tensorflow_model_server: 错误 "The first dimension of paddings must be the rank of inputs[4,2]..."

Question

我正在使用 tensorflow_model_server 来提供 SavedModel。我不断收到此响应代码 400 和以下错误：

{ "error": "The first dimension of paddings must be the rank of inputs[4,2] [1,1,1,208,770,3]\n\t [[{{node Generator/FlatConv/sequential/zero_padding2d/Pad}}]]" }

saved-model-cli 显示的输出...

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

signature_def['__saved_model_init_op']:
  The given SavedModel SignatureDef contains the following input(s):
  The given SavedModel SignatureDef contains the following output(s):
    outputs['__saved_model_init_op'] tensor_info:
        dtype: DT_INVALID
        shape: unknown_rank
        name: NoOp
  Method name is: 

signature_def['serving_default']:
  The given SavedModel SignatureDef contains the following input(s):
    inputs['input_1'] tensor_info:
        dtype: DT_FLOAT
        shape: (-1, -1, -1, 3)
        name: serving_default_input_1:0
  The given SavedModel SignatureDef contains the following output(s):
    outputs['output_1'] tensor_info:
        dtype: DT_FLOAT
        shape: (-1, -1, -1, 3)
        name: StatefulPartitionedCall:0
  Method name is: tensorflow/serving/predict
WARNING:tensorflow:From /tensorflow-1.15.0/python3.6/tensorflow_core/python/ops/resource_variable_ops.py:1781: calling BaseResourceVariable.__init__ (from tensorflow.python.ops.resource_variable_ops) with constraint is deprecated and will be removed in a future version.
Instructions for updating:
If using Keras pass *_constraint arguments to layers.

Defined Functions:
  Function Name: '_default_save_signature'
    Option #1
      Callable with:
        Argument #1
          input_1: TensorSpec(shape=(?, ?, ?, 3), dtype=tf.float32, name='input_1')

预处理

img_path = "/content/input_images/my_img.jpg"

img = np.array(Image.open(img_path).convert("RGB"))
img = np.expand_dims(img, 0).astype(np.float32) / 127.5 - 1

请求码：

payload = {
  "instances": [{'input_1': [input_image.tolist()]}]
}
headers = {"content-type": "application/json"}
json_response = requests.post('http://localhost:8501/v1/models/my_model:predict', data=json.dumps(payload), headers=headers)
print("Request complete")
print (json_response)
response_text =  json_response.text
response_text

响应/输出

Request complete
<Response [400]>
'{ "error": "The first dimension of paddings must be the rank of inputs[4,2] [1,1,1,449,674,3]\n\t [[{{node Generator/FlatConv/sequential/zero_padding2d/Pad}}]]" }'

Colab 上的代码是运行

我不明白这里有什么问题。

Answer 1

也就是说你的输入数据应该是四维数组，而你有6d

Answer 2

试试这个：

  "instances": [{'input_1': np.squeeze(input_image).tolist()}]

移除外部 [] 并挤压它似乎将 6d 减少到 4d，这可能会起作用。

当我有一个 multi-modal 输入时，我运行陷入了类似的错误，其中第一项是图像，第二项是字符串。我尝试删除图像输入中的批次维度并且它有效。在我看来，这似乎是 tensorflow-serving 中的一个错误。它应该能够处理一批图像的散列。

（或者，如果您之前没有 np.expand_dims，则不需要挤压。

tensorflow_model_server: 错误 "The first dimension of paddings must be the rank of inputs[4,2]..."

tensorflow_model_server: Error "The first dimension of paddings must be the rank of inputs[4,2]..."

tensorflow-serving