tensorflow-serving - 如何使模型为带有 base64 编码图像的 TensorFlow Serving REST 接口(interface)做好准备？

Question

我的理解是，我应该能够从 Google 的 AI Hub 中获取 TensorFlow 模型，将其部署到 TensorFlow Serving 并使用它通过使用 curl 的 REST 请求发布图像来进行预测。

目前我在 AI Hub 上找不到任何 bbox 预测器，但我确实在 TensorFlow 模型动物园中找到了一个:

http://download.tensorflow.org/models/object_detection/ssd_mobilenet_v2_coco_2018_03_29.tar.gz

我已将模型部署到 TensorFlow 服务，但文档不清楚 REST 请求的 JSON 中应包含的确切内容。

我的理解是

模型的 SignatureDefinition 决定 JSON 的样子

我应该对图像进行base64编码

我能够像这样获得模型的签名定义:

>python tensorflow/tensorflow/python/tools/saved_model_cli.py show --dir /Users/alexryan/alpine/git/tfserving-tutorial3/model-volume/models/bbox/1/ --all

MetaGraphDef with tag-set: 'serve' contains the following SignatureDefs:

signature_def['serving_default']:
  The given SavedModel SignatureDef contains the following input(s):
    inputs['in'] tensor_info:
        dtype: DT_UINT8
        shape: (-1, -1, -1, 3)
        name: image_tensor:0
  The given SavedModel SignatureDef contains the following output(s):
    outputs['out'] tensor_info:
        dtype: DT_FLOAT
        shape: unknown_rank
        name: detection_boxes:0
  Method name is: tensorflow/serving/predict

我认为这里的形状信息告诉我模型可以处理任何尺寸的图像？

输入层在 Tensorboard 中如下所示:


但是如何将此 SignatureDefinition 转换为有效的 JSON 请求？
我假设我应该使用预测 API ...

和 Google's doc说……

URL

POST http://host:port/v1/models/${MODEL_NAME}[/versions/${MODEL_VERSION}]:predict

/versions/${MODEL_VERSION} is optional. If omitted the latest version is used.

Request format
The request body for predict API must be JSON object formatted as follows:

{
  // (Optional) Serving signature to use.
  // If unspecifed default serving signature is used.
  "signature_name": <string>,  
  // Input Tensors in row ("instances") or columnar ("inputs") format.
  // A request can have either of them but NOT both.
  "instances": <value>|<(nested)list>|<list-of-objects>
  "inputs": <value>|<(nested)list>|<object>
}

Encoding binary values JSON uses UTF-8 encoding. If you have input feature or tensor values that need to be binary (like image bytes), you must Base64 encode the data and encapsulate it in a JSON object having b64 as the key as follows:

{ "b64": "base64 encoded string" }

You can specify this object as a value for an input feature or tensor. The same format is used to encode output response as well.

A classification request with image (binary data) and caption features is shown below:

{   "signature_name": "classify_objects",   "examples": [
    {
      "image": { "b64": "aW1hZ2UgYnl0ZXM=" },
      "caption": "seaside"
    },
    {
      "image": { "b64": "YXdlc29tZSBpbWFnZSBieXRlcw==" },
      "caption": "mountains"
    }   ] }

不确定性包括:

我应该在我的 JSON 中使用“实例”

我应该对 JPG 或 PNG 或其他东西进行 base64 编码吗？

图像应该是特定的
宽度和高度？

在 Serving Image-Based Deep Learning Models with TensorFlow-Serving’s RESTful API建议采用这种格式:

{
  "instances": [
                  {"b64": "iVBORw"},
                  {"b64": "pT4rmN"},
                  {"b64": "w0KGg2"}
                 ]
}

我使用了这张图片:
https://tensorflow.org/images/blogs/serving/cat.jpg

和base64编码它像这样:

  # Download the image
  dl_request = requests.get(IMAGE_URL, stream=True)
  dl_request.raise_for_status()

  # Compose a JSON Predict request (send JPEG image in base64).
  jpeg_bytes = base64.b64encode(dl_request.content).decode('utf-8')
  predict_request = '{"instances" : [{"b64": "%s"}]}' % jpeg_bytes

但是当我使用 curl 像这样发布 base64 编码的图像时:

{"instances" : [{"b64": "/9j/4AAQSkZJRgABAQAASABIAAD/4QBYRXhpZgAATU0AKgAA
...
KACiiigAooooAKKKKACiiigAooooA//Z"}]}

我得到这样的回应:

>./test_local_tfs.sh 
HEADER=|Content-Type:application/json;charset=UTF-8|
   URL=|http://127.0.0.1:8501/v1/models/saved_model/versions/1:predict|
*   Trying 127.0.0.1...
* TCP_NODELAY set
* Connected to 127.0.0.1 (127.0.0.1) port 8501 (#0)
> POST /v1/models/saved_model/versions/1:predict HTTP/1.1
> Host: 127.0.0.1:8501
> User-Agent: curl/7.54.0
> Accept: */*
> Content-Type:application/json;charset=UTF-8
> Content-Length: 85033
> Expect: 100-continue
> 
< HTTP/1.1 100 Continue
* We are completely uploaded and fine
< HTTP/1.1 400 Bad Request
< Content-Type: application/json
< Date: Tue, 17 Sep 2019 10:47:18 GMT
< Content-Length: 85175
< 
{ "error": "Failed to process element: 0 of \'instances\' list. Error: Invalid argument: JSON Value: {\n    \"b64\": \"/9j/4AAQSkZJRgABAQAAS
...
ooooA//Z\"\n} Type: Object is not of expected type: uint8" }

我试过像这样将同一文件的本地版本转换为base64(确认dtype是uint8)......

  img = cv2.imread('cat.jpg')   
  print('dtype: ' +  str(img.dtype))                                                                                                                                                                                
  _, buf = cv2.imencode('.jpg', img)
  jpeg_bytes = base64.b64encode(buf).decode('utf-8')
  predict_request = '{"instances" : [{"b64": "%s"}]}' % jpeg_bytes

但是发布这个 JSON 会产生同样的错误。

但是，当 json 像这样格式化时......

{'instances': [[[[112, 71, 48], [104, 63, 40], [107, 70, 20], [108, 72, 21], [109, 77, 0], [106, 75, 0], [92, 66, 0], [106, 80, 0], [101, 80, 0], [98, 77, 0], [100, 75, 0], [104, 80, 0], [114, 88, 17], [94, 68, 0], [85, 54, 0], [103, 72, 11], [93, 62, 0], [120, 89, 25], [131, 101, 37], [125, 95, 31], [119, 91, 27], [121, 93, 29], [133, 105, 40], [119, 91, 27], [119, 96, 56], [120, 97, 57], [119, 96, 53], [102, 78, 36], [132, 103, 44], [117, 88, 28], [125, 89, 4], [128, 93, 8], [133, 94, 0], [126, 87, 0], [110, 74, 0], [123, 87, 2], [120, 92, 30], [124, 95, 33], [114, 90, 32], 
...
, [43, 24, 33], [30, 17, 36], [24, 11, 30], [29, 20, 38], [37, 28, 46]]]]}

... 有用。
问题是这个 json 文件的大小 > 11 MB。

如何使 json 的 base64 编码版本工作？

更新:似乎我们必须编辑预训练模型以在输入层接受 base64 图像

本文介绍了如何编辑模型...
Medium: Serving Image-Based Deep Learning Models with TensorFlow-Serving’s RESTful API
...不幸的是，它假设我们可以访问生成模型的代码。

user260826 的解决方案提供了一种使用估计器的解决方法，但它假设模型是 keras 模型。在这种情况下不正确。

是否有一种通用方法可以使模型为 TensorFlow Serving REST 接口(interface)做好准备，该接口(interface)具有适用于任何 TensorFlow 模型格式的 base64 编码图像？

Answer 1

第一步是以适当的格式导出训练好的模型。使用export_inference_graph.py像这样

python export_inference_graph \
    --input_type encoded_image_string_tensor \
    --pipeline_config_path path/to/ssd_inception_v2.config \
    --trained_checkpoint_prefix path/to/model.ckpt \
    --output_directory path/to/exported_model_directory

在上面的代码片段中，指定

--input_type encoded_image_string_tensor

导出模型后，像往常一样使用新导出的模型运行 tensorflow 服务器。

推理代码将如下所示:

from __future__ import print_function
import base64
import requests

SERVER_URL = 'http://localhost:8501/v1/models/vedNet:predict'

IMAGE_URL = 'test_images/19_inp.jpg'


def main():
    with open(IMAGE_URL, "rb") as image_file:
        jpeg_bytes = base64.b64encode(image_file.read()).decode('utf-8')
        predict_request = '{"instances" : [{"b64": "%s"}]}' % jpeg_bytes
        response = requests.post(SERVER_URL, predict_request)
        response.raise_for_status()
        prediction = response.json()['predictions'][0]

if __name__ == '__main__':
  main()