From 2180c68999eb8dc0c7bcec015b2703f5b8b20223 Mon Sep 17 00:00:00 2001 From: zhang Date: Wed, 4 May 2022 08:47:54 +0800 Subject: ndarray axis --- learn_torch/basics/nd_grad.py | 42 ++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 42 insertions(+) create mode 100644 learn_torch/basics/nd_grad.py (limited to 'learn_torch/basics/nd_grad.py') diff --git a/learn_torch/basics/nd_grad.py b/learn_torch/basics/nd_grad.py new file mode 100644 index 0000000..d8af59e --- /dev/null +++ b/learn_torch/basics/nd_grad.py @@ -0,0 +1,42 @@ +# -*- coding: utf-8 -*- +import numpy as np +import math + +# Create random input and output data +x = np.linspace(-math.pi, math.pi, 2000) +y = np.sin(x) + +# Randomly initialize weights +a = np.random.randn() +b = np.random.randn() +c = np.random.randn() +d = np.random.randn() + +learning_rate = 1e-3 +for t in range(500): + # Forward pass: compute predicted y + # y = a + b x + c x^2 + d x^3 + y_pred = a + b * x + c * x ** 2 + d * x ** 3 + + # Compute and print loss + loss = np.square(y_pred - y).mean() + if t % 10 == 0: + print(x.shape, y_pred.shape, y.shape) + print(t, loss) + + # Backprop to compute gradients of a, b, c, d with respect to loss + grad_y_pred = 2.0 * (y_pred - y) + # grad_y_pred = 2.0 * (y - y_pred) + + grad_a = grad_y_pred.mean() + grad_b = (grad_y_pred * x).mean() + grad_c = (grad_y_pred * x ** 2).mean() + grad_d = (grad_y_pred * x ** 3).mean() + + # Update weights + a -= learning_rate * grad_a + b -= learning_rate * grad_b + c -= learning_rate * grad_c + d -= learning_rate * grad_d + +print(f'Result: y = {a} + {b} x + {c} x^2 + {d} x^3') \ No newline at end of file -- cgit v1.2.3