Skip to main content

Viewing network information

Function Signature

def specs(self) -> str:

Return Value

  • output (str): A string representation of the network information, including the model type, optimizer, parameters, loss function, and DeeprAI version.

Description

The specs function returns a string representation of the network information, including the model type, optimizer, parameters, loss function, and DeeprAI version.

Examples

Here's an example of how to use the specs function:

from deeprai.models import FeedForward

model = FeedForward()
model.add_dense(784)
model.add_dense(128, activation='relu')
model.add_dense(64, activation='relu')
model.add_dense(10, activation='softmax')
model.config(optimizer='gradient descent', loss='mean square error')

model_specs = model.specs()
print(model_specs)

This code creates a FeedForward model with a single dense layer of size 784, followed by two additional dense layers with ReLU activation functions, and a final dense layer with a softmax activation function. The config function sets the optimizer to gradient descent and the loss function to mean square error.

The specs function returns a string representation of the network information, including the model type, optimizer, parameters, loss function, and DeeprAI version, which can be printed to the console. The output should look something like this:

.---------------.------------------.-----------------.------------------.
|      Key      |       Val        |       Key       |       Val        |
:---------------+------------------+-----------------+------------------:
| Model         | Feed Forward     | Optimizer       | Gradient Descent |
:---------------+------------------+-----------------+------------------:
| Parameters    | 15               | Layer Model     | 2x5x1            |
:---------------+------------------+-----------------+------------------:
| Loss Function | Mean Square Error| DeeprAI Version | 0.0.12 BETA      |
'---------------'------------------'-----------------'------------------'