Linear regression using PyTorch

👻 Check our latest review to choose the best laptop for Machine Learning engineers and Deep learning tasks!

First, you will need to install PyTorch in your Python environment. The easiest way to do this is — use the pip or conda tool. Visit pytorch.org and install the version of your Python interpreter and package manager that you would like to use.

With PyTorch installed, let’s now look at the code.
Write the two lines below to import the required library functions and objects.

We also define some data and assign it to the variables x_data and y_data, as follows:

Here x_data — our independent variable, and y_data — our dependent variable. This will be our dataset for now. Next, we need to define our model. There are two main steps involved in defining our model. They are:

1. Initializing our model.
2. Declaring a forward pass.

We use the class below:

As you can see, our Model class is a subclass of torch.nn.module . In addition, since we only have one input and one output here, we use a linear model with an input and output size of 1.

Next, we create an object of this model.

After that choose an optimizer and loss criteria. Here we will use mean squared error (MSE) as our loss function and Stochastic Gradient Descent (SGD) as our optimizer. We also arbitrarily fix the learning rate to 0.01.

Now we come to our learning stage. We perform the following tasks 500 times during training:

1. Perform a live transfer by passing in our data and figuring out the predicted y value.
2. Calculate loss using MSE.
3. Reset all gradients to 0, back propagate and then update the weights.

After completing the training we check if we are getting the correct results using the model that we have defined. So we check it for an unknown x_data value, in this case 4.0.

If you followed all the steps correctly, you you will see that for entry 4.0 you get a value very close to 8.0, as shown below. Thus, our model essentially learns the relationship between input and output without explicit programming.

predict (after training) 4 7.966438293457031

For reference, you can find all the code for this article below:

Links

• PyTorchZeroToAll
• target State STAT 501

👻 Read also: what is the best laptop for engineering students?

Linear regression using PyTorch __del__: Questions

import time
time.sleep(5)   # Delays for 5 seconds. You can also use a float value.

import time
while True:
    print("This prints once a minute.")
    time.sleep(60) # Delay for 1 minute (60 seconds).

from time import sleep
sleep(0.1) # Time in seconds

Linear regression using PyTorch __del__: Questions

We hope this article has helped you to resolve the problem. Apart from Linear regression using PyTorch, check other __del__-related topics.

Want to excel in Python? See our review of the best Python online courses 2023. If you are interested in Data Science, check also how to learn programming in R.

By the way, this material is also available in other languages:

• Italiano Linear regression using PyTorch
• Deutsch Linear regression using PyTorch
• Français Linear regression using PyTorch
• Español Linear regression using PyTorch
• Türk Linear regression using PyTorch
• Русский Linear regression using PyTorch
• Português Linear regression using PyTorch
• Polski Linear regression using PyTorch
• Nederlandse Linear regression using PyTorch
• 中文 Linear regression using PyTorch
• 한국어 Linear regression using PyTorch
• 日本語 Linear regression using PyTorch
• हिन्दी Linear regression using PyTorch