Help Center/
FunctionGraph/
User Guide/
Dependency Management/
Public Dependency Demos/
Linear Regression with PyTorch
Updated on 2023-11-16 GMT+08:00
Linear Regression with PyTorch
Adding Torch on Function Details Page
Figure 1 Adding Torch
![](https://support.huaweicloud.com/eu/usermanual-functiongraph/en-us_image_0000001709359028.png)
Importing Torch to Code
# -*- coding:utf-8 -*- import json # Import Torch. import torch as t import numpy as np def handler (event, context): print("start training!") train() print("finished!") return { "statusCode": 200, "isBase64Encoded": False, "body": json.dumps(event), "headers": { "Content-Type": "application/json" } } def get_fake_data(batch_size=8): x = t.rand(batch_size, 1) * 20; y = x * 2 + (1 + t.randn(batch_size, 1)) * 3 return x, y def train(): t.manual_seed(1000) x, y = get_fake_data() w = t.rand(1, 1) b = t.zeros(1, 1) lr = 0.001 for ii in range(2000): x, y = get_fake_data() y_pred = x.mm(w) + b.expand_as(y) loss = 0.5 * (y_pred - y) ** 2 loss = loss.sum() dloss = 1 dy_pred = dloss * (y_pred - y) dw = x.t().mm(dy_pred) db = dy_pred.sum() w.sub_(lr * dw) b.sub_(lr * db) if ii % 10 == 0: x = t.arange(0, 20).view(-1, 1) y = x.float().mm(w)+ b.expand_as(x) x2, y2 = get_fake_data(batch_size=20) print("w=",w.item(), "b=",b.item())
Parent topic: Public Dependency Demos
Feedback
Was this page helpful?
Provide feedbackThank you very much for your feedback. We will continue working to improve the documentation.
The system is busy. Please try again later.