The text transcription feature does. But the AutoML documentation doesn't list TIFF as a supported file type. Is that documentation outdated?
You mentioned two different products, the first link you shared is from Cloud Vision API which are pre-trained models and indeed supports TIFF files as is mentioned in the Support Images page. And the second link you mentioned belongs to AutoML Vision where you can train your own models and doesn't support TIFF files, the difference between products is mentioned in the "NOTE" section.
Related
I've used the Video Intelligence API to do object tracking on video.
In the document [1], it recognizes more than 20,000 objects, places, and actions in stored and streaming video.
I have a questions. Is there any document that shows what kind of objects can be recognized or can't be recognized?
It's my first question. Thank you.
[1] https://cloud.google.com/video-intelligence
In this GCP documentation, it enumerates the categories in which Cloud Video Intelligence API can detect, analyze, track, transcribe and recognize: https://cloud.google.com/video-intelligence/docs/how-to
Among the things that are listed on the GCP documentation that Cloud Video Intelligence API can detect, track and recognize are: faces, people, shot changes, explicit content, objects, logos and text. Cloud Video Intelligence API are already pre-trained, if in case there are objects that Cloud Video Intelligence API can't recognize, you can train your own custom models using AutoML Video Intelligence. To get started with AutoML Video Intelligence, you can refer to this GCP documentation: https://cloud.google.com/video-intelligence/automl/docs/beginners-guide
As to the limitation of object that can be recognized in Cloud Video Intelligence API, there is no document that states which object are not recognizable. The only limits that are in the Cloud Video Intelligence API documentation are in terms of video size, per request and length. GCP Documentation: https://cloud.google.com/video-intelligence/quotas
I want to do OCR and I know that Cloud Vision API supports it. But I'm interested in making my custom model for it and wish to use AutoML for the same. But I couldn't find anything related to OCR using AutoML. Is it possible to do OCR using AutoML? How do we go about this? I know this is a very open-ended question, but I'd appreciate some help.
AutoML Natural Language can perform OCR on PDFs; however, this is just a step because is intended for creating your on models on text classification, entity extraction or sentiment analysis.
If you goal is just to perform OCR the best approach will be Vision API.
You cannot do OCR from AutoML. Your options are to use the Cloud Vision API to do OCR and then apply your own algorithms to put the detected letters together in a certain way, or to start from scratch and train your own OCR model (not recommended).
I trained a model using google AutoML Vision and now I want to export it to use it locally, I tried this tutorial from Google official doc with no success.
Actually, in model list, when I click the three dots (more actions) there is no export option:
Even in the test & use page there is no option to export the model:
Thanks in advance,
First of all, the tutorial you are following is for AutoML tables and, although similar, is not exactly the same as for AutoML Vision.
For AutoML Vision you can train two types of models, Cloud hosted and Edge-exportable. As the name may infer, only the second ones can be exported.
Here you can see the documentation for exporting AutoML Vision Edge models.
My assumption is you have trained a Cloud hosted model which is not exportable.
There is currently a feature request opened to allow this behavior. You can find it here. If you would also be interested on it you can star it to keep updated about the progress.
I've trained a video classification model using Google's video intelligence platform, I want to now download the model to predict on-prem for security purpose but I don't see anyway of exporting the model. Is there any way to do so?
I inform you that indeed you are right. As of today the AutoML Video Intelligence is on Beta and there is no way to export your model.
I would advise you to stay alert for the Release Notes to check for updates on the product.
I want to be able to select similar images using Google Cloud Vision AI out of range of images that I provide.
It seems there is Web Detection feature allows to show similar images across the web but I want to search across user provided images or even just within a particular website (not across entire web).
Is this possible to do?
There is no built in feature that allows you to do that on the Google Cloud Vision API, but what you can do is fetch the URL of the matching images detected across the web and filter the ones you are interested in. You can follow this tutorial.
I hope that helps
You could try out Vision API's ProductSearch: https://cloud.google.com/vision/product-search/docs/
See this answer: https://stackoverflow.com/a/58402071/11201290