如何对输入为编码的\u图像\u字符串\u张量的tensorflow模型的输入进行编码

我在谷歌人工智能平台上训练了一个目标检测模型，并下载了该模型。这是一个标准保存的_model.pb文件，我想用python加载它，并提供一个用于推断的图像。 问题是该模型的输入被定义为

编码的\图像\字符串\张量

，它需要base64编码的字符串。如何在python中以这种格式对图像文件进行编码

print(model.inputs)
print(model.output_dtypes)
print(model.output_shapes)

[<tf.Tensor 'encoded_image_string_tensor:0' shape=(None,) dtype=string>, <tf.Tensor 'key:0' shape=(None,) dtype=string>, <tf.Tensor 'global_step:0' shape=() dtype=resource>]
{'detection_scores': tf.float32, 'detection_classes': tf.float32, 'num_detections': tf.float32, 'key': tf.string, 'detection_boxes': tf.float32}
{'detection_scores': TensorShape([None, 100]), 'detection_classes': TensorShape([None, 100]), 'num_detections': TensorShape([None]), 'key': TensorShape([None]), 'detection_boxes': TensorShape([None, 100, 4])}

当我在模型上运行此代码时，将

encoded\u image\u string\u tensor

作为输入，它会产生以下错误：

---------------------------------------------------------------------------
TypeError                                 Traceback (most recent call last)
 in 
      1 for i in range(1):
----> 2     show_inference(model, TEST_IMAGE_PATHS[i])

 in show_inference(model, image_path)
     39 #   print(image_np)
     40   # Actual detection.
---> 41   output_dict = run_inference_for_single_image(model, image_np)
     42   # Visualization of the results of a detection.
     43   print(output_dict['detection_scores'][:3])

 in run_inference_for_single_image(model, image)
      7 
      8   # Run inference
----> 9   output_dict = model(input_tensor)
     10 
     11   # All outputs are batches tensors.

~\anaconda3\envs\tf2\lib\site-packages\tensorflow\python\eager\function.py in __call__(self, *args, **kwargs)
   1603       TypeError: For invalid positional/keyword argument combinations.
   1604     """
-> 1605     return self._call_impl(args, kwargs)
   1606 
   1607   def _call_impl(self, args, kwargs, cancellation_manager=None):

~\anaconda3\envs\tf2\lib\site-packages\tensorflow\python\eager\function.py in _call_impl(self, args, kwargs, cancellation_manager)
   1622            "of {}), got {}. When calling a concrete function, positional "
   1623            "arguments may not be bound to Tensors within nested structures."
-> 1624           ).format(self._num_positional_args, self._arg_keywords, args))
   1625     args = list(args)
   1626     for keyword in self._arg_keywords[len(args):]:

TypeError: Expected at most 0 positional arguments (and the rest keywords, of ['encoded_image', 'key']), got (,). When calling a concrete function, positional arguments may not be bound to Tensors within nested structures.

---

通过使用

tf.io.encode\u jpeg（）

对图像进行编码，您可以很容易地从笔记本（您的示例中似乎使用了）中调整

run\u expression\u for\u single\u image（）

函数

Google AI平台的内置对象检测模型还需要一个键（任何具有批量大小维度的字符串张量）作为输入，我还将其添加到下面示例中的

model（）

调用中

def为单个图像（模型，图像）运行推理：
image=np.asarray（图像）
#输入必须是张量，请使用“tf.convert\u to\u tensor”将其转换。
输入\u张量=tf。将\u转换为\u张量（图像）
#将（数字）张量编码为“编码的_图像”
编码图像=tf.io.encode\u jpeg（输入张量）
#模型需要一批图像，因此添加一个带有“tf.newaxis”的轴。
编码图像=编码图像[tf.newaxis，…]
#运行推断（从AI平台下载的SavedModel也需要一个“键”作为输入。）
输出dict=模型（编码图像=编码图像，键=tf.expand\u dims（tf.convert\u to\u tensor（“test\u key”），0））
# ...

---------------------------------------------------------------------------
TypeError                                 Traceback (most recent call last)
 in 
      1 for i in range(1):
----> 2     show_inference(model, TEST_IMAGE_PATHS[i])

 in show_inference(model, image_path)
     39 #   print(image_np)
     40   # Actual detection.
---> 41   output_dict = run_inference_for_single_image(model, image_np)
     42   # Visualization of the results of a detection.
     43   print(output_dict['detection_scores'][:3])

 in run_inference_for_single_image(model, image)
      7 
      8   # Run inference
----> 9   output_dict = model(input_tensor)
     10 
     11   # All outputs are batches tensors.

~\anaconda3\envs\tf2\lib\site-packages\tensorflow\python\eager\function.py in __call__(self, *args, **kwargs)
   1603       TypeError: For invalid positional/keyword argument combinations.
   1604     """
-> 1605     return self._call_impl(args, kwargs)
   1606 
   1607   def _call_impl(self, args, kwargs, cancellation_manager=None):

~\anaconda3\envs\tf2\lib\site-packages\tensorflow\python\eager\function.py in _call_impl(self, args, kwargs, cancellation_manager)
   1622            "of {}), got {}. When calling a concrete function, positional "
   1623            "arguments may not be bound to Tensors within nested structures."
-> 1624           ).format(self._num_positional_args, self._arg_keywords, args))
   1625     args = list(args)
   1626     for keyword in self._arg_keywords[len(args):]:

TypeError: Expected at most 0 positional arguments (and the rest keywords, of ['encoded_image', 'key']), got (,). When calling a concrete function, positional arguments may not be bound to Tensors within nested structures.