Google Cloud Vision API批处理图像Anotater

Question

我有一个目录，其中有近200张图像，我想使用image属性使用google> google-cloud-vision api。

我对这些图像的批处理请求遇到问题。 发布的代码是官方网站的教程。但它使用gs：//作为图像的来源。

我想使用我的本地目录，但无法弄清楚该怎么做。 第二是我写的。我试图用ImagelOdeLoader加载图像，但失败了。

请帮忙！

from google.cloud import vision_v1

def sample_async_batch_annotate_images(
    input_image_uri="gs://cloud-samples-data/vision/label/wakeupcat.jpg",
    output_uri="gs://your-bucket/prefix/",
):
    """Perform async batch image annotation."""
    client = vision_v1.ImageAnnotatorClient()

    source = {"image_uri": input_image_uri}
    image = {"source": source}
    features = [
        {"type_": vision_v1.Feature.Type.LABEL_DETECTION},
        {"type_": vision_v1.Feature.Type.IMAGE_PROPERTIES},
    ]

    # Each requests element corresponds to a single image.  To annotate more
    # images, create a request element for each image and add it to
    # the array of requests
    requests = [{"image": image, "features": features}]
    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=requests, output_config=output_config)

    print("Waiting for operation to complete...")
    response = operation.result(90)

    # 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))

我试图简单地将通往本地目录的路径更改，但是出现了一个错误，即它必须是gs：//，然后我开始使用imgs将图像加载a imageloader，但然后得到此错误typeError：无法设置Google.cloud.vision.vis.v1.imagesource.image_uri to [＆lt; pil; pil;

import io
import os

from google.cloud import vision_v1

from os import listdir
from PIL import Image as PImage

os.environ["GOOGLE_APPLICATION_CREDENTIALS"] = r"/Users/example/Documents/Project/ServiceAccountTolken.json"

def loadImages(path):
    # return array of images

    imagesList = listdir(path)
    loadedImages = []
    for image in imagesList:
        img = PImage.open(path + image)
        loadedImages.append(img)

    return loadedImages

path = "/Users/Documents/Project/images/"

# your images in an array
imgs = loadImages(path)

# its a bit messy here since I tried some options

def sample_async_batch_annotate_images(
    input_image_uri = imgs, #os.path.abspath("/Users/Documents/Project/images"),
    output_uri = os.path.abspath("/Users/Documents/Project/images/output"),
):
    """Perform async batch image annotation."""
    client = vision_v1.ImageAnnotatorClient()

    source = {"image_uri": input_image_uri}
    image = {"source": source}
    features = [
        {"type_": vision_v1.Feature.Type.IMAGE_PROPERTIES},
    ]

    # Each requests element corresponds to a single image.  To annotate more
    # images, create a request element for each image and add it to
    # the array of requests
    requests = [{"image": image, "features": features}]
    gcs_destination = {"uri": output_uri}

    # The max number of responses to output in each JSON file
    batch_size = 6
    output_config = {"gcs_destination": gcs_destination,
                     "batch_size": batch_size}

    operation = client.async_batch_annotate_images(requests=requests, output_config=output_config)

    print("Waiting for operation to complete...")
    response = operation.result(90)

    # 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

async_batch_annotate_images（）不支持读取本地文件。您需要使用batch_annotate_images（）。要读取本地图像，您需要将图像内容读取为字节，然后将其传递给请求。下面的代码包括将Response.json保存到GCS存储桶中。但是，如果您不需要将其保存到GCS中，请在本地保存该文件的部分。

请参阅下面的代码：

import io
import os

from google.cloud import vision_v1

from os import listdir
import proto
from google.cloud import storage
#os.environ["GOOGLE_APPLICATION_CREDENTIALS"] = r"/Users/example/Documents/Project/ServiceAccountTolken.json"

def loadImages(path):
    # return array of bytes

    imagesList = listdir(path)
    loadedImages = []

    for image in imagesList:
        with io.open(path+image, 'rb') as image:
            content = image.read()
        loadedImages.append(content)

    return loadedImages

path = "/home/user/your_local_path"

# your images in an array
contents = loadImages(path)

def batch_annotate(
    contents = contents,
):
    """Perform async batch image annotation."""
    client = vision_v1.ImageAnnotatorClient()

    bucket_name = "your-bucket-name"
    destination_blob_name = "response.json"

    storage_client = storage.Client()
    bucket = storage_client.bucket(bucket_name)
    blob = bucket.blob(destination_blob_name)

    requests = []

    for content in contents:
        image = {"content": content}
        features = [
            {"type_": vision_v1.Feature.Type.IMAGE_PROPERTIES},
        ]
        requests.append({"image": image, "features": features})

    response = client.batch_annotate_images(requests=requests,)
    to_text = proto.Message.to_json(response) # convert object to text

    # uncomment if you want to save the response to your local directory
    """f = open('response.json', 'w')
    for data in to_text:
        f.write(data)
    f.close()"""

    file_obj = io.StringIO(to_text)
    file_obj.seek(0)
    blob.upload_from_file(file_obj)

batch_annotate()

请参见GCS中的保存结果：

response.json的示例摘要：