https://github.com/rjohnpaul/cnn_for_vision_mod
TensorFlow script (`fashion_mnist_models.py`) for building and training two models on the Fashion MNIST dataset. The script first creates a basic neural network and then extends it to a Convolutional Neural Network (CNN)
https://github.com/rjohnpaul/cnn_for_vision_mod
Last synced: 3 months ago
JSON representation
TensorFlow script (`fashion_mnist_models.py`) for building and training two models on the Fashion MNIST dataset. The script first creates a basic neural network and then extends it to a Convolutional Neural Network (CNN)
- Host: GitHub
- URL: https://github.com/rjohnpaul/cnn_for_vision_mod
- Owner: RJohnPaul
- License: mit
- Created: 2024-01-09T17:41:06.000Z (over 1 year ago)
- Default Branch: main
- Last Pushed: 2024-01-13T13:10:12.000Z (over 1 year ago)
- Last Synced: 2025-01-20T07:44:02.749Z (5 months ago)
- Language: Python
- Size: 3.43 MB
- Stars: 0
- Watchers: 2
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
--- ---
# Convolutional Neural Network (CNN) for Fashion MNIST Classification
This repo contains TensorFlow code for building and train Convolutional Neural Networks (CNNs) on the Fashion MNIST dataset. The code is provided in two models, one using a simple Dense neural network and the other using a Convolutional Neural Network.
## Table of Contents
- [Dense Neural Network](#dense-neural-network)
- [Convolutional Neural Network (CNN)](#convolutional-neural-network-cnn)
- [Visualization of Convolutional Layers](#visualization-of-convolutional-layers)
## Dense Neural Network
```python
import tensorflow as tf
# Load Fashion MNIST dataset
mnist = tf.keras.datasets.fashion_mnist
(training_images, training_labels), (test_images, test_labels) = mnist.load_data()
training_images = training_images / 255.0
test_images = test_images / 255.0
# Build and compile the model
model = tf.keras.models.Sequential([
tf.keras.layers.Flatten(),
tf.keras.layers.Dense(128, activation='relu'),
tf.keras.layers.Dense(10, activation='softmax')
])
model.compile(optimizer='adam', loss='sparse_categorical_crossentropy', metrics=['accuracy'])
# Train the model
model.fit(training_images, training_labels, epochs=5)
# Evaluate the model on the test set
test_loss, test_accuracy = model.evaluate(test_images, test_labels)
print(f'Test loss: {test_loss}, Test accuracy: {test_accuracy * 100}%')
```
## Convolutional Neural Network (CNN)
```python
import tensorflow as tf
# Load Fashion MNIST dataset
mnist = tf.keras.datasets.fashion_mnist
(training_images, training_labels), (test_images, test_labels) = mnist.load_data()
training_images = training_images.reshape(60000, 28, 28, 1) / 255.0
test_images = test_images.reshape(10000, 28, 28, 1) / 255.0
# Build and compile the CNN model
model = tf.keras.models.Sequential([
tf.keras.layers.Conv2D(64, (3, 3), activation='relu', input_shape=(28, 28, 1)),
tf.keras.layers.MaxPooling2D(2, 2),
tf.keras.layers.Conv2D(64, (3, 3), activation='relu'),
tf.keras.layers.MaxPooling2D(2,2),
tf.keras.layers.Flatten(),
tf.keras.layers.Dense(128, activation='relu'),
tf.keras.layers.Dense(10, activation='softmax')
])
model.compile(optimizer='adam', loss='sparse_categorical_crossentropy', metrics=['accuracy'])
# Print model summary
model.summary()
# Train the CNN model
model.fit(training_images, training_labels, epochs=5)
# Evaluate the CNN model on the test set
test_loss, test_accuracy = model.evaluate(test_images, test_labels)
print(f'Test loss: {test_loss}, Test accuracy: {test_accuracy * 100}%')
```
## Visualization of Convolutional Layers
This section of the code visualizes the activation of convolutional layers using matplotlib. It generates a 3x4 grid of images for the first, second, and third images in the test set.
```python
import matplotlib.pyplot as plt
f, axarr = plt.subplots(3, 4)
FIRST_IMAGE = 0
SECOND_IMAGE = 23
THIRD_IMAGE = 28
CONVOLUTION_NUMBER = 6
# Extract layer outputs for visualization
layer_outputs = [layer.output for layer in model.layers]
activation_model = tf.keras.models.Model(inputs=model.input, outputs=layer_outputs)
# Visualize convolutional layer activations
for x in range(0, 4):
f1 = activation_model.predict(test_images[FIRST_IMAGE].reshape(1, 28, 28, 1))[x]
axarr[0, x].imshow(f1[0, :, :, CONVOLUTION_NUMBER], cmap='inferno')
axarr[0, x].grid(False)
f2 = activation_model.predict(test_images[SECOND_IMAGE].reshape(1, 28, 28, 1))[x]
axarr[1, x].imshow(f2[0, :, :, CONVOLUTION_NUMBER], cmap='inferno')
axarr[1, x].grid(False)
f3 = activation_model.predict(test_images[THIRD_IMAGE].reshape(1, 28, 28, 1))[x]
axarr[2, x].imshow(f3[0, :, :, CONVOLUTION_NUMBER], cmap='inferno')
axarr[2, x].grid(False)
```
---