Lesson 2: Image Classification (Basic Model Project)

🧰 इस प्रोजेक्ट में क्या-क्या इस्तेमाल होगा?

• Python Programming
• TensorFlow / Keras Library
• Image Dataset (जैसे CIFAR-10 या Custom)
• Google Colab या Jupyter Notebook

📝 Step-by-Step Process

1. 📥 Step 1: Dataset Load करना (जैसे CIFAR-10 from Keras)
2. 🧹 Step 2: Preprocessing – Resize, Normalize Images
3. 🏗️ Step 3: CNN Model बनाना (Using Keras Sequential API)
4. 📊 Step 4: Model को Train और Evaluate करना
5. 🖼️ Step 5: नई तस्वीर पर Prediction करना

Bonus: Accuracy और Loss को Graph में Visualize करें

from tensorflow.keras.datasets import cifar10
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Conv2D, MaxPooling2D, Flatten, Dense

# Load Data
(x_train, y_train), (x_test, y_test) = cifar10.load_data()

# Normalize
x_train, x_test = x_train / 255.0, x_test / 255.0

# Model
model = Sequential([
  Conv2D(32, (3,3), activation='relu', input_shape=(32,32,3)),
  MaxPooling2D((2,2)),
  Flatten(),
  Dense(64, activation='relu'),
  Dense(10, activation='softmax')
])

model.compile(optimizer='adam', loss='sparse_categorical_crossentropy', metrics=['accuracy'])
model.fit(x_train, y_train, epochs=5, validation_data=(x_test, y_test))