Hi everyone,
I am trying to convert an online image annotation process to a batch process, following the python recipe here: https://cloud.google.com/vision/docs/batch (I'm using google-cloud-vision 3.1.4, and importing with: 'from google.cloud import vision').
The problem is, the properties of the json response I extract from the batch annotation is different from that I get from the online annotation, so that my existing postprocessing pipeline is not working with the batch outputs.
In the online version, I am using two steps to generate a json response:
- api_response =vision.ImageAnnotatorClient().annotate_image(
vision.AnnotateImageRequest(image, features))
- api_response_json_str = vision.AnnotateImageResponse.to_json(api_response)
where, the only feature I am specifying is vision.Feature(type_="DOCUMENT_TEXT_DETECTION").
In the batch version, a single step dumps the response as a json file in the gcs bucket specified in the output config:
vision.ImageAnnotatorClient().async_batch_annotate_images(requests, output_config)
looking at the vision.ImageAnnotatorClient.async_batch_annotate_images(), the second step of the online process seems to be already executed (through image_annotator.AsyncBatchAnnotateImagesResponse), which makes sense. But it seems as if the behavior of the AnnotateImageResponse and the AsyncBatchAnnotateImagesResponse are different.
Here a segment of the json from the online version:
{
"property": {
"detectedBreak": {
"type": 1,
"isPrefix": false
},
"detectedLanguages": []
},
"boundingBox": {
"vertices": [
{
"x": 99,
"y": 99
},
{
"x": 106,
"y": 99
},
{
"x": 106,
"y": 109
},
{
"x": 99,
"y": 109
}
],
"normalizedVertices": []
},
"text": "n",
"confidence": 0.98761535
}
And here the same segment from the batch prediction:
{
"property": {
"detectedBreak": {
"type": "SPACE"
}
},
"boundingBox": {
"vertices": [
{
"x": 99,
"y": 99
},
{
"x": 106,
"y": 99
},
{
"x": 106,
"y": 109
},
{
"x": 99,
"y": 109
}
]
},
"text": "n",
"confidence": 0.98761535
}
Note how all the numbers match, but not all the content.
I could not find any relevant documentation. As the last resort, of course I can hack my code or the json files to make things work, but I feel like there must be a way to reproduce the behavior of the online request (and actually this must be the case by default!).
Any help would be greatly appreciated!
Best,
Onur
LinkedIn
Twitter
