All classes Deep Learning CNN-LSTM Pneumonia Detection Syllabus · Episode 5 of 6

Class Deep Learning CNN-LSTM Pneumonia Detection #5: Training CNN-LSTM: Class Weights, Scheduler & Early Stopping

4 views

PyTorch CNN-LSTM model training tutorial: class weights for imbalanced data, learning rate scheduler, early stopping, and best checkpoint. Episode 5 of the pneumonia detection series.

Software: Deep Learning (PyTorch)
Level: Advanced
Duration: ± 8 min
Series total: 57 min · 6 videos
Published: October 24, 2026

Episode 5 of 6 · view syllabus

Download PDF (5 PDF pages)

0 downloads

Download Project File· 44 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 / 5

Class Deep Learning CNN-LSTM Pneumonia Detection #5: Training CNN-LSTM: Class Weights, Scheduler & Early Stopping: Cover: Class Deep Learning CNN-LSTM Pneumonia Detection #5: Training CNN-LSTM: Class Weight, Scheduler & Early Stopping

Class Deep Learning CNN-LSTM Pneumonia Detection #5: Training CNN-LSTM: Class Weights, Scheduler & Early Stopping: Before you start, steps list, and Step 1

Class Deep Learning CNN-LSTM Pneumonia Detection #5: Training CNN-LSTM: Class Weights, Scheduler & Early Stopping: Steps 2–3: Weighted Loss, Optimizer, Scheduler

Class Deep Learning CNN-LSTM Pneumonia Detection #5: Training CNN-LSTM: Class Weights, Scheduler & Early Stopping: Step 4: Reading training results

Class Deep Learning CNN-LSTM Pneumonia Detection #5: Training CNN-LSTM: Class Weights, Scheduler & Early Stopping: Done: Final Result and Further Practice

The end

Cover: Class Deep Learning CNN-LSTM Pneumonia Detection #5: Training CNN-LSTM: Class Weight, Scheduler & Early Stopping

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 Deep Learning Courses Ask on WhatsApp

Recommended classes for you

Picked from the software, topic, and level of “Class Deep Learning CNN-LSTM Pneumonia Detection #5: Training CNN-LSTM: Class Weights, Scheduler & Early Stopping”.

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

Transfer Learning for Leaf Disease

6 video lessons with PDF guides, 1 h 5 min in total. Starts with: PlantVillage Dataset: Folder Structure, Class Distribution & Data Split.

1 h 5 min 9 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

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

Electric Load Forecasting with LSTM

6 video lessons with PDF guides, 53 min in total. Starts with: Hourly Electricity Load Data: Daily, Weekly, and Seasonal Patterns.

53 min 0 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

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

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

Here is the final result, the training curve of the Hybrid CNN-LSTM model, with training and validation loss at each epoch. The best model achieves a validation accuracy of about 97%, and training stops automatically when the model starts to plateau, thanks to early stopping. Let's get started. Hello, welcome to episode five of the Hybrid CNN-LSTM model series for early detection of lung diseases. The architecture is ready, now we will train it using techniques commonly used in research. Class weights for imbalanced data, learning rate scheduler, early stopping to prevent overfitting, and saving the best model checkpoint.

Step 1: Class weights

Create a file named train_underscore_hybrid.py We import the loader and the CNN-LSTM model from the previous episode. Remember, the training data is 74% pneumonia. Without handling, the model tends to favor the majority class. The solution is class weights, the number of data is divided by twice the number of each class. The result is normal getting a weight of about 1.94, pneumonia 0.67, so errors in the normal class are penalized almost three times more.

Step 2: Weighted loss, optimizer, scheduler

These weights are then added to the cross entropy loss. The optimizer is Adam, plus a scheduler reduceron plata or, which automatically halves the learning rate if the validation loss does not improve. We also create a function to calculate the validation loss and accuracy.

Step 3: Training loop and early stopping

Now the training loop with early stopping. Every time the validation loss reaches a new best, the model is saved to hybrid_underscore_best.pt and the patience counter is reset. If there is no improvement for 4 consecutive epochs, training is stopped. The maximum limit is 20 epochs. The history is saved to JSON and we plot the curve.

Step 4: Reading training results

Check the terminal. At the beginning, the validation loss fluctuates. This is normal because LSTM takes time to adjust. Around epoch 9, the validation loss reaches its lowest point with a validation accuracy of about 97%. After that, there is no improvement for 4 epochs, so early stopping stops training at epoch 13. The left graph shows the training loss continuously decreasing, while the validation loss starts to rise again, indicating the early signs of overfitting that have been successfully prevented. Done. We have handled the imbalanced data using class weights, employing a learning rate scheduler, early stopping, and saving the best model checkpoint. In the final episode, we will evaluate the model clinically, including sensitivity, specificity, ROC-AUC, and observe where the model looks with grade cam. Currently working on a thesis, research, or AI project in the field of medical imaging? Cerdas Inovasi Digital helps implement deep learning, from CNN, LSTM, hybrid models, up to grade cam interpretation and result writing. as well as offering deep learning courses with PyTorch. Want to master the entire series, from the Röntgen dataset to evaluation and grade cam? All 6 episodes, complete with PDF step-by-step guides and source code, are available for premium tutorial subscribers. Subscribe starting at Rp69.000 per month, save 28% with the 12-month package, or pay once Rp999.000 for lifetime access. Want just one class? Buy a single class with lifetime access. Subscribe now at the premium page cerdasinovasidigital.com Contact us via WhatsApp, or visit cerdasinovasidigital.com Thank you for watching, see you in the next episode. 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

0:46Step 1: Class weights

2:14Step 2: Weighted loss, optimizer, scheduler

3:25Step 3: Training loop and early stopping

6:05Step 4: Reading training results

Ask the class material

My notes

Questions & answers

Your instructor

▶ Video Lesson

Recommended classes for you

Need more than a video?

Transcript

0:03Introduction

0:46Step 1: Class weights

2:14Step 2: Weighted loss, optimizer, scheduler

3:25Step 3: Training loop and early stopping

6:05Step 4: Reading training results

Ask the class material

My notes

Questions & answers

Your instructor

Introduction

Step 1: Class weights

Step 2: Weighted loss, optimizer, scheduler

Step 3: Training loop and early stopping

Step 4: Reading training results

Introduction

Step 1: Class weights

Step 2: Weighted loss, optimizer, scheduler

Step 3: Training loop and early stopping

Step 4: Reading training results