Animal Species Prediction with VGG16(AI)

🐾 AI Mini Project: Animal Species Prediction with VGG16

This tutorial shows how to build an animal image classifier using TensorFlow and VGG16. Make sure your dataset is organized in folders by class within the path_to_dataset directory.

import tensorflow as tf
from tensorflow.keras.applications import VGG16
from tensorflow.keras.preprocessing.image import ImageDataGenerator
from tensorflow.keras import layers, models

# Load VGG16 model + higher level layers
base_model = VGG16(weights='imagenet', include_top=False, input_shape=(224, 224, 3))

# Freeze convolutional layers
for layer in base_model.layers:
    layer.trainable = False

# Create new model on top
model = models.Sequential([
    base_model,
    layers.Flatten(),
    layers.Dense(256, activation='relu'),
    layers.Dropout(0.5),
    layers.Dense(10, activation='softmax')  # Assuming 10 classes
])

# Compile model
model.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])

# Data generators
train_datagen = ImageDataGenerator(rescale=1./255, validation_split=0.2)
train_generator = train_datagen.flow_from_directory(
    'path_to_dataset',
    target_size=(224, 224),
    batch_size=32,
    class_mode='categorical',
    subset='training'
)
validation_generator = train_datagen.flow_from_directory(
    'path_to_dataset',
    target_size=(224, 224),
    batch_size=32,
    class_mode='categorical',
    subset='validation'
)

# Train model
model.fit(train_generator, epochs=10, validation_data=validation_generator)

💡 Tip: Replace path_to_dataset with the actual path to your image dataset organized by class folders.