Melatih model multi-output

Saat melatih model dengan banyak keluaran, sangat penting untuk memastikan bahwa fungsi loss didefinisikan dengan benar.

Dalam kasus ini, model menghasilkan dua keluaran: prediksi untuk alfabet dan karakter. Untuk masing-masing, terdapat label ground truth yang sesuai, yang memungkinkan Anda menghitung dua loss terpisah: satu akibat kesalahan klasifikasi alfabet, dan satu lagi akibat kesalahan klasifikasi karakter. Karena pada keduanya Anda menangani tugas klasifikasi multi-label, loss Cross-Entropy dapat diterapkan setiap kali.

Namun, gradient descent hanya dapat mengoptimalkan satu fungsi loss. Oleh karena itu, Anda akan mendefinisikan total loss sebagai jumlah dari loss alfabet dan loss karakter.

Latihan ini adalah bagian dari kursus

Deep Learning Lanjutan dengan PyTorch

Petunjuk latihan

Hitung loss klasifikasi alfabet dan simpan ke loss_alpha.
Hitung loss klasifikasi karakter dan simpan ke loss_char.
Hitung total loss sebagai penjumlahan dari dua loss parsial dan simpan ke loss.

Latihan interaktif praktis

Cobalah latihan ini dengan menyelesaikan kode contoh berikut.

net = Net()
criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(net.parameters(), lr=0.05)

for epoch in range(1):
    for images, labels_alpha, labels_char in dataloader_train:
        optimizer.zero_grad()
        outputs_alpha, outputs_char = net(images)
        # Compute alphabet classification loss
        loss_alpha = ____
        # Compute character classification loss
        loss_char = ____
        # Compute total loss
        loss = ____
        loss.backward()
        optimizer.step()

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 and object-oriented programming Exercise 2: PyTorch Dataset Exercise 3: PyTorch DataLoader Exercise 4: PyTorch Model Exercise 5: Optimizers, training, and evaluation Exercise 6: Training loop Exercise 7: Optimizers Exercise 8: Model evaluation Exercise 9: Vanishing and exploding gradients Exercise 10: Initialization and activation Exercise 11: Activations: 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: Model multi-masukan Exercise 2: Himpunan data dua masukan Exercise 3: Model dua masukan Exercise 4: Melatih model dengan dua masukan Exercise 5: Model multi-output Exercise 6: Dataset dan DataLoader dengan Dua Keluaran Exercise 7: Arsitektur model dua keluaran Exercise 8: Melatih model multi-output

Latihan Saat Ini

Exercise 9: Evaluasi model multi-output dan pembobotan loss Exercise 10: Evaluasi model multi-output Exercise 11: Pembobotan loss Exercise 12: Penutup