Skip to content

Training Pipeline - PyTorch Beginner 06

In this part we improve the code from the last part and will learn how a complete training pipeline is implemented in PyTorch.


Learn all the basics you need to get started with this deep learning framework! In this part we improve the code from the last part and will learn how a complete training pipeline is implemented in PyTorch. We replace the manually computed loss and weight updates with a loss and an optimizer from the PyTorch framework, which can do the optimization for us. We will then see how a PyTorch model is implemented and used for the forward pass.

  • Training Pipeline in PyTorch
  • Model Design
  • Loss and Optimizer
  • Automatic Training steps with forward pass, backward pass, and weight updates

All code from this course can be found on GitHub.

Introduce Loss and Optimizer

# 1) Design model (input, output, forward pass with different layers)
# 2) Construct loss and optimizer
# 3) Training loop
#       - Forward = compute prediction and loss
#       - Backward = compute gradients
#       - Update weights

import torch
import torch.nn as nn

# Linear regression
# f = w * x 

# here : f = 2 * x

# 0) Training samples
X = torch.tensor([1, 2, 3, 4], dtype=torch.float32)
Y = torch.tensor([2, 4, 6, 8], dtype=torch.float32)

# 1) Design Model: Weights to optimize and forward function
w = torch.tensor(0.0, dtype=torch.float32, requires_grad=True)

def forward(x):
    return w * x

print(f'Prediction before training: f(5) = {forward(5).item():.3f}')

# 2) Define loss and optimizer
learning_rate = 0.01
n_iters = 100

# callable function
loss = nn.MSELoss()

optimizer = torch.optim.SGD([w], lr=learning_rate)

# 3) Training loop
for epoch in range(n_iters):
    # predict = forward pass
    y_predicted = forward(X)

    # loss
    l = loss(Y, y_predicted)

    # calculate gradients = backward pass
    l.backward()

    # update weights
    optimizer.step()

    # zero the gradients after updating
    optimizer.zero_grad()

    if epoch % 10 == 0:
        print('epoch ', epoch+1, ': w = ', w, ' loss = ', l)

print(f'Prediction after training: f(5) = {forward(5).item():.3f}')

Introduce the model class

# 1) Design model (input, output, forward pass with different layers)
# 2) Construct loss and optimizer
# 3) Training loop
#       - Forward = compute prediction and loss
#       - Backward = compute gradients
#       - Update weights

import torch
import torch.nn as nn

# Linear regression
# f = w * x 

# here : f = 2 * x

# 0) Training samples, watch the shape!
X = torch.tensor([[1], [2], [3], [4]], dtype=torch.float32)
Y = torch.tensor([[2], [4], [6], [8]], dtype=torch.float32)

n_samples, n_features = X.shape
print(f'#samples: {n_samples}, #features: {n_features}')
# 0) create a test sample
X_test = torch.tensor([5], dtype=torch.float32)

# 1) Design Model, the model has to implement the forward pass!
# Here we can use a built-in model from PyTorch
input_size = n_features
output_size = n_features

# we can call this model with samples X
model = nn.Linear(input_size, output_size)

'''
class LinearRegression(nn.Module):
    def __init__(self, input_dim, output_dim):
        super(LinearRegression, self).__init__()
        # define diferent layers
        self.lin = nn.Linear(input_dim, output_dim)
    def forward(self, x):
        return self.lin(x)
model = LinearRegression(input_size, output_size)
'''

print(f'Prediction before training: f(5) = {model(X_test).item():.3f}')

# 2) Define loss and optimizer
learning_rate = 0.01
n_iters = 100

loss = nn.MSELoss()
optimizer = torch.optim.SGD(model.parameters(), lr=learning_rate)

# 3) Training loop
for epoch in range(n_iters):
    # predict = forward pass with our model
    y_predicted = model(X)

    # loss
    l = loss(Y, y_predicted)

    # calculate gradients = backward pass
    l.backward()

    # update weights
    optimizer.step()

    # zero the gradients after updating
    optimizer.zero_grad()

    if epoch % 10 == 0:
        [w, b] = model.parameters() # unpack parameters
        print('epoch ', epoch+1, ': w = ', w[0][0].item(), ' loss = ', l)

print(f'Prediction after training: f(5) = {model(X_test).item():.3f}')

FREE VS Code / PyCharm Extensions I Use

鉁 Write cleaner code with Sourcery, instant refactoring suggestions: Link*

* This is an affiliate link. By clicking on it you will not have any additional costs. Instead, you will support my project. Thank you! 馃檹