【AI实战】最全 TensorFlow 官方模型
1.模型和实现
1.1计算机视觉
- 图像分类
Model | Reference (Paper) |
---|---|
Mobile Video Networks (MoViNets) | MoViNets: Mobile Video Networks for Efficient Video Recognition |
1.2自然语言处理
- Pre-trained Language Model
- 神经机器翻译 Neural Machine Translation
Model | Reference (Paper) |
---|---|
Transformer | Attention Is All You Need |
- 自然语言生成 Natural Language Generation
Model | Reference (Paper) |
---|---|
NHNet (News Headline generation model) | Generating Representative Headlines for News Stories |
- 知识蒸馏 Knowledge Distillation
Model | Reference (Paper) |
---|---|
MobileBERT | MobileBERT: a Compact Task-Agnostic BERT for Resource-Limited Devices |
- 推荐 Recommendation
2.如何开始使用官方模型
2.1 pip安装
pip3 install tf-models-nightly
pip3 install tensorflow-text-nightly # when model uses `nlp` packages
对于针对特定版本的稳定版本,Tensorflow-models 存储库版本号与目标 TensorFlow 版本相匹配。
pip3 install tf-models-official==2.5.0
pip3 install tensorflow-text==2.5.0 # when model uses `nlp` packages
2.3其他安装参考
https://github.comhttps://github.com/tensorflow/models#Installation
szZack的博客