High-level CNTK Example¶

import numpy as np
import os
import sys
import cntk
from cntk.layers import Convolution2D, MaxPooling, Dense, Dropout
from common.params import *
from common.utils import *

def create_symbol():
    # Weight initialiser from uniform distribution
    # Activation (unless states) is None
    with cntk.layers.default_options(init = cntk.glorot_uniform(), activation = cntk.relu):
        x = Convolution2D(filter_shape=(3, 3), num_filters=50, pad=True)(features)
        x = Convolution2D(filter_shape=(3, 3), num_filters=50, pad=True)(x)
        x = MaxPooling((2, 2), strides=(2, 2), pad=False)(x)
        x = Dropout(0.25)(x)

        x = Convolution2D(filter_shape=(3, 3), num_filters=100, pad=True)(x)
        x = Convolution2D(filter_shape=(3, 3), num_filters=100, pad=True)(x)
        x = MaxPooling((2, 2), strides=(2, 2), pad=False)(x)
        x = Dropout(0.25)(x)    
        
        x = Dense(512)(x)
        x = Dropout(0.5)(x)
        x = Dense(N_CLASSES, activation=None)(x)
        return x

def init_model(m):
    # Loss (dense labels); check if support for sparse labels
    loss = cntk.cross_entropy_with_softmax(m, labels)
    # Momentum SGD
    # https://github.com/Microsoft/CNTK/blob/master/Manual/Manual_How_to_use_learners.ipynb
    # unit_gain=False: momentum_direction = momentum*old_momentum_direction + gradient
    # if unit_gain=True then ...(1-momentum)*gradient
    learner = cntk.momentum_sgd(m.parameters, 
                                lr=cntk.learning_rate_schedule(LR, cntk.UnitType.minibatch) , 
                                momentum=cntk.momentum_schedule(MOMENTUM),
                                unit_gain=False)
    return loss, learner