在本地,当我们想使用TensorFlow加载模型时,我们这样做:
path_to _frozen = model_path + '/frozen_inference_graph.pb'
detection_graph = tf.Graph()
with detection_graph.as_default():
od_graph_def = tf.GraphDef()
with tf.io.gfile.GFile(path_to _frozen, 'rb') as fid:
serialized_graph = fid.read()
od_graph_def.ParseFromString(serialized_graph)
tf.import_graph_def(od_graph_def, name='')
我们如何使用Google云功能将存储的模型加载到Google存储桶上?
答案 0 :(得分:1)
您可以将pb文件存储在存储中。
然后,在您的函数中,将其下载到local writable directory /tmp
中。请记住,该目录位于“内存中”。这意味着必须正确定义分配给您的函数的内存,以处理应用程序的内存占用以及模型下载的文件
用类似这样的内容替换第一行。
# Be sure that your function service account as access to the storage bucket
storage_client = storage.Client()
bucket = storage_client.get_bucket('<bucket_name>')
blob = bucket.blob('<path/to>/frozen_inference_graph.pb')
# Download locally your pb file
path_to_frozen = '/tmp/frozen_inference_graph.pb'
blob.download_to_filename(path_to_frozen)
答案 1 :(得分:1)
constructor(
private dataService: DataService
){ }
ngOnInit() {
this.dataService.getProducts().subscribe(
data => {
console.log(data)
},
error => {
console.log(error)
}
);
}
def处理程序(请求): download_blob(“ BUCKET_NAME”,“ redbull / output_inference_graph.pb / frozen_inference_graph.pb”,“ / tmp / frozen_inference_graph.pb”) 打印(“好”) detection_graph = tf.Graph() 使用detection_graph.as_default(): od_graph_def = tf.GraphDef() 使用tf.io.gfile.GFile('/ tmp / frozen_inference_graph.pb','rb')作为fid: serialized_graph = fid.read() od_graph_def.ParseFromString(serialized_graph) tf.import_graph_def(od_graph_def,name ='')