python - 如何从 Google Cloud Storage 存储桶加载保存在 joblib 文件中的模型

Question

我想加载一个从 Google Cloud Storage 存储桶保存为 joblib 文件的模型。当它在本地路径时，我们可以按如下方式加载它(考虑到model_file是系统中的完整路径):

loaded_model = joblib.load(model_file)

我们如何使用 Google Cloud Storage 完成相同的任务？

Answer 1

对于任何在谷歌上搜索答案的人。
除了显而易见的之外，还有两个选项，使用 Google AI 平台进行模型托管(和在线预测)。

选项 1 是像这样使用 TemporaryFile:

from google.cloud import storage
from sklearn.externals import joblib
from tempfile import TemporaryFile

storage_client = storage.Client()
bucket_name=<bucket name>
model_bucket='model.joblib'

bucket = storage_client.get_bucket(bucket_name)
#select bucket file
blob = bucket.blob(model_bucket)
with TemporaryFile() as temp_file:
    #download blob into temp file
    blob.download_to_file(temp_file)
    temp_file.seek(0)
    #load into joblib
    model=joblib.load(temp_file)
#use the model
model.predict(...)

选项 2 是像这样使用 BytesIO:

from google.cloud import storage
from sklearn.externals import joblib
from io import BytesIO

storage_client = storage.Client()
bucket_name=<bucket name>
model_bucket='model.joblib'

bucket = storage_client.get_bucket(bucket_name)
#select bucket file
blob = bucket.blob(model_bucket)
#download blob into an in-memory file object
model_file = BytesIO()
blob.download_to_file(model_file)
#load into joblib
model=joblib.load(model_local)