`ml.service`

class tinychain.ml.service.NeuralNets[source]

Bases: Library

class ConvLayer(*args, **kwargs)

classmethod create(inputs_shape, filter_shape, stride=1, padding=1, activation=None, optimal_std=None)

Create a new, empty ConvLayer with the given shape and activation function.

Args:

inputs_shape: size of inputs [c_i, h_i, w_i] where: c_i: number of channels, h_i: channel height, ‘w_i’: channel width;
filter_shape: size of filter [h_f, w_f, out_c] where: out_c: number of output channels, h_f: kernel height, ‘w_f`: kernel width;

activation: activation function

class DNN(*args, **kwargs)

classmethod create(schema)

Create a new Sequential neural net of Linear layers.

schema should be a list of 2- or 3-tuples of the form (input_size, output_size, activation) (the arguments to Linear.create).

class Layer(*args, **kwargs)

Bases: Model, Differentiable

A Layer in a NeuralNet

class Linear(*args, **kwargs)

classmethod create(input_size, output_size, activation=None, optimal_std=None)

class NeuralNet(*args, **kwargs)

Bases: Model, Differentiable

A neural network

class Sequential(*args, **kwargs)

A sequence of Layer s

class tinychain.ml.service.Optimizers[source]

Bases: Library

class Adam(*args, **kwargs)

Adam optimizer, an adaptive learning rate optimization algorithm designed to handle sparse gradients and noisy data.

Based on “Adam: A Method for Stochastic Optimization” by Kingma & Ba, 2014: https://arxiv.org/abs/1412.6980

class GradientDescent(*args, **kwargs)

A simple gradient descent optimizer with a configurable learning rate.

class Optimizer(*args, **kwargs)

An optimizer for a Differentiable Model

ml.service