Movatterモバイル変換


[0]ホーム

URL:


Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly

Sign up
Appearance settings

Unofficial implementation of MobileNetV3 architecture described in paper Searching for MobileNetV3.

License

NotificationsYou must be signed in to change notification settings

Bisonai/mobilenetv3-tensorflow

Repository files navigation

Unofficial implementation of MobileNetV3 architecture described in paperSearching for MobileNetV3.This repository containssmall andlarge MobileNetV3 architecture implemented using TensforFlow withtf.keras API.

Google Colab

  • Open In Colab MNIST
  • Open In Colab CIFAR10

Requirements

  • Python 3.6+
  • TensorFlow 1.13+
pip install -r requirements.txt

Build model

MobileNetV3 Small

frommobilenetv3_factoryimportbuild_mobilenetv3model=build_mobilenetv3("small",input_shape=(224,224,3),num_classes=1001,width_multiplier=1.0,)

MobileNetV3 Large

frommobilenetv3_factoryimportbuild_mobilenetv3model=build_mobilenetv3("large",input_shape=(224,224,3),num_classes=1001,width_multiplier=1.0,)

Train

CIFAR10 dataset

python train.py \    --model_type small \    --width_multiplier 1.0 \    --height 128 \    --width 128 \    --dataset cifar10 \    --lr 0.01 \    --optimizer rmsprop \    --train_batch_size 256 \    --valid_batch_size 256 \    --num_epoch 10 \    --logdir logdir

MNIST dataset

python train.py \    --model_type small \    --width_multiplier 1.0 \    --height 128 \    --width 128 \    --dataset mnist \    --lr 0.01 \    --optimizer rmsprop \    --train_batch_size 256 \    --valid_batch_size 256 \    --num_epoch 10 \    --logdir logdir

Evaluate

CIFAR10 dataset

python evaluate.py \    --model_type small \    --width_multiplier 1.0 \    --height 128 \    --width 128 \    --dataset cifar10 \    --valid_batch_size 256 \    --model_path mobilenetv3_small_cifar10_10.h5

MNIST dataset

python evaluate.py \    --model_type small \    --width_multiplier 1.0 \    --height 128 \    --width 128 \    --dataset mnist \    --valid_batch_size 256 \    --model_path mobilenetv3_small_mnist_10.h5

TensorBoard

Graph, training and evaluaion metrics are saved to TensorBoard event file uder directory specified with --logdir` argument during training.You can launch TensorBoard using following command.

tensorboard --logdir logdir

License

Apache License 2.0

About

Unofficial implementation of MobileNetV3 architecture described in paper Searching for MobileNetV3.

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages


[8]ページ先頭

©2009-2025 Movatter.jp