如何为张量流服务准备预热请求文件？

Question

当前版本的 tensorflow-serving 尝试从 assets.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] No warmup data file found at /tmp/faster_rcnn_inception_v2_coco_2018_01_28_string_input_version-export/1/assets.extra/tf_serving_warmup_requests

不知道tensorflow有没有提供通用的api导出请求到位置？或者我们应该手动向该位置写入请求？

Answer 1

此时没有通用的 API 可以将预热数据导出到 assets.extra。写个脚本比较简单（类似下面）：

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

我们参考了official doc

特别是，我们使用分类而不是预测，因此我们将该代码更改为

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

我将此文件移动到 /your_model_location/resnet/1538687457/assets.extra/，然后重新启动我的 docker 图像以获取新的更改。

如何为张量流服务准备预热请求文件？

How to prepare warmup request file for tensorflow serving?

tensorflow

tensorflow-serving

inference