I have made an image recognition system using python and I am trying to implement that in website. I have have a system that recognizes the fruit images built using CNN. Now, I have built a website which is of a Fruit-blog. I want a section or a page in in that website in which a user can upload an image and the website can recognize which fruit is the given image of but I have no idea how to implement my recognition system in the website. Can you please help me explaining what to do and how can I implement the AI from python to Django website?
The main part comes from freezing your model and serving it using a web framework like flask or django. Then you can communicate with it by passing images and receiving prediction objects. An example is at this github repo written in Django for deploy in Heroku https://github.com/marcogdepinto/Deep-learning-model-deploy-with-django
Related
is it possible for me to create a website that uses ONNX.js to serve the model and create a frontend using React? If yes, please point toward some resources.
Also, what other ways can a Pytorch model be served into production in conjunction with a react frontend, any suggestions are welcome.
Thanks!
I have done my final year Engineering project using FastAi and PyTorch and I created a website for deployment using Flask Framework. It was straightforward and simple to create. I suggest looking into this and as for deployment, you can use Heroku or GitHub pages for deploying your model.
You can refer to this https://medium.com/unpackai/how-to-deploy-fast-ai-models-8704ea711ad2
You can also create a notebook app if you are using Jupyter Notebooks. For reference https://www.analyticsvidhya.com/blog/2020/10/develop-and-deploy-an-image-classifier-app-using-fastai/
It was not easy to understand in the beginning but by watching various YouTube videos, I was able to successfully deploy my model online for anyone to use.
I want to develop a WEb-based voting system in java. The system has facial recognition and OTP verification. I have a a facial recognition code in python and the model is 85% accurate. How can I implement facial recognition in my web based voting system?
You can call the python function in your Java code via ProcessBuilder, but it's not recommended unless you are confident in the robust of your python code and you are sure it's easy to maintain in this way.
My advice is to build a python backend service (using Flask, for example, it's a light-weighted framework for python web services) and call your python service via HTTP request in your Java code. By doing this, the two programs are decoupled and might be reused conveniently.
Is there a way to deploy my machine learning model(which is currently a pickle file) into Pycharm through Tkinter GUI. I have seen methods to deploy models in python but they all have to do with integrating through flask or Django. The gui allows users to input data but I need the input to be passed through the trained model to produce a prediction.
This Tutorial can give you some insight into how to use a machine learning model with Tkinter.
Machine Learning model is like any other python package you can load your model anywhere in the code and use it with the native API, without a need for an HTTP request like with Django and Flask
I've developed a website for uploading and downloading images using Django. I've also written a python code using the Google Vision API and executed the file successfully on the command line. Now, where should I place that python code in my Django project, so that my images pass through the API?
I am new to web development and working on a personal project with motive to learn to build websites in Python that interacts with third party API.
My website is very simple, it that allows user to play a YouTube video and list the data corresponding to it, like no. of views, Likes & Dislikes,in the same page similar to a YouTube page where videos are played. I would be using YouTube Data API and Player API to do it.
I would like to know which web architecture should i follow to build such a website. I have build sites on MVC architecture in Java but here i am not sure if that is feasible. I would be using urllib2 and requests library to access the API in XML & JSON. I tried to search it in the web but in most of the cases i got 'how to build a Web API' which do not suffice my requirement.
I would appreciate if someone provide me a link to resource or any Github project from where i can learn about architecture in depth.
Thanks in Advance.
Unless I misunderstood your requirements, your app consumes the YouTube API. At the minimum you would need these python packages flask, requests, google-api-python-client and oauth2client (documentation available in each project's page)
Here are some examples from Google on how you would use their library.
The 12 factor app page has general guidlines on how to design a web application.