Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/neuleaf/MobileNetV2
A Tensorflow implementation of MobileNet V2
https://github.com/neuleaf/MobileNetV2
Last synced: about 1 month ago
JSON representation
A Tensorflow implementation of MobileNet V2
- Host: GitHub
- URL: https://github.com/neuleaf/MobileNetV2
- Owner: neuleaf
- Created: 2018-01-29T08:33:31.000Z (almost 7 years ago)
- Default Branch: master
- Last Pushed: 2019-05-07T02:59:13.000Z (over 5 years ago)
- Last Synced: 2024-08-01T22:50:07.416Z (4 months ago)
- Language: Python
- Size: 39.1 KB
- Stars: 150
- Watchers: 11
- Forks: 72
- Open Issues: 3
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
- awesome-image-classification - unofficial-tensorflow : https://github.com/neuleaf/MobileNetV2
- awesome-image-classification - unofficial-tensorflow : https://github.com/neuleaf/MobileNetV2
README
# Note
- update 2019.05.06
Tensorflow的API发生了很大变化,原来的代码已经不实用。而且TF官方models也开源了相关的代码。
此项目不再更新,并且已删除了部分代码,只留下网络结构代码,有需要可供参考。# MobileNet V2 with Tensorflow
论文链接 https://arxiv.org/abs/1801.04381
## Task1 classification
1. 制作tfrecord文件
训练图片及类别标签组织为`train_data.txt`的形式,每一行表示一个样本及其标签,用空格或Tab隔开.
run `python convert2tf.py [--options]` 生成tfrecord文件。
(同时会打印数据集样本的格式'num_samples', 训练时需要输入该参数)2. 训练
run `python main.py --epoch 10 --dataset_dir ./tfrecords --n_classes 10 --batch_size 4 --num_samples 20000 [--options]`启动训练.
注意更改参数
3. test/infer测试时需要指定`--no_train`,如:
`python main.py --n_classe 10 --no_train`## Task2 detection
TODO
## Task3 segmentationTODO