Image Classifier

import gzip                  #used to uncomress the zip files

import numpy as np

import matplotlib.pyplot as plt

from tensorflow import keras

from tensorflow.keras import layers

# function to load images

def load_images(path):

   with gzip.open(path, 'rb') as f:

       data = np.frombuffer(f.read(), np.uint8, offset=16)

   return  data.reshape(-1, 28, 28)

def load_labels(path):

   with gzip.open(path, 'rb') as f:

       data = np.frombuffer(f.read(), np.uint8, offset=8)

       return data

x_train = load_images('data/train-images-idx3-ubyte.gz')

y_train = load_labels('data/train-labels-idx1-ubyte.gz')

x_test = load_images('data/t10k-images-idx3-ubyte.gz')

y_test = load_labels('data/t10k-labels-idx1-ubyte.gz')

print(x_train.shape, y_train.shape)

print(x_test.shape, y_test.shape)

# see the data

'''

class_names = [

   "T-shirt/top", "Trouser", "Pullover", "Dress", "Coat",

   "Sandal", "Shirt", "Sneaker", "Bag", "Ankle boot"

]

# Plot a 5×5 grid of training images

plt.figure(figsize=(8, 8))

for i in range(25):

   plt.subplot(5, 5, i + 1)

   plt.xticks([]); plt.yticks([])       # no axis ticks

   plt.grid(False)

   plt.imshow(x_train[i], cmap='gray')  # grayscale

   plt.xlabel(class_names[y_train[i]])

plt.suptitle("Fashion-MNIST training samples", fontsize=14)

plt.show()

'''

# -------------------------

# 3. Build the model

# -------------------------

model = keras.Sequential([

   layers.Flatten(input_shape=(28, 28)),

   layers.Dense(128, activation='relu'),

   layers.Dropout(0.2),

   layers.Dense(10, activation='softmax')

])

# -------------------------

# 4. Compile the model

# -------------------------

model.compile(

   optimizer='adam',

   loss='sparse_categorical_crossentropy',

   metrics=['accuracy']

)

# 2. Print initial weights (before training)

print("=== Weights BEFORE training ===")

for layer in model.layers:

   weights = layer.get_weights()

   print(f"Layer: {layer.name}")

   for w in weights:

       print(w)

   print("-" * 40)

# -------------------------

# 5. Train the model

# -------------------------

history = model.fit(

   x_train, y_train,

   epochs=10,

   batch_size=32,

   validation_split=0.1,

   verbose=1

)

# -------------------------

# 6. Evaluate

# -------------------------

test_loss, test_acc = model.evaluate(x_test, y_test, verbose=2)

print(f"\n✅ Test accuracy: {test_acc:.3f}")

# 4. Print weights after training

print("=== Weights AFTER training ===")

for layer in model.layers:

   weights = layer.get_weights()

   print(f"Layer: {layer.name}")

   for w in weights:

       print(w)

   print("-" * 40)

# -------------------------

# 7. Save model

# -------------------------

model.save("fashion_mnist_model.keras")

print('acuracy\n')

print(history.history['accuracy'])

print('val accuracy\n')

print(history.history['val_accuracy'])

# -------------------------

# 8. Plot training progress

# -------------------------

plt.figure(figsize=(10,4))

plt.subplot(1,2,1)

plt.plot(history.history['accuracy'], label='Training Accuracy')

plt.plot(history.history['val_accuracy'], label='Validation Accuracy')

plt.title('Model Accuracy')

plt.xlabel('Epoch')

plt.ylabel('Accuracy')

plt.legend()

plt.show()

# --- First training session ---

history1 = model.fit(X_train, y_train, epochs=50, validation_data=(X_val, y_val))

model.save("my_model.keras")

# --- Later training continuation ---

model2 = keras.models.load_model("my_model.keras")

history2 = model2.fit(X_train, y_train,

                      epochs=100,          # total target epochs

                      initial_epoch=50,    # continue from where we left off

                      validation_data=(X_val, y_val))