Question

当前版本的tensorflow-serving尝试从asset.extra / tf_serving_warmup_requests文件加载预热请求。

2018-08-16 16：05：28.513085：I tensorflow_serving / servables / tensorflow / saved_model_warmup.cc：83]在/tmp/faster_rcnn_inception_v2_coco_2018_01_28_string_input_version-export/1/assets.extra/tp_up_reserving/ >

我想知道tensorflow是否提供通用API来将请求导出到该位置吗？还是我们应该手动将请求写到该位置？

Answer 1

目前，尚无用于将预热数据导出到asset.extra的通用API。编写脚本相对简单（类似于以下内容）：

import tensorflow as tf
from tensorflow_serving.apis import model_pb2
from tensorflow_serving.apis import predict_pb2
from tensorflow_serving.apis import prediction_log_pb2

def main():
    with tf.python_io.TFRecordWriter("tf_serving_warmup_requests") as writer:
        request = predict_pb2.PredictRequest(
            model_spec=model_pb2.ModelSpec(name="<add here>"),
            inputs={"examples": tf.make_tensor_proto([<add here>])}
        )
    log = prediction_log_pb2.PredictionLog(
        predict_log=prediction_log_pb2.PredictLog(request=request))
    writer.write(log.SerializeToString())

if __name__ == "__main__":
    main()

Answer 2

我们提到了official doc

特别是，我们使用分类而不是预测，因此我们将代码更改为 log = prediction_log_pb2.PredictionLog( classify_log=prediction_log_pb2.ClassifyLog(request=<request>))

Answer 3

这是使用ResNet model的对象检测系统的完整示例。预测由图像组成。

import tensorflow as tf
import requests
import base64

from tensorflow.python.framework import tensor_util
from tensorflow_serving.apis import predict_pb2
from tensorflow_serving.apis import prediction_log_pb2


IMAGE_URL = 'https://tensorflow.org/images/blogs/serving/cat.jpg'
NUM_RECORDS = 100


def get_image_bytes():
    image_content = requests.get(IMAGE_URL, stream=True)
    image_content.raise_for_status()
    return image_content.content


def main():
    """Generate TFRecords for warming up."""

    with tf.io.TFRecordWriter("tf_serving_warmup_requests") as writer:
        image_bytes = get_image_bytes()
        predict_request = predict_pb2.PredictRequest()
        predict_request.model_spec.name = 'resnet'
        predict_request.model_spec.signature_name = 'serving_default'
        predict_request.inputs['image_bytes'].CopyFrom(
            tensor_util.make_tensor_proto([image_bytes], tf.string))        
        log = prediction_log_pb2.PredictionLog(
            predict_log=prediction_log_pb2.PredictLog(request=predict_request))
        for r in range(NUM_RECORDS):
            writer.write(log.SerializeToString())    

if __name__ == "__main__":
    main()

此脚本将创建一个名为“ tf_serving_warmup_requests”的文件

我将此文件移至/your_model_location/resnet/1538687457/assets.extra/，然后重新启动docker镜像以获取新更改。

如何准备张量流服务的预热请求文件？

3 个答案: