trainning.py

import os
import cv2
import numpy as np
import tensorflow as tf
from sklearn.utils import shuffle
from huggingface_hub import push_to_hub_keras
from sklearn.model_selection import train_test_split
from sklearn.utils.class_weight import compute_class_weight
from tensorflow.keras.preprocessing.image import ImageDataGenerator

# Environment variable for Hugging Face token
sac = os.getenv('accesstoken')

class_names = ['buildings', 'forest', 'glacier']
class_names_label = {class_name: i for i, class_name in enumerate(class_names)}
IMAGE_SIZE = (150, 150)

def load_data():
    DIRECTORY = "imgdataset"
    CATEGORY = ["seg_train", "seg_test"]
    output = []
    for category in CATEGORY:
        path = os.path.join(DIRECTORY, category)
        images = []
        labels = []
        print("Loading {}".format(category))
        for folder in os.listdir(path):
            label = class_names_label[folder]
            for file in os.listdir(os.path.join(path, folder)):
                img_path = os.path.join(os.path.join(path, folder), file)
                image = cv2.imread(img_path)
                image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
                image = cv2.resize(image, IMAGE_SIZE)
                images.append(image)
                labels.append(label)
        images = np.array(images, dtype='float32')
        labels = np.array(labels, dtype='int32')
        output.append((images, labels))
    return output

(train_images, train_labels), (test_images, test_labels) = load_data()
train_images, train_labels = shuffle(train_images, train_labels, random_state=25)

# Split the training set into training and validation sets
train_images, val_images, train_labels, val_labels = train_test_split(
    train_images, train_labels, test_size=0.2, random_state=42
)

# Data Augmentation
datagen = ImageDataGenerator(
    rotation_range=20,
    width_shift_range=0.2,
    height_shift_range=0.2,
    shear_range=0.2,
    zoom_range=0.2,
    horizontal_flip=True,
    fill_mode='nearest'
)

# Calculate class weights to handle data imbalance
# class_weights = compute_class_weight('balanced', np.unique(train_labels), train_labels)
class_weights = compute_class_weight(class_weight='balanced',classes=np.unique(train_labels),y= train_labels)

# Model Architecture
model = tf.keras.models.Sequential([
    tf.keras.layers.Conv2D(32, (3, 3), activation='relu', input_shape=(150, 150, 3)),
    tf.keras.layers.MaxPooling2D(2, 2),
    tf.keras.layers.Conv2D(64, (3, 3), activation='relu'),
    tf.keras.layers.MaxPooling2D(2, 2),
    tf.keras.layers.Conv2D(128, (3, 3), activation='relu'),
    tf.keras.layers.MaxPooling2D(2, 2),
    tf.keras.layers.Conv2D(128, (3, 3), activation='relu'),
    tf.keras.layers.MaxPooling2D(2, 2),
    tf.keras.layers.Flatten(),
    tf.keras.layers.Dense(512, activation='relu'),
    tf.keras.layers.Dense(3, activation='softmax')
])

# Model Compilation
model.compile(optimizer='adam', loss='sparse_categorical_crossentropy', metrics=['accuracy'])

# Model Training with Data Augmentation
batch_size = 32
epochs = 10

history = model.fit(
    datagen.flow(train_images, train_labels, batch_size=batch_size),
    steps_per_epoch=len(train_images) // batch_size,
    epochs=epochs,
    validation_data=(val_images, val_labels),
    class_weight=dict(enumerate(class_weights))
)

# Model Evaluation
model.evaluate(test_images, test_labels)

# Save the model
model.save("model_with_augmentation.keras")

# Upload the model to your Hugging Face space repository
push_to_hub_keras(
    model,
    repo_id="okeowo1014/imageaugmentationa",
    commit_message="Model with data augmentation and class weights",
    tags=["image-classifier", "data-augmentation", "class-weights"],
    include_optimizer=True,
    token=sac
)