Using pre-trained machine learning models
1. Using pre-trained machine learning models
Pre-trained learning models can help you add powerful features to your applications. Google Cloud offers several pre- trained machine-learning models that you can use to add intelligence to your application. Vision AI lets you perform complex image detection. Speech-to-Text and Text-to-Speech enable developers to convert audio to text and text to audio. Translation AI lets you translate an arbitrary string into any supported language. The Cloud Translation API is highly responsive. Websites and applications can use the Cloud Translation API for fast, dynamic translation of text from a source language to a target language. Natural Language AI lets you extract information about entities that are mentioned in text documents, news articles, or blog posts. You can use the Cloud Natural Language API to understand sentiment about your product on social media, or parse intent from customer conversations. Video AI lets you search video files to extract and label entities at the shot, frame, or video level. The Video Intelligence API annotates videos stored in Cloud Storage and helps you identify key entities in your video and when they occur within the video. Document AI takes unstructured data from documents and transforms it into structured data, making it easier to understand, analyze, and consume. AutoML on Gemini Enterprise Agent Platform (Agent Platform AutoML) enables users with limited ML expertise to train high-quality models specific to their business needs. Agent Platform AutoML lets you train models on images, tabular data, or videos without writing any code. You can also use your own data to build and train your own custom ML models by using frameworks like TensorFlow and PyTorch. It's really easy to invoke the REST APIs to implement machine learning in your application, no ML knowledge is required. In this example, we are using the Vision API to process an image that's stored in Cloud Storage. We invoke the REST API and send it a JSON request, and we receive a JSON response with attributes that describe the image. Let's take a look at a few examples now. The Vision API can categorize objects under labels and perform optical character recognition, or OCR. The Vision API can detect landmarks, logos, faces, and explicit content. For example, the Vision API can analyze faces and return information about emotions and head wear. In the wedding picture, the API accurately returns the emotional expressions on the faces in the picture. In the picture of the Sphinx, Vision API correctly detects that the image is from the Sphinx in Las Vegas and not the Sphinx in Egypt. The Speech-to-Text API enables developers to convert audio to text. It handles 110 languages and variants to support your global user base. You can transcribe the text of users dictating to an application’s microphone, enable command-and-control through voice, transcribe audio files, and more. Here's an example of how Google uses machine learning. Google’s conference room systems perform occupancy detection by using motion detection with the VC camera. Every 30 seconds, the system sends a Pub/Sub notification indicating whether motion was detected or not. It also sends a Pub/Sub notification when a call starts or ends. If motion is detected between 6 and 8 minutes after the meeting start time, the room counts as occupied. Otherwise, it's empty, and is available for someone else to reserve.2. Let's practice!
Create Your Free Account
or
By continuing, you accept our Terms of Use, our Privacy Policy and that your data is stored in the USA.