python - 如何从本地系统加载 TF hub 模型

Question

一种方法是每次从 tensorflow_hub 下载模型喜欢以下

import tensorflow as tf
import tensorflow_hub as hub

hub_url = "https://tfhub.dev/google/tf2-preview/nnlm-en-dim128/1"
embed = hub.KerasLayer(hub_url)
embeddings = embed(["A long sentence.", "single-word", "http://example.com"])
print(embeddings.shape, embeddings.dtype)

我想下载一次文件并一次又一次地使用，而不是每次都下载

Answer 1

从 url + "?tf-hub-format=compressed"下载你的模型
例如“https://tfhub.dev/google/tf2-preview/nnlm-en-dim128/1?tf-hub-format=compressed”

解压

在代码中加载未解压的文件夹

import tensorflow as tf
import tensorflow_hub as hub

embed = hub.KerasLayer('path/to/untarred/folder')
embeddings = embed(["A long sentence.", "single-word", "http://example.com"])
print(embeddings.shape, embeddings.dtype)