DEV Community

Cover image for Pytorch for Neural Networks Part 4: Testing the Neural Network
Rijul Rajesh
Rijul Rajesh

Posted on

Pytorch for Neural Networks Part 4: Testing the Neural Network

#machinelearning #ai

In the previous article, we defined the forward pass for our neural network.

Now, we will provide inputs to the network so that we can test whether it works correctly.

Creating Input Values

To create a sequence of input values, we can define them like this:

input_doses = torch.linspace(start=0, end=1, steps=11)
Enter fullscreen mode Exit fullscreen mode

Here, we use the PyTorch function linspace() to create a tensor containing 11 evenly spaced values between 0 and 1, including both endpoints.

The resulting tensor is stored in a variable called input_doses.

We can print input_doses to see what it looks like:

tensor([0.0000, 0.1000, 0.2000, 0.3000, 0.4000, 0.5000, 0.6000, 0.7000, 0.8000,
        0.9000, 1.0000])
Enter fullscreen mode Exit fullscreen mode

Creating the Neural Network

Now, we need to create an instance of our neural network.

model = MyBasicNN()
Enter fullscreen mode Exit fullscreen mode

Passing Inputs Through the Neural Network

Next, we pass the input values through the model.

output_values = model(input_doses)
Enter fullscreen mode Exit fullscreen mode

By default, PyTorch automatically calls the forward() method that we defined earlier.

The outputs from the neural network are stored in the variable output_values.

Plotting the Results

Now, let us visualize the outputs using a graph.

For this, we will use Seaborn and Matplotlib.

import seaborn as sns
import matplotlib.pyplot as plt

sns.set(style="whitegrid")

sns.lineplot(
    x=input_doses,
    y=output_values,
    color="green",
    linewidth=2.5
)
Enter fullscreen mode Exit fullscreen mode

Next, we set labels for the graph:

plt.ylabel("Effectiveness")
plt.xlabel("Dose")
Enter fullscreen mode Exit fullscreen mode

This gives us the following result:

You can try out the code yourself by checking out this colab notebook

In the next article, we will explore a scenario where the final bias is unknown.

We will solve this problem by implementing backpropagation in code.

AI agents write code fast. They also silently remove logic, change behavior, and introduce bugs -- without telling you. You often find out in production.

git-lrc fixes this. It hooks into git commit and reviews every diff before it lands. 60-second setup. Completely free.

Any feedback or contributors are welcome! It's online, source-available, and ready for anyone to use.

Give it a ⭐ star on Github

Top comments (0)