Hello I'm
Aditya Mishra
Machine Learning Engineer
- mishraaditya6991@gmail.com
- +91 7021590384
- Mumbai, India
Hello, I’m Aditya, machine learning engineer based on Mumbai. I have experience in developing end to end machine learning project, software engineering, web site design and linux. Also I am good at
Boards is a data science discussion app. Each board contains various topics and represents different aspects of data science. Users can signup in the app and start discussion on different topics. Posts can be modified by users. Boards are created by admin but users can create different topics in a particular board. Have fun!!
View GitHub
BotVic is a IPL chatbot. Named after , which was the first attempt by a bot to commentate in a sport. BotVic is a retrival based chatbot. It is trained on the text from IPL & IPL franchises wikipedia pages. Ask him any question and it will give a response, it could best find. Check out the app on desktop and have fun!!.
View GitHub
Legal Compose is a language modeling app that predicts next few words given a statement. It is trained on judgements available in Supreme Court reports. These reports were scraped from Supreme Court of India's website. It is an attempt at developing Google's Smart Compose like feature for legal Indian text.
GitHub
Train an object detection model on custom data. TensorFlow’s Object Detection API is a very powerful tool that can quickly enable anyone to build and deploy powerful image recognition software. Here, I used the Object Detection API to train a model on a bunch of mobile handset images, using SSD MobileNet as a pretrained model. Follow the steps to collect your own data & train a detection model on it.
GitHub
Deep Diagnosis is a CNN classifier which classifies skin lesions into malignant or benign skin cancer. It is also capable of predicting the severity of Diabetic Retinopathy from a given retina image.
GitHub
Image classification is assumed to be a nearly solved problem. Fun part is when you have to use all your cunning to gain that extra 1% accuracy.
Read More
Evaluating your machine learning algorithm is an essential part of any project.
our model may give you satisfying results when evaluated against one metric but may
give poor results when evaluated against other metrics.
This is the first part of two part series on training your own model on handwritten characters. This part focuses on generating your own character dataset. In the next part, we will discuss, as how to create and train our own model.
Read More