Sequential

neuralpy.models.Sequential(force_cpu=False, training_device=None, random_state=None)
info

NeuralPy Sequential Model Class is mostly stable and can be used for any project. In the future, any chance of breaking changes is very low.

Sequential is a linear stack of layers with single input and output layer. It is one of the simplest types of models. In Sequential models, each layer has a single input and output tensor.

The Sequential model works on top of Model class, so all the methods that are available on the Model is also available here in Sequential class

Supported Arguments

  • force_cpu=False: (Boolean) If True, then uses CPU even if CUDA is available
  • training_device=None: (NeuralPy device class) Device that will be used for training predictions
  • random_state: (Integer) Random state for the device

Supported Methods

.add() method:

In a Sequential model, the .add() method is responsible for adding a new layer to the model. It accepts a NeuralPy layer class as an argument and builds a model, and based on that. The .add() method can be called as many times as needed. There is no limitation on that, assuming you have enough computation power to handle it.

Supported Arguments
  • layer: (NeuralPy layer classes) Adds a layer into the model
Example Codes
from neuralpy.models import Sequential
from neuralpy.layers.linear import Dense
from neuralpy.layers.activation_functions import ReLU
from neuralpy import device
# Setting a training device
training_device = device('cpu')
# Initializing the Sequential models
model = Sequential(force_cpu=False, training_device=training_device, random_state=1969)
# Adding layers to the model
model.add(Dense(n_nodes=3, n_inputs=5, bias=True))
model.add(ReLU())
model.add(Dense(n_nodes=3, n_inputs=3, bias=True))

.build() method:

In a Sequential model, the .build() method is responsible for building the PyTorch model from the NeuralPy model.

After finishing the architecture of the model, the model needed to be built before training.

Supported Arguments:
  • There is no argument for this model

Example Code

from neuralpy.models import Sequential
...
# Rest of the imports
...
model = Sequential()
...
# Model Architecture
...
# Calling .build to build the model
model.build()
Edit this page