Memperbarui bobot secara manual

Sekarang setelah Anda tahu cara mengakses bobot dan bias, Anda akan melakukan secara manual tugas yang biasanya dikerjakan oleh optimizer PyTorch. Meskipun PyTorch mengotomatiskannya, berlatih secara manual membantu Anda membangun intuisi tentang cara model belajar dan menyesuaikan diri. Pemahaman ini akan berguna saat melakukan debug atau penyetelan halus jaringan saraf.

Sebuah jaringan saraf dengan tiga lapisan telah dibuat dan disimpan dalam variabel model. Jaringan ini telah digunakan untuk forward pass dan loss beserta turunannya telah dihitung. Laju pembelajaran default, lr, telah dipilih untuk mengalikan gradien saat melakukan pembaruan.

Latihan ini adalah bagian dari kursus

Pengantar Deep Learning dengan PyTorch

Latihan interaktif praktis

Cobalah latihan ini dengan menyelesaikan kode contoh berikut.

weight0 = model[0].weight
weight1 = model[1].weight
weight2 = model[2].weight

# Access the gradients of the weight of each linear layer
grads0 = ____
grads1 = ____
grads2 = ____

Edit dan Jalankan Kode

Latihan ini adalah bagian dari kursus

Pengantar Deep Learning dengan PyTorch

SkillTag.level.intermediateSkillTag.label

4.8+

Mulai Kursus Gratis

Self-driving cars, smartphones, search engines... Deep learning is now everywhere. Before you begin building complex models, you will become familiar with PyTorch, a deep learning framework. You will learn how to manipulate tensors, create PyTorch data structures, and build your first neural network in PyTorch with linear layers.

Exercise 1: Introduction to deep learning with PyTorch Exercise 2: Getting started with PyTorch tensors Exercise 3: Checking and adding tensors Exercise 4: Neural networks and layers Exercise 5: Linear layer network Exercise 6: Understanding weights Exercise 7: Hidden layers and parameters Exercise 8: Your first neural network Exercise 9: Stacking linear layers Exercise 10: Counting the number of parameters

To train a neural network in PyTorch, you will first need to understand additional components, such as activation and loss functions. You will then realize that training a network requires minimizing that loss function, which is done by calculating gradients. You will learn how to use these gradients to update your model's parameters.

Exercise 1: Mengenal fungsi aktivasi Exercise 2: Aktifkan pemahaman Anda!Exercise 3: Fungsi sigmoid dan softmax Exercise 4: Menjalankan forward pass Exercise 5: Membangun pengklasifikasi biner di PyTorch Exercise 6: Dari regresi ke klasifikasi multi-kelas Exercise 7: Menggunakan fungsi loss untuk menilai prediksi model Exercise 8: Membuat label one-hot encoded Exercise 9: Menghitung cross-entropy loss Exercise 10: Menggunakan turunan untuk memperbarui parameter model Exercise 11: Mengakses parameter model Exercise 12: Memperbarui bobot secara manual

Latihan Saat Ini

Exercise 13: Menggunakan optimizer PyTorch

Now that you've learned the key components of a neural network, you'll train one using a training loop. You'll explore potential issues like vanishing gradients and learn strategies to address them, such as alternative activation functions and tuning learning rate and momentum.

Exercise 1: A deeper dive into loading data Exercise 2: Using TensorDataset Exercise 3: Using DataLoader Exercise 4: Writing our first training loop Exercise 5: Using the MSELoss Exercise 6: Writing a training loop Exercise 7: ReLU activation functions Exercise 8: Implementing ReLU Exercise 9: Implementing leaky ReLU Exercise 10: Understanding activation functions Exercise 11: Learning rate and momentum Exercise 12: Experimenting with learning rate Exercise 13: Experimenting with momentum

Training a deep learning model is an art, and to make sure our model is trained correctly, we need to keep track of certain metrics during training, such as the loss or the accuracy. We will learn how to calculate such metrics and how to reduce overfitting.

Exercise 1: Layer initialization and transfer learning Exercise 2: Fine-tuning process Exercise 3: Freeze layers of a model Exercise 4: Layer initialization Exercise 5: Evaluating model performance Exercise 6: Writing the evaluation loop Exercise 7: Calculating accuracy using torchmetrics Exercise 8: Fighting overfitting Exercise 9: Experimenting with dropout Exercise 10: Understanding overfitting Exercise 11: Improving model performance Exercise 12: Implementing random search Exercise 13: Wrap-up video