nipunsgeeth/Cats_vs_Dogs_v2

Cats vs Dogs — EfficientNetB0 Classifier

This repository contains a convolutional neural network model trained to classify images of cats and dogs.
The model uses EfficientNetB0 (pretrained on ImageNet) as a base + custom classification head, and was trained on the cats_vs_dogs dataset via TensorFlow Datasets.

---

✅ Model Details

Item	Description
Base architecture	EfficientNetB0 (pretrained, top layers removed)
Input shape	224 × 224 × 3 (RGB image)
Output	Single sigmoid output — probability that the image is a “dog”
Training data	cats_vs_dogs (split ~80% train / 20% validation)
Preprocessing	Resize → 224×224, Normalize pixels to [0,1], optional data-augmentation
Loss / Optimizer	binary_crossentropy, Adam
Training strategy	Feature-extraction (base frozen) → Optional fine-tuning (unfreeze part of base)
Evaluation metric	Accuracy (binary classification)

---

📈 Performance (Your results — update after training)

Metric	Value
Validation accuracy (after feature-extraction)	~0.5098…
Validation accuracy (after fine-tuning)	~0.7052…

⚠️ These metrics depend on training/validation split, augmentation, fine-tuning. Consider re-training or cross-validation for better estimates.

---

💡 Inference / Usage Example

import tensorflow as tf
import numpy as np
from tensorflow.keras.preprocessing import image

# Load model (assuming you saved as model.keras or .h5)
model = tf.keras.models.load_model("path/to/your_model.keras")

# Load and preprocess a new image
img = image.load_img("path/to/image.jpg", target_size=(224, 224))
img = image.img_to_array(img) / 255.0
img = np.expand_dims(img, axis=0)

# Predict
prob = model.predict(img)[0][0]
if prob >= 0.5:
    print("Dog 🐶 — confidence:", prob)
else:
    print("Cat 🐱 — confidence:", 1 - prob)