[如何使用Google的视觉API注释一次调用中的多张图像？ Python

Question

我最近开始使用Google的视觉API。我正在尝试批注图像，因此从其文档中发布了'batch image annotation offline'指南。

但是，我不清楚如何从一个API调用中注释多个图像。假设我在Google云端存储桶中存储了10张图片。如何一次注释所有这些图像并将它们存储在一个JSON文件中？现在，我编写了一个程序，调用它们的示例函数，并且可以运行，但是简单起见，为什么我不能说：“查看此文件夹并注释其中的所有图像。”]

提前感谢。

from batch_image_labeling import sample_async_batch_annotate_images
counter = 0
for file in os.listdir('my_directory'):
    filename = file
    sample_async_batch_annotate_images('gs://my_bucket/{}'.format(filename), 'gs://my_bucket/{}'.format(counter))
    counter += 1


from google.cloud import vision_v1
from google.cloud.vision_v1 import enums
import six

def sample_async_batch_annotate_images(input_image_uri, output_uri):
  """Perform async batch image annotation"""

  client = vision_v1.ImageAnnotatorClient()

  if isinstance(input_image_uri, six.binary_type):
    input_image_uri = input_image_uri.decode('utf-8')
  if isinstance(output_uri, six.binary_type):
    output_uri = output_uri.decode('utf-8')
  source = {'image_uri': input_image_uri}
  image = {'source': source}
  type_ = enums.Feature.Type.LABEL_DETECTION
  features_element = {'type': type_}
  type_2 = enums.Feature.Type.IMAGE_PROPERTIES
  features_element_2 = {'type': type_2}
  features = [features_element, features_element_2]
  requests_element = {'image': image, 'features': features}
  requests = [requests_element]
  gcs_destination = {'uri': output_uri}

  # The max number of responses to output in each JSON file
  batch_size = 2
  output_config = {'gcs_destination': gcs_destination, 'batch_size': batch_size}

  operation = client.async_batch_annotate_images(requests, output_config)

  print('Waiting for operation to complete...')
  response = operation.result()

  # The output is written to GCS with the provided output_uri as prefix
  gcs_output_uri = response.output_config.gcs_destination.uri
  print('Output written to GCS with prefix: {}'.format(gcs_output_uri))

Answer 1

从该示例尚不清楚，但是您对async_batch_annotate_images的调用采用了requests参数，该参数是多个请求的列表。因此，您可以执行以下操作：

rom google.cloud import vision_v1
from google.cloud.vision_v1 import enums
import six

def generate_request(input_image_uri):
  if isinstance(input_image_uri, six.binary_type):
    input_image_uri = input_image_uri.decode('utf-8')
  if isinstance(output_uri, six.binary_type):
    output_uri = output_uri.decode('utf-8')
  source = {'image_uri': input_image_uri}
  image = {'source': source}
  type_ = enums.Feature.Type.LABEL_DETECTION
  features_element = {'type': type_}
  type_2 = enums.Feature.Type.IMAGE_PROPERTIES
  features_element_2 = {'type': type_2}
  features = [features_element, features_element_2]
  requests_element = {'image': image, 'features': features}

  return requests_element


def sample_async_batch_annotate_images(input_uri, output_uri):
  """Perform async batch image annotation"""

  client = vision_v1.ImageAnnotatorClient()

  requests = [
    generate_request(input_uri.format(filename))
    for filename in os.listdir('my_directory')
  ]

  gcs_destination = {'uri': output_uri}

  # The max number of responses to output in each JSON file
  batch_size = 1
  output_config = {'gcs_destination': gcs_destination, 'batch_size': batch_size}

  operation = client.async_batch_annotate_images(requests, output_config)

  print('Waiting for operation to complete...')
  response = operation.result()

  # The output is written to GCS with the provided output_uri as prefix
  gcs_output_uri = response.output_config.gcs_destination.uri
  print('Output written to GCS with prefix: {}'.format(gcs_output_uri))


sample_async_batch_annotate_images('gs://my_bucket/{}', 'gs://my_bucket/results')

这可以在单个请求中注释多达2,000张图像。唯一的缺点是您只能将单个output_uri指定为目标，因此无法使用counter将每个结​​果放在单独的文件中，但是可以设置batch_size = 1以确保每个响应如果需要的话，将单独编写。