Inisialisasi dan aktivasi

Masalah gradien yang tidak stabil (menghilang atau meledak) adalah tantangan yang sering muncul saat melatih deep neural network. Dalam latihan ini dan berikutnya, Anda akan memperluas arsitektur model yang Anda bangun untuk tugas klasifikasi kelayakan air minum agar lebih kebal terhadap masalah tersebut.

Sebagai langkah pertama, Anda akan memperbaiki inisialisasi bobot dengan menggunakan strategi inisialisasi He (Kaiming). Untuk melakukannya, Anda perlu memanggil initializer yang sesuai dari modul torch.nn.init, yang telah diimpor untuk Anda sebagai init. Selanjutnya, Anda akan memperbarui fungsi aktivasi dari ReLU bawaan ke ELU yang seringkali lebih baik.

Latihan ini adalah bagian dari kursus

Deep Learning Lanjutan dengan PyTorch

Petunjuk latihan

Panggil initializer He (Kaiming) pada atribut bobot layer kedua, fc2, serupa dengan yang dilakukan untuk fc1.
Panggil initializer He (Kaiming) pada atribut bobot layer ketiga, fc3, dengan mempertimbangkan perbedaan fungsi aktivasi yang digunakan pada layer akhir.
Perbarui fungsi aktivasi dalam metode forward() dari relu menjadi elu.

Latihan interaktif praktis

Cobalah latihan ini dengan menyelesaikan kode contoh berikut.

class Net(nn.Module):
    def __init__(self):
        super().__init__()
        self.fc1 = nn.Linear(9, 16)
        self.fc2 = nn.Linear(16, 8)
        self.fc3 = nn.Linear(8, 1)
        
        # Apply He initialization
        init.kaiming_uniform_(self.fc1.weight)
        ____(____)
        ____(____, ____)

    def forward(self, x):
        # Update ReLU activation to ELU
        x = nn.functional.relu(self.fc1(x))
        x = nn.functional.relu(self.fc2(x))
        x = nn.functional.sigmoid(self.fc3(x))
        return x

Edit dan Jalankan Kode

Latihan ini adalah bagian dari kursus

Deep Learning Lanjutan dengan PyTorch

SkillTag.level.intermediateSkillTag.label

4.8+

Mulai Kursus Gratis

Learn how to train neural networks in a robust way. In this chapter, you will use object-oriented programming to define PyTorch datasets and models and refresh your knowledge of training and evaluating neural networks. You will also get familiar with different optimizers and, finally, get to grips with various techniques that help mitigate the problems of unstable gradients so ubiquitous in neural nets training.

Exercise 1: PyTorch dan pemrograman berorientasi objek Exercise 2: Himpunan Data PyTorch Exercise 3: PyTorch DataLoader Exercise 4: Model PyTorch Exercise 5: Optimizer, pelatihan, dan evaluasi Exercise 6: Training loop Exercise 7: Optimizer Exercise 8: Evaluasi model Exercise 9: Gradien menghilang dan meledak Exercise 10: Inisialisasi dan aktivasi

Latihan Saat Ini

Exercise 11: Aktivasi: ReLU vs. ELU Exercise 12: Batch Normalization

Train neural networks to solve image classification tasks. In this chapter, you will learn how to handle image data in PyTorch and get to grips with convolutional neural networks (CNNs). You will practice training and evaluating an image classifier while learning about how to improve the model performance with data augmentation.

Exercise 1: Handling images with PyTorch Exercise 2: Image dataset Exercise 3: Data augmentation Exercise 4: Data augmentation in PyTorch Exercise 5: Convolutional Neural Networks Exercise 6: The convolutional layer Exercise 7: Building convolutional networks Exercise 8: Training image classifiers Exercise 9: Choosing augmentations Exercise 10: Dataset with augmentations Exercise 11: Image classifier training loop Exercise 12: Evaluating image classifiers Exercise 13: Multi-class model evaluation Exercise 14: Analyzing metrics per class

Build and train recurrent neural networks (RNNs) for processing sequential data such as time series, text, or audio. You will learn about the two most popular recurrent architectures, Long-Short Term Memory (LSTM) and Gated Recurrent Unit (GRU) networks, as well as how to prepare sequential data for model training. You will practice your skills by training and evaluating a recurrent model for predicting electricity consumption.

Exercise 1: Handling sequences with PyTorch Exercise 2: Generating sequences Exercise 3: Sequential Dataset Exercise 4: Recurrent Neural Networks Exercise 5: Sequential architectures Exercise 6: Building a forecasting RNN Exercise 7: LSTM and GRU cells Exercise 8: RNN vs. LSTM vs. GRU Exercise 9: LSTM network Exercise 10: GRU network Exercise 11: Training and evaluating RNNs Exercise 12: RNN training loop Exercise 13: Evaluating forecasting models

Build multi-input and multi-output models, demonstrating how they can handle tasks requiring more than one input or generating multiple outputs. You will explore how to design and train these models using PyTorch and delve into the crucial topic of loss weighting in multi-output models. This involves understanding how to balance the importance of different tasks when training a model to perform multiple tasks simultaneously.

Exercise 1: Multi-input models Exercise 2: Two-input dataset Exercise 3: Two-input model Exercise 4: Training two-input model Exercise 5: Multi-output models Exercise 6: Two-output Dataset and DataLoader Exercise 7: Two-output model architecture Exercise 8: Training multi-output models Exercise 9: Evaluation of multi-output models and loss weighting Exercise 10: Multi-output model evaluation Exercise 11: Loss weighting Exercise 12: Wrap-up