47 lines
1.2 KiB
Python
47 lines
1.2 KiB
Python
# this is a recap
|
|
|
|
# a training pipeline generally consists of 3 steps:
|
|
# 1. Design model (input, output size, forward pass (layers))
|
|
# 2. Construct loss and optimizer
|
|
# 3. Training loop
|
|
# - forward pass: compute prediction
|
|
# - backward pass: gradient computation
|
|
# - update parameters
|
|
|
|
# (iterate step 3)
|
|
|
|
import torch
|
|
import torch.nn as nn
|
|
|
|
X = torch.tensor([[1], [2], [3], [4]], dtype=torch.float32)
|
|
Y = torch.tensor([[3], [6], [9], [12]], dtype=torch.float32)
|
|
|
|
X_test = torch.tensor([5], dtype=torch.float32)
|
|
|
|
n_samples, n_features = X.shape
|
|
input_size = output_size = n_features
|
|
|
|
learning_rate = 0.01
|
|
n_iter = 100
|
|
|
|
|
|
model = nn.Linear(input_size, output_size, bias=False)
|
|
loss = nn.MSELoss()
|
|
optimizer = torch.optim.SGD(model.parameters(), lr = learning_rate)
|
|
|
|
print(f'Prediction before training: f(5) = {model(X_test).item():.3f}')
|
|
for epoch in range(n_iter):
|
|
Y_pred = model(X)
|
|
l = loss(Y, Y_pred)
|
|
l.backward()
|
|
optimizer.step()
|
|
optimizer.zero_grad()
|
|
|
|
[w] = model.parameters()
|
|
w = w.item()
|
|
|
|
if epoch % 10 == 0:
|
|
print(f'Epoch {epoch}: w = {w:.3f}, loss = {l:.5f}')
|
|
|
|
print(f'Prediction after training: f(5) = {model(X_test).item():.3f}')
|