TensorFlow Hub
使用集合让一切井井有条
根据您的偏好保存内容并对其进行分类。
TensorFlow Hub 是用于存储可重用机器学习资产的开放仓库和库。tfhub.dev 仓库中提供了许多预训练模型:文本嵌入向量、图像分类模型、TF.js/TFLite 模型等。该仓库向社区贡献者开放。
借助 tensorflow_hub
库,您可以下载并以最少的代码量在 TensorFlow 程序中重用这些模型。
import tensorflow_hub as hub
model = hub.KerasLayer("https://tfhub.dev/google/nnlm-en-dim128/2")
embeddings = model(["The rain in Spain.", "falls",
"mainly", "In the plain!"])
print(embeddings.shape) #(4,128)
后续步骤
如未另行说明,那么本页面中的内容已根据知识共享署名 4.0 许可获得了许可,并且代码示例已根据 Apache 2.0 许可获得了许可。有关详情,请参阅 Google 开发者网站政策。Java 是 Oracle 和/或其关联公司的注册商标。
最后更新时间 (UTC):2024-01-11。
[null,null,["最后更新时间 (UTC):2024-01-11。"],[],[],null,["# TensorFlow Hub\n\n\u003cbr /\u003e\n\nTensorFlow Hub is an open repository and library for reusable machine learning.\nThe [tfhub.dev](https://tfhub.dev) repository provides many pre-trained models:\ntext embeddings, image classification models, TF.js/TFLite models and much more.\nThe repository is open to\n[community contributors](https://tfhub.dev/s?subtype=publisher).\n\nThe [`tensorflow_hub`](https://github.com/tensorflow/hub) library lets you\ndownload and reuse them in your TensorFlow program with a minimum amount of\ncode. \n\n import tensorflow_hub as hub\n\n model = hub.KerasLayer(\"https://tfhub.dev/google/nnlm-en-dim128/2\")\n embeddings = model([\"The rain in Spain.\", \"falls\",\n \"mainly\", \"In the plain!\"])\n\n print(embeddings.shape) #(4,128)\n\nNext Steps\n----------\n\n- [Find models on tfhub.dev](https://tfhub.dev)\n- [Publish models on tfhub.dev](/hub/publish)\n- TensorFlow Hub library\n - [Install TensorFlow Hub](/hub/installation)\n - [Library overview](/hub/lib_overview)\n- [Follow tutorials](/hub/tutorials)"]]