Project 16: CNN Image Classifier
ML Engineer
Builds on these lessons
Current Task
Objective
A CNN stacks Conv2D layers (learning spatial filters) with pooling layers (downsampling), ending in Dense layers for classification.
Task: build a small CNN for 28x28 grayscale images and print its summary.
index.py
import tensorflow as tf
from tensorflow.keras import layers, Sequential
model = Sequential([
layers.Conv2D(16, (3, 3), activation='relu', input_shape=(28, 28, 1)),
layers.MaxPooling2D((2, 2)),
layers.Flatten(),
layers.Dense(10, activation='softmax')
])
print(model.summary())
* Hint: Correct characters turn green, incorrect ones turn red.
Live Preview
🖼️
Verify your code to see the preview