.. note:: :class: sphx-glr-download-link-note Click :ref:`here ` to download the full example code .. rst-class:: sphx-glr-example-title .. _sphx_glr_beginner_basics_buildmodel_tutorial.py: `Learn the Basics `_ || `Quickstart `_ || `Tensors `_ || `Datasets & DataLoaders `_ || `Transforms `_ || **Build Model** || `Autograd `_ || `Optimization `_ || `Save & Load Model `_ Build the Neural Network =================== Neural networks comprise of layers/modules that perform operations on data. The `torch.nn `_ namespace provides all the building blocks you need to build your own neural network. Every module in PyTorch subclasses the `nn.Module `_. A neural network is a module itself that consists of other modules (layers). This nested structure allows for building and managing complex architectures easily. In the following sections, we'll build a neural network to classify images in the FashionMNIST dataset. .. code-block:: default import os import torch from torch import nn from torch.utils.data import DataLoader from torchvision import datasets, transforms Get Device for Training ----------------------- We want to be able to train our model on a hardware accelerator like the GPU, if it is available. Let's check to see if `torch.cuda `_ is available, else we continue to use the CPU. .. code-block:: default device = 'cuda' if torch.cuda.is_available() else 'cpu' print('Using {} device'.format(device)) .. rst-class:: sphx-glr-script-out Out: .. code-block:: none Using cuda device Define the Class ------------------------- We define our neural network by subclassing ``nn.Module``, and initialize the neural network layers in ``__init__``. Every ``nn.Module`` subclass implements the operations on input data in the ``forward`` method. .. code-block:: default class NeuralNetwork(nn.Module): def __init__(self): super(NeuralNetwork, self).__init__() self.flatten = nn.Flatten() self.linear_relu_stack = nn.Sequential( nn.Linear(28*28, 512), nn.ReLU(), nn.Linear(512, 512), nn.ReLU(), nn.Linear(512, 10), ) def forward(self, x): x = self.flatten(x) logits = self.linear_relu_stack(x) return logits We create an instance of ``NeuralNetwork``, and move it to the ``device``, and print its structure. .. code-block:: default model = NeuralNetwork().to(device) print(model) .. rst-class:: sphx-glr-script-out Out: .. code-block:: none NeuralNetwork( (flatten): Flatten(start_dim=1, end_dim=-1) (linear_relu_stack): Sequential( (0): Linear(in_features=784, out_features=512, bias=True) (1): ReLU() (2): Linear(in_features=512, out_features=512, bias=True) (3): ReLU() (4): Linear(in_features=512, out_features=10, bias=True) ) ) To use the model, we pass it the input data. This executes the model's ``forward``, along with some `background operations `_. Do not call ``model.forward()`` directly! Calling the model on the input returns a 10-dimensional tensor with raw predicted values for each class. We get the prediction probabilities by passing it through an instance of the ``nn.Softmax`` module. .. code-block:: default X = torch.rand(1, 28, 28, device=device) logits = model(X) pred_probab = nn.Softmax(dim=1)(logits) y_pred = pred_probab.argmax(1) print(f"Predicted class: {y_pred}") .. rst-class:: sphx-glr-script-out Out: .. code-block:: none Predicted class: tensor([1], device='cuda:0') -------------- Model Layers ------------------------- Let's break down the layers in the FashionMNIST model. To illustrate it, we will take a sample minibatch of 3 images of size 28x28 and see what happens to it as we pass it through the network. .. code-block:: default input_image = torch.rand(3,28,28) print(input_image.size()) .. rst-class:: sphx-glr-script-out Out: .. code-block:: none torch.Size([3, 28, 28]) nn.Flatten ^^^^^^^^^^^^^^^^^^^^^^ We initialize the `nn.Flatten `_ layer to convert each 2D 28x28 image into a contiguous array of 784 pixel values ( the minibatch dimension (at dim=0) is maintained). .. code-block:: default flatten = nn.Flatten() flat_image = flatten(input_image) print(flat_image.size()) .. rst-class:: sphx-glr-script-out Out: .. code-block:: none torch.Size([3, 784]) nn.Linear ^^^^^^^^^^^^^^^^^^^^^^ The `linear layer `_ is a module that applies a linear transformation on the input using its stored weights and biases. .. code-block:: default layer1 = nn.Linear(in_features=28*28, out_features=20) hidden1 = layer1(flat_image) print(hidden1.size()) .. rst-class:: sphx-glr-script-out Out: .. code-block:: none torch.Size([3, 20]) nn.ReLU ^^^^^^^^^^^^^^^^^^^^^^ Non-linear activations are what create the complex mappings between the model's inputs and outputs. They are applied after linear transformations to introduce *nonlinearity*, helping neural networks learn a wide variety of phenomena. In this model, we use `nn.ReLU `_ between our linear layers, but there's other activations to introduce non-linearity in your model. .. code-block:: default print(f"Before ReLU: {hidden1}\n\n") hidden1 = nn.ReLU()(hidden1) print(f"After ReLU: {hidden1}") .. rst-class:: sphx-glr-script-out Out: .. code-block:: none Before ReLU: tensor([[ 0.0222, -0.6033, -0.0729, -0.2444, -0.4527, -0.0818, -0.1731, 0.6106, -0.0841, -0.2071, -0.0412, 0.3886, 0.2097, 0.1175, 0.5225, 0.1585, 0.4200, -0.0334, 0.2474, 0.0671], [ 0.2991, -0.5166, -0.1019, -0.5737, -0.2419, -0.0240, 0.0627, 0.3513, 0.2351, -0.2838, 0.3582, 0.4613, -0.0718, -0.1388, 0.2659, -0.0998, 0.5224, 0.0668, 0.1589, 0.0842], [ 0.4199, -0.3572, -0.1495, -0.4688, -0.4321, 0.2206, -0.1632, 0.3074, 0.2776, -0.5483, 0.4343, 0.1575, -0.1756, 0.1867, 0.5402, -0.1659, 0.4503, 0.0280, 0.3984, 0.0697]], grad_fn=) After ReLU: tensor([[0.0222, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.6106, 0.0000, 0.0000, 0.0000, 0.3886, 0.2097, 0.1175, 0.5225, 0.1585, 0.4200, 0.0000, 0.2474, 0.0671], [0.2991, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0627, 0.3513, 0.2351, 0.0000, 0.3582, 0.4613, 0.0000, 0.0000, 0.2659, 0.0000, 0.5224, 0.0668, 0.1589, 0.0842], [0.4199, 0.0000, 0.0000, 0.0000, 0.0000, 0.2206, 0.0000, 0.3074, 0.2776, 0.0000, 0.4343, 0.1575, 0.0000, 0.1867, 0.5402, 0.0000, 0.4503, 0.0280, 0.3984, 0.0697]], grad_fn=) nn.Sequential ^^^^^^^^^^^^^^^^^^^^^^ `nn.Sequential `_ is an ordered container of modules. The data is passed through all the modules in the same order as defined. You can use sequential containers to put together a quick network like ``seq_modules``. .. code-block:: default seq_modules = nn.Sequential( flatten, layer1, nn.ReLU(), nn.Linear(20, 10) ) input_image = torch.rand(3,28,28) logits = seq_modules(input_image) nn.Softmax ^^^^^^^^^^^^^^^^^^^^^^ The last linear layer of the neural network returns `logits` - raw values in [-\infty, \infty] - which are passed to the `nn.Softmax `_ module. The logits are scaled to values [0, 1] representing the model's predicted probabilities for each class. ``dim`` parameter indicates the dimension along which the values must sum to 1. .. code-block:: default softmax = nn.Softmax(dim=1) pred_probab = softmax(logits) Model Parameters ------------------------- Many layers inside a neural network are *parameterized*, i.e. have associated weights and biases that are optimized during training. Subclassing ``nn.Module`` automatically tracks all fields defined inside your model object, and makes all parameters accessible using your model's ``parameters()`` or ``named_parameters()`` methods. In this example, we iterate over each parameter, and print its size and a preview of its values. .. code-block:: default print("Model structure: ", model, "\n\n") for name, param in model.named_parameters(): print(f"Layer: {name} | Size: {param.size()} | Values : {param[:2]} \n") .. rst-class:: sphx-glr-script-out Out: .. code-block:: none Model structure: NeuralNetwork( (flatten): Flatten(start_dim=1, end_dim=-1) (linear_relu_stack): Sequential( (0): Linear(in_features=784, out_features=512, bias=True) (1): ReLU() (2): Linear(in_features=512, out_features=512, bias=True) (3): ReLU() (4): Linear(in_features=512, out_features=10, bias=True) ) ) Layer: linear_relu_stack.0.weight | Size: torch.Size([512, 784]) | Values : tensor([[-0.0041, 0.0328, -0.0100, ..., 0.0231, -0.0036, 0.0232], [ 0.0020, 0.0093, 0.0192, ..., -0.0017, -0.0252, -0.0018]], device='cuda:0', grad_fn=) Layer: linear_relu_stack.0.bias | Size: torch.Size([512]) | Values : tensor([0.0006, 0.0228], device='cuda:0', grad_fn=) Layer: linear_relu_stack.2.weight | Size: torch.Size([512, 512]) | Values : tensor([[-0.0058, 0.0006, -0.0206, ..., -0.0282, 0.0279, 0.0129], [ 0.0239, 0.0063, 0.0113, ..., -0.0428, 0.0211, 0.0381]], device='cuda:0', grad_fn=) Layer: linear_relu_stack.2.bias | Size: torch.Size([512]) | Values : tensor([-0.0131, 0.0273], device='cuda:0', grad_fn=) Layer: linear_relu_stack.4.weight | Size: torch.Size([10, 512]) | Values : tensor([[-0.0393, -0.0319, 0.0136, ..., -0.0394, -0.0401, 0.0230], [-0.0360, -0.0034, -0.0023, ..., -0.0278, 0.0245, 0.0025]], device='cuda:0', grad_fn=) Layer: linear_relu_stack.4.bias | Size: torch.Size([10]) | Values : tensor([-0.0152, -0.0243], device='cuda:0', grad_fn=) -------------- Further Reading -------------- - `torch.nn API `_ .. rst-class:: sphx-glr-timing **Total running time of the script:** ( 0 minutes 6.180 seconds) .. _sphx_glr_download_beginner_basics_buildmodel_tutorial.py: .. only :: html .. container:: sphx-glr-footer :class: sphx-glr-footer-example .. container:: sphx-glr-download :download:`Download Python source code: buildmodel_tutorial.py ` .. container:: sphx-glr-download :download:`Download Jupyter notebook: buildmodel_tutorial.ipynb ` .. only:: html .. rst-class:: sphx-glr-signature `Gallery generated by Sphinx-Gallery `_