Mengenal LightningModule

Bersiaplah membangun LightningModule pertama Anda! Dalam latihan praktis ini, Anda akan menyiapkan struktur inti alur kerja klasifikasi. Anda akan mendefinisikan sebuah layer linear, meneruskan data melaluinya di metode forward, dan menghitung loss pada langkah pelatihan. Struktur yang rapi ini memberi Anda dasar yang kuat untuk mulai bereksperimen dengan model Anda.

torch dan lightning.pytorch yang diimpor sebagai pl telah dimuat sebelumnya untuk Anda.

Latihan ini adalah bagian dari kursus

Model AI yang Dapat Diskalakan dengan PyTorch Lightning

Petunjuk latihan

Definisikan kelas LightModel yang mewarisi pl.LightningModule.
Definisikan sebuah layer linear untuk mentransformasikan masukan Anda, dengan asumsi fitur masukan berjumlah 16 dan terdapat 10 kelas keluaran.

Latihan interaktif praktis

Cobalah latihan ini dengan menyelesaikan kode contoh berikut.

# Define the model class
class LightModel(____):
  	# Define a linear layer to transform your input
    def __init__(self):
        super().__init__()
        self.layer = ____
    def forward(self, x):
        return self.layer(x)
    def training_step(self, batch, batch_idx):
        x, y = batch
        logits = self(x)
        loss = torch.nn.functional.cross_entropy(logits, y)
        return loss

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: Pengantar PyTorch Lightning Exercise 2: Mengenal LightningModule

Latihan Saat Ini

Exercise 3: Menjalankan Lightning Trainer Exercise 4: Mendefinisikan model dengan LightningModule Exercise 5: Penggunaan LightningModule Exercise 6: Menguasai metode init Exercise 7: Menyempurnakan metode forward Exercise 8: Menerapkan logika pelatihan Exercise 9: Mengimplementasikan langkah pelatihan Exercise 10: Mengonfigurasi pengoptimal Exercise 11: Melatih dan mengevaluasi

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: Applying dynamic quantization Exercise 2: Apply dynamic quantization Exercise 3: Comparing quantized model performance Exercise 4: Implementing model pruning techniques Exercise 5: Apply pruning to a linear layer Exercise 6: Finalize pruning by removing the mask Exercise 7: Exporting models with TorchScript Exercise 8: Choosing the right conversion method Exercise 9: Optimizing models for scalability Exercise 10: Recap: Scalable AI Models with PyTorch Lightning