DL eBook Fundamentals of Deep Learning
Home Read Lab Manual Resources Glossary Admin

Exp 3 — CNN for MRI dataset

Record-ready template Fill placeholders with your dataset, code, outputs, plots, and viva.
AIML355 • Fundamentals of Deep Learning Lab

EXP03 — CNN for MRI Dataset

Record-ready template Replace placeholders with your final work (code + outputs + screenshots).
Submission checklist
Aim ✓ • Environment ✓ • Dataset ✓ • Procedure ✓ • Code ✓ • Output ✓ • Discussion ✓ • Viva ✓

1) Aim

To implement a Convolutional Neural Network (CNN) for an MRI dataset in Python.

Learning outcomes
  • Load and preprocess MRI images (resize, normalization, split).
  • Design a CNN with conv/pool layers and evaluate performance.
  • Use confusion matrix and classification report for results.

2) Requirements / Environment

Software
  • Python 3.10+ (recommended)
  • TensorFlow/Keras (or PyTorch where applicable)
  • NumPy, Pandas, Matplotlib
  • Jupyter/Colab optional
Hardware
  • CPU is OK for small runs; GPU optional
  • RAM: 4–8 GB+ recommended
Reproducibility
Record library versions and random seed in your final report.

3) Dataset

  • Source: Use an MRI classification dataset (e.g., brain MRI tumor/no-tumor). Mention source URL/citation in your final report.
  • Features/Labels: [Describe X and y; mention classes if classification]
  • Split: [Train/Validation/Test or K-fold]
  • Preprocessing: [Scaling/Normalization, resizing, tokenization, etc.]

4) Procedure / Steps

  1. Load dataset and perform preprocessing.
  2. Define model architecture and justify key choices.
  3. Compile model (loss + optimizer + metrics).
  4. Train with validation and log curves.
  5. Evaluate on test set and compute required metrics.
  6. Summarize observations and limitations.
Model hint
Conv2D → ReLU → MaxPool blocks, then Dense classifier. Consider dropout and batch norm.

5) Code (Skeleton)

Paste your complete runnable code below (or attach notebook link in the final submission).

import tensorflow as tf
from tensorflow import keras

# TODO: load images from folders
train_ds = keras.utils.image_dataset_from_directory('DATASET_DIR', image_size=(IMG, IMG), batch_size=32)
val_ds   = keras.utils.image_dataset_from_directory('DATASET_DIR', validation_split=0.2, subset='validation', seed=42, image_size=(IMG, IMG))

model = keras.Sequential([
  keras.layers.Rescaling(1./255),
  keras.layers.Conv2D(32, 3, activation='relu'),
  keras.layers.MaxPooling2D(),
  keras.layers.Conv2D(64, 3, activation='relu'),
  keras.layers.MaxPooling2D(),
  keras.layers.Flatten(),
  keras.layers.Dense(128, activation='relu'),
  keras.layers.Dense(NUM_CLASSES, activation='softmax')
])
model.compile(optimizer='adam', loss='sparse_categorical_crossentropy', metrics=['accuracy'])

6) Results / Output

  • Metrics: [Write your final values: accuracy/F1 or MAE/MSE]
  • Plots: [Attach loss/metric curves; prediction vs actual plots if forecasting]
  • Screenshots: [Paste screenshots of outputs, confusion matrix, sample predictions]

7) Observations / Discussion

  • [Observation 1: what changed when you tuned epochs/batch size?]
  • [Observation 2: evidence of overfitting/underfitting?]
  • [Observation 3: what improved performance (augmentation, regularization, fine-tuning)?]

8) Conclusion

Write 3–6 lines summarizing what you implemented, key result, and what you learned.

9) Viva Questions

  1. Why do CNNs work well for images?
  2. What is the role of pooling layers?
  3. What is the difference between training and validation data?
  4. Explain overfitting and two ways to reduce it.
  5. Why do we normalize/scale inputs?
  6. What does batch size and epoch mean?
  7. How do you choose a loss function for a task?

10) Post-lab Assignment

  • Try data augmentation and report improvement.
  • Experiment with batch normalization or dropout.
Tip: press Esc to close.