Udemyallja

【画像判定AIアプリ開発パート2】Django・TensorFlow・Python・転移学習による高精度AIアプリ開発

Build an image classification AI app with Python 3! Learn data collection, transfer learning, deep learning models, and deploy with Django. Practical AI development.

4.4(483)
5,402students
3h 16m
Certificate
井上 博樹 (Hiroki Inoue)
井上 博樹 (Hiroki Inoue)AI開発, スタートアップ, Udemy講師

Course Content

【画像判定AIアプリ開発パート2】Django・TensorFlow・Python・転移学習による高精度AIアプリ開発 is an all-levels Udemy course taught by 井上 博樹 (Hiroki Inoue). It runs 3h 16m, is taught in Japanese, and includes a certificate of completion. Learners rate it 4.4 out of 5 from 483 reviews, with 5,402 students enrolled. It is a paid course, last updated October 2021.

Develop AI Web Applications with Django & TensorFlow/Keras

This course guides you through building a practical AI web application using the powerful combination of Django 2.2 and TensorFlow/Keras. It's a sequel to our popular TensorFlow introductory course and a Keras image classification project, taking you from basic concepts to a fully functional, deployed application.

What you'll build:

Create a web app that classifies images as either "car" or "bike" with 100% accuracy! The application allows users to upload images, which are then analyzed by a pre-trained VGG-16 model (using transfer learning) to determine the object present. The results are then displayed on the web page.

Key Skills & Technologies:

  • Django 2.2: Learn to build robust and scalable web applications with Django, focusing on image upload, model inference, and result display.
  • TensorFlow & Keras: Master TensorFlow and the high-level Keras API for building and training image classification models. This course leverages the built-in Keras within TensorFlow, simplifying the setup process.
  • Image Classification AI: Develop and deploy a real-world image classification solution using transfer learning techniques.
  • Transfer Learning: Boost model accuracy by leveraging pre-trained models like VGG-16.
  • Bootstrap 4: Enhance the user interface with a modern and responsive design using Bootstrap 4.
  • Data Preprocessing: Learn essential data cleaning and preparation techniques using NumPy.
  • CNNs (Convolutional Neural Networks): Understand the fundamentals of CNNs for image analysis.

Course Highlights:

  • Simplified Setup: No need to install Keras separately! We utilize the Keras implementation directly within TensorFlow 2.
  • Step-by-Step Guidance: We cover everything from environment setup and data collection to deployment.
  • High Accuracy: Achieve impressive results with a 100% accuracy rate on the car vs. bike classification task.
  • Practical Application: Build a real-world application that can be easily adapted to other image classification problems.
  • Version Updated: The course has been updated to reflect the latest Django 2.2 version.
  • Recent Update (2021/10/28): Added code modifications to enable training using only TensorFlow 2's built-in Keras, eliminating the need for a separate Keras installation.

Course Outline:

  1. Environment Setup & Data Acquisition: Setting up your development environment and gathering the necessary image data.
  2. Data Preprocessing: Cleaning, preparing, and saving your image data as NumPy arrays.
  3. AI Model Development with CNNs & Transfer Learning: Building and training your image classification model using TensorFlow/Keras. Learn to save your model files.
  4. Model Definition, Training & Inference: Defining, training, and using your Keras model for prediction.
  5. Command-Line Application (Python 3): Creating a command-line interface for testing your model.
  6. Web Application Development with Django: Building the web application to handle image uploads, model inference, and result display.
  7. Styling with Bootstrap 4: Improving the visual appeal of your web application.
  8. Image Prediction & Result Display: Displaying uploaded images and their corresponding classification results.

Prerequisites:

A basic understanding of Python is recommended. Prior experience with TensorFlow or Keras is helpful, but not required. We recommend completing the "TensorFlow Experience Course" for a solid foundation.

Related Courses:

Explore other deep learning courses including:

Support:

If you encounter any issues, don't hesitate to reach out! Please re-run the program or provide a screenshot along with your question in the course Q&A. We strive to respond promptly. This course is not recommended for those who prefer video-based learning; text-based platforms like Techpit are better suited.

Commercial Use:

Course content can be utilized within companies and educational institutions. Please contact us for details. Cloud-based access is also available.

$ whoami — the devs behind tutorialsearch.io

Want AI in your product? Hire the team behind TutorialSearch.io

LLM features, RAG, agents and automation wired into a real product — built by the devs who shipped this site.