AI Projects

Apply everything you've learned by building complete AI projects from scratch.

Project 1: Sentiment Analyzer

from transformers import pipeline
import gradio as gr

classifier = pipeline("sentiment-analysis")

def analyze_sentiment(text):
    result = classifier(text)[0]
    return f"{result['label']} ({result['score']:.2%})"

demo = gr.Interface(
    fn=analyze_sentiment,
    inputs="text",
    outputs="text",
    title="AI Sentiment Analyzer",
    description="Analyze the sentiment of any text using AI"
)

demo.launch()

Project 2: Image Classifier

from transformers import ViTImageProcessor, ViTForImageClassification
from PIL import Image
import requests

processor = ViTImageProcessor.from_pretrained("google/vit-base-patch16-224")
model = ViTForImageClassification.from_pretrained("google/vit-base-patch16-224")

image = Image.open("photo.jpg")
inputs = processor(images=image, return_tensors="pt")

outputs = model(**inputs)
predicted_class = outputs.logits.argmax(-1).item()
label = model.config.id2label[predicted_class]

print(f"Prediction: {label}")

Project 3: AI Chatbot

from transformers import pipeline

chatbot = pipeline("conversational", model="microsoft/DialoGPT-medium")

conversation = [
    {"role": "user", "content": "Hello, can you help me learn Python?"},
    {"role": "assistant", "content": "Of course! I'd be happy to help you learn Python. What would you like to start with?"},
]

response = chatbot(conversation)
print(response[-1]['generated_text'])

Next Steps

• Deploy your AI models to cloud platforms (AWS, GCP, Azure)
• Learn MLOps for model deployment and monitoring
• Explore advanced architectures (LLMs, Diffusion Models)
• Build end-to-end AI applications
• Contribute to open-source AI projects

Summary

Congratulations! You've completed the AI with Python tutorial. You now have the skills to build intelligent AI applications. Keep practicing and building!