l (WORK IN PROCESS) 92.72% 99.79% 5.8M, -
IMAGENET MixNet-s (WORK IN PROCESS) 4.1M, 4.1M
IMAGENET MixNet-m (WORK IN PROCESS) 5.0M, 5.0M
IMAGENET MixNet-l (WORK IN PROCESS) 7.3M, 7.3M

Usage

python main.py

  • --data (str): the ImageNet dataset path

  • --dataset (str): dataset name, (example: CIFAR10, CIFAR100, MNIST, IMAGENET)

  • --batch-size (int)

  • --num-workers (int)

  • --epochs (int)

  • --lr (float): learning rate

  • --momentum (float): momentum

  • --weight-decay (float): weight dacay

  • --print-interval (int): training log print cycle

  • --cuda (bool)

  • --pretrained-model (bool): hether to use the pretrained model

Todo

  • Distributed SGD
  • ImageNet experiment

Reference