All classes Transfer Learning for Leaf Disease Syllabus · Episode 6 of 6

Class Transfer Learning Leaf Disease #6: Class-wise Evaluation, Confusion Matrix & Leaf Detection Web Application

0 views

Tutorial on model evaluation and Streamlit web application: classification report, confusion matrix, analysis of mispredictions, and tomato leaf disease detection application using MobileNetV2. Episode 6, the conclusion of the series.

Software: Deep Learning (PyTorch MobileNetV2)
Level: Advanced
Duration: ± 14 min
Series total: 1 h 5 min · 6 videos
Published: October 24, 2026

Episode 6 of 6 · view syllabus

Download PDF (6 PDF pages)

0 downloads

Download Project File· 48 MB Unlock All Premium Classes ▶ Watch the video lesson0 plays

▶ Video Lesson

Watch every step above performed live, with English narration.

0 plays

Class book

Page 1 / 6

Class Transfer Learning Leaf Disease #6: Class-wise Evaluation, Confusion Matrix & Leaf Detection Web Application: Cover: Class Transfer Learning Leaf Disease #6: Class-wise Evaluation, Confusion Matrix & Web Detection Application

Class Transfer Learning Leaf Disease #6: Class-wise Evaluation, Confusion Matrix & Leaf Detection Web Application: Before you start, steps list, and Step 1

Class Transfer Learning Leaf Disease #6: Class-wise Evaluation, Confusion Matrix & Leaf Detection Web Application: Step 2: Class report & confusion matrix

Class Transfer Learning Leaf Disease #6: Class-wise Evaluation, Confusion Matrix & Leaf Detection Web Application: Step 3–4: Prediction error analysis

Class Transfer Learning Leaf Disease #6: Class-wise Evaluation, Confusion Matrix & Leaf Detection Web Application: Step 5–6: Prediction view & running the application

Class Transfer Learning Leaf Disease #6: Class-wise Evaluation, Confusion Matrix & Leaf Detection Web Application: Done: Final Result and Further Practice

Cover: Class Transfer Learning Leaf Disease #6: Class-wise Evaluation, Confusion Matrix & Web Detection Application

Click a page or use ◀ ▶ to turn · swipe on mobile · to enlarge

Want to go deeper?

Join one of our courses or ask us directly on WhatsApp.

Download PDF· 0 downloads View the full 6-episode syllabus View Transfer Learning for Agriculture Courses Ask on WhatsApp

Recommended classes for you

Picked from the software, topic, and level of “Class Transfer Learning Leaf Disease #6: Class-wise Evaluation, Confusion Matrix & Leaf Detection Web Application”.

Deep Learning CNN-LSTM Pneumonia Detection

6 episodesFree preview

Python · Intermediate–Advanced

Deep Learning CNN-LSTM Pneumonia Detection

6 video lessons with PDF guides, 57 min in total. Starts with: Chest X-ray Dataset: Loading, Exploration & Data Splitting.

57 min 22 0

View class

18 episodesFree preview

Python · Beginner–Advanced

Machine Learning Python

18 video lessons with PDF guides, 3 h 41 min in total. Starts with: Introduction to Machine Learning & First Model.

3 h 41 min 61 0

View class

6 episodesFree preview

Python · Intermediate–Advanced

Brain Tumor Segmentation with U-Net

6 video lessons with PDF guides, 1 h 10 min in total. Starts with: Brain MRI Dataset & Tumor Mask: Loading, Visualization & Patient-wise Splitting.

1 h 10 min 28 0

View class

50 episodesFree preview

Agentic AI · Beginner–Intermediate

Agentic AI Without Coding

50 video lessons with PDF guides, 14 h 29 min in total. Starts with: Chatbots, Automation, and AI Agents: What's the Difference?.

14 h 29 min 66 0

View class

100 episodesFree preview

Claude · Beginner–Advanced

Claude from Zero to Expert

100 video lessons with PDF guides, 15 h 1 min in total. Starts with: What Claude Is and How It Differs from ChatGPT and Gemini.

15 h 1 min 62 0

View class

6 episodesFree preview

Python · Intermediate–Advanced

Deepfake Detection Vision Transformer

6 video lessons with PDF guides, 1 h 11 min in total. Starts with: Deepfake Concepts, Manipulation Types & Real vs Fake Face Dataset.

1 h 11 min 0 0

View class

EKG Arrhythmia Classification Wavelet Deep Learning

6 episodesFree preview

Python · Intermediate–Advanced

EKG Arrhythmia Classification Wavelet Deep Learning

6 video lessons with PDF guides, 56 min in total. Starts with: EKG & EEG Signals: Characteristics and Public Datasets (MIT-BIH).

56 min 2 0

View class

ANFIS Metaheuristics Time Series Forecasting

6 episodesFree preview

Python · Intermediate–Advanced

ANFIS Metaheuristics Time Series Forecasting

6 video lessons with PDF guides, 59 min in total. Starts with: Non-Linear Time Series: Dataset, Stationarity, and Patterns.

59 min 13 0

View class

Need more than a video?

Other ways we can help with Python.

Learn with a mentor

Scheduled AI & Machine Learning courses with live guidance and a certificate.

Course

Multi-Objective Optimization Course: NSGA-II, MOPSO & Hybrid Algorithms (Python)

Course

ECG Arrhythmia Classification Course with Wavelet & Deep Learning (PyTorch)

Course

ANFIS + PSO/GA Course for Non-Linear Time Series Forecasting (Python)

See all in AI & Machine Learning →

Have it built for you

No time to learn Python? Our team can do the project for you.

Service

Python Machine Learning — Prediction Models, Customer Segmentation, Fraud Detection & AI Apps

Service

AI Image Creation with Stable Diffusion — Unlimited Custom Visual Production

★ 4.9

Service

AI Image & Video Creation with Leonardo AI — All-in-One Visuals for Business

★ 4.9

See all in AI & Machine Learning →

Get notified about new Python classes

At most one email a week. Unfollow anytime with one click.

Transcript

The full narration of this video. The current sentence is highlighted while the video plays; click any sentence to jump there.

Show transcript

Introduction

This is the final result, a web application for detecting tomato leaf diseases. Select or upload a leaf photo, and the optimized MobileNet V2 model directly displays the disease along with its confidence level. On the test data, the accuracy is 93.7%. Let's get started. Hello, welcome to the final episode of the leaf disease detection series using transfer learning and hyperparameter optimization. We have three models: feature extraction, manual fine-tuning, and fine-tuning with hyperparameter optimization using Optuna. Now we will evaluate all three on the unseen test data, analyze performance per class, and then convert the best model into a web application that anyone can use.

Step 1: Test Accuracy of Three Models

Create an evaluation file for leaf disease report. We load all three models from their respective PT files, predict 300 test images, and then calculate the accuracy. Run Feature extraction 75.3%, fine-tuning 92.3%, and Optuna model 93.7%. The order is the same as the validation results, meaning our model is not overfitting on the validation data.

Step 2: Class-wise Report 8 Confusion Matrix

Accuracy alone is not enough for research. The classification report displays precision, recall, and F1 per class. Leaf mold and virus mosaic are perfect with F1 1.0, healthy leaf 0.98. The hardest class is early blight with F1 0.867. Spider mite has recall 1 but precision 0.81, meaning some leaves from other classes are incorrectly predicted as spider mite. The confusion matrix clarifies this, with the green diagonal representing correct predictions, and for example, three target spot leaves are predicted as spider mite.

Step 3: Analysis of Misclassifications

Let's look at an example of incorrect prediction. Out of 300 test images, 19 are incorrect. If you look closely, many errors occur on leaves with small spots that are similar across diseases, something that is sometimes also difficult for the human eye. At the end, we save one example leaf per class to the examples folder for the web application.

Step | Streamlit Application: Loading Model & Input

Now the web application. Create an app file for leaf disease with Streamlit. The model is loaded once with cache resource, so it is not reloaded on every interaction. The page contains a title, a select box to choose a leaf example, and a file uploader to upload your own photo.

Step 5: Prediction Display & Running the Application

In the prediction section, images are displayed in the left column, then processed with the same evaluation transformation as during evaluation, and softmax converts the model's output into probabilities. The right column displays the top prediction in the green box, plus the top three possibilities with a progress bar. We run it with streamlit run on the background, then open it in the browser at localhost port 8501.

Step 6: Trying the Application in the Browser

The application is displayed. First example, bacterial spots, predicted correctly with confidence around 99%. We select another example from the select box, leaf mold, and the model updates its prediction correctly. This application is ready to be developed into a tool for farmers or agricultural extension workers. Done, and that concludes this series.

Done!

We have already built a complete leaf disease detection research, dataset plan village, augmentation and data pipeline, transfer learning with MobileNet V2 and ResNet 50 Fine-tuning with cosine annealing, hyperparameter optimization with Optuna, class-wise evaluation, up to web application. For further research, try photos of leaves from the field, other plant classes, or the efficient net model. Thank you for following this series. Working on a thesis, dissertation, or AI research in the field of agricultural AI? Cerdas Inovasi Digital helps implement deep learning, from transfer learning MobileNet and ResNet, Fine-tuning, hyperparameter optimization with Optuna, up to web application and result writing as well as opening a deep learning course with Pythor. Want to master the entire series, from the Plant Village dataset to the web app for leaf disease detection? All 6 episodes, complete with a step-by-step PDF guide and source code, Available for premium tutorial subscribers. Subscribe starting at Rp69.000 per month, save 28% with 12-month package, or pay once Rp999.000 for lifetime access. Thank you for watching, see you in the next episode.

Ask the class material

Type a question or keyword; we find the part of this episode that explains it and jump the video there.

My notes

Notes are saved with the current video time and are only visible to you.

Questions & answers

Stuck on a step? Ask here; the instructor and other learners can answer.

No questions yet.

Your instructor

Cerdas Inovasi Digital Team

Software developers, BIM & 3D engineers, and AI practitioners

53 video classes1,296 episodes

We build software, BIM models, games and AI automations for clients every day, and turn that hands-on work into step-by-step classes: every step is shown on screen and comes with a PDF guide you can keep.

See our clients →

Memuat

▶ Video Lesson

Recommended classes for you

Need more than a video?

Transcript

0:03Introduction

0:50Step 1: Test Accuracy of Three Models

3:49Step 2: Class-wise Report 8 Confusion Matrix

5:23Step 3: Analysis of Misclassifications

7:42Step | Streamlit Application: Loading Model & Input

10:22Step 5: Prediction Display & Running the Application

12:24Step 6: Trying the Application in the Browser

12:49Done!

Ask the class material

My notes

Questions & answers

Your instructor

▶ Video Lesson

Recommended classes for you

Need more than a video?

Transcript

0:03Introduction

0:50Step 1: Test Accuracy of Three Models

3:49Step 2: Class-wise Report 8 Confusion Matrix

5:23Step 3: Analysis of Misclassifications

7:42Step | Streamlit Application: Loading Model & Input

10:22Step 5: Prediction Display & Running the Application

12:24Step 6: Trying the Application in the Browser

12:49Done!

Ask the class material

My notes

Questions & answers

Your instructor

Introduction

Step 1: Test Accuracy of Three Models

Step 2: Class-wise Report 8 Confusion Matrix

Step 3: Analysis of Misclassifications

Step | Streamlit Application: Loading Model & Input

Step 5: Prediction Display & Running the Application

Step 6: Trying the Application in the Browser

Done!

Introduction

Step 1: Test Accuracy of Three Models

Step 2: Class-wise Report 8 Confusion Matrix

Step 3: Analysis of Misclassifications

Step | Streamlit Application: Loading Model & Input

Step 5: Prediction Display & Running the Application

Step 6: Trying the Application in the Browser

Done!