Membandingkan kinerja model terkuantisasi

Memahami peningkatan kinerja tidak hanya soal akurasi. Model yang dikuantisasi sering memberikan waktu inferensi yang lebih cepat—keunggulan utama dalam skenario deployment. Anda akan mengukur berapa lama waktu yang dibutuhkan model asli dan model terkuantisasi untuk memproses himpunan uji.

Fungsi measure_time() telah didefinisikan. Fungsi ini mengatur model ke mode evaluasi, menjalankan forward pass pada semua batch di dataloader, dan mengembalikan waktu yang berlalu.

model (model asli) dan model_quantized (versi terkuantisasi) telah dimuat bersama dengan test_loader.

Latihan ini adalah bagian dari kursus

Model AI yang Dapat Diskalakan dengan PyTorch Lightning

Petunjuk latihan

Hitung waktu inferensi untuk model asli dan model terkuantisasi.
Cetak kedua waktu tersebut dengan pembulatan dua angka desimal.

Latihan interaktif praktis

Cobalah latihan ini dengan menyelesaikan kode contoh berikut.

# Measure inference time of the original model
original_time = measure_time(____)

# Measure inference time of the quantized model
quant_time = measure_time(____)

# Print results
print(f"Original Model Time: {____}s")
print(f"Quantized Model Time: {____}s")

Edit dan Jalankan Kode

Latihan ini adalah bagian dari kursus

Model AI yang Dapat Diskalakan dengan PyTorch Lightning

SkillTag.level.intermediateSkillTag.label

4.8+

Mulai Kursus Gratis

In this chapter, we'll explore how PyTorch Lightning simplifies the development and deployment of scalable AI models. Starting with foundational concepts, we'll go through the core structure of a PyTorch Lightning project, including essential components like the LightningModule and Trainer, to set a strong foundation for more advanced AI solutions.

Exercise 1: Introduction to PyTorch Lightning Exercise 2: Introducing the LightningModule Exercise 3: Running the Lightning Trainer Exercise 4: Defining models with LightningModule Exercise 5: Usage of the LightningModule Exercise 6: Mastering the init method Exercise 7: Perfecting the forward method Exercise 8: Implementing training logic Exercise 9: Implementing the training step Exercise 10: Configuring the optimizer Exercise 11: Training and evaluating

We'll dive deeper into PyTorch Lightning to efficiently manage data and refine model training in this chapter. We'll learn how to create modular and reusable data workflows with LightningDataModule, evaluate your models accurately through validation and testing, and enhance training processes using Lightning Callbacks to automate model improvement and avoid overfitting.

Exercise 1: Managing data with LightningDataModule Exercise 2: Splitting data with LightningDataModule Exercise 3: Creating a train DataLoader Exercise 4: Incorporating validation and testing Exercise 5: Implementing the validation step Exercise 6: Evaluate model accuracy using Torchmetrics Exercise 7: Enhancing training with Lightning callbacks Exercise 8: Classifying Lightning callbacks Exercise 9: Optimizing model training with Lightning

Learn to prepare deep learning models for real-world deployment by making them leaner and faster. This chapter introduces techniques such as dynamic quantization, pruning, and TorchScript conversion, helping you reduce model size and latency without sacrificing accuracy

Exercise 1: Menerapkan kuantisasi dinamis Exercise 2: Terapkan kuantisasi dinamis Exercise 3: Membandingkan kinerja model terkuantisasi

Latihan Saat Ini

Exercise 4: Menerapkan teknik pruning model Exercise 5: Terapkan pruning pada lapisan linear Exercise 6: Finalisasi pruning dengan menghapus mask Exercise 7: Mengekspor model dengan TorchScript Exercise 8: Memilih metode konversi yang tepat Exercise 9: Mengoptimalkan model untuk skalabilitas Exercise 10: Rekap: Model AI yang Dapat Diskalakan dengan PyTorch Lightning