在线时间:8:00-16:00
迪恩网络APP
随时随地掌握行业动态
扫描二维码
关注迪恩网络微信公众号
开源软件名称(OpenSource Name):Bisonai/mobilenetv3-tensorflow开源软件地址(OpenSource Url):https://github.com/Bisonai/mobilenetv3-tensorflow开源编程语言(OpenSource Language):Python 100.0%开源软件介绍(OpenSource Introduction):MobileNetV3 TensorFlowUnofficial implementation of MobileNetV3 architecture described in paper Searching for MobileNetV3.
This repository contains small and large MobileNetV3 architecture implemented using TensforFlow with Google ColabRequirements
pip install -r requirements.txt Build modelMobileNetV3 Smallfrom mobilenetv3_factory import build_mobilenetv3
model = build_mobilenetv3(
"small",
input_shape=(224, 224, 3),
num_classes=1001,
width_multiplier=1.0,
) MobileNetV3 Largefrom mobilenetv3_factory import build_mobilenetv3
model = build_mobilenetv3(
"large",
input_shape=(224, 224, 3),
num_classes=1001,
width_multiplier=1.0,
) TrainCIFAR10 datasetpython 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 datasetpython 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 EvaluateCIFAR10 datasetpython 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 datasetpython 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 TensorBoardGraph, 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 |
2023-10-27
2022-08-15
2022-08-17
2022-09-23
2022-08-13
请发表评论