Find inspiring and useful tools and experiments related to AI and Machine Learning.
This is Part 2 of the two-part series on how to deploy a Django application to Google Cloud Platform (GCP). In Part 1, I discussed how to set up a Virtual Machine using GCP's Compute Engine, and deploy a Django application to it, which was then accessible through just an IP address.
In this tutorial, I will continue from where we left off, and demonstrate the following 3 things:
In the past, whenever I wanted to launch a Django website on a Linux server, I would follow the steps outlined in the famous Corey Shafer's tutorial on launching a Django Application on Linode.com. However, recently I've had to launch a Django application on the Google Cloud Platform, and even though most of the steps are the same, I had to do a lot of trial and error to figure out the exact steps required to achieve the same. And this is what I will show you in this tutorial.
In this tutorial, we will be fine-tuning a DistilBert model for the Multiclass text classification problem using a custom dataset and the HuggingFace's transformers library.
In this tutorial, I'm going to share with you how I implemented Glove Vector Embeddings for a text classification task that uses the Scikit-learn Pipeline. I will explain how Pipelines work in general and how to create a custom class in Scikit-learn for Glove Vector Embeddings while going through an example classification task using a dataset from Kaggle.
Extract information from scanned images.
Extract and Generate Keywords and Key-phrases from text.
Generates story based on a text prompt and genre, using the GPT-2 transformer model.
Paraphrase some text.
Given a body of text and a question, find the answer from the text
Predict whether a sentence is positive or negative.