def create_bn_inception():
# Input variables denoting the features and label data
feature_var = input_variable((NUM_CHANNELS, IMAGE_HEIGHT, IMAGE_WIDTH))
label_var = input_variable((NUM_CLASSES))
bn_time_const = 4096
z = bn_inception_model(feature_var, NUM_CLASSES, bn_time_const)
# loss and metric
ce = cross_entropy_with_softmax(z, label_var)
pe = classification_error(z, label_var)
pe5 = classification_error(z, label_var, topN=5)
log_number_of_parameters(z)
print()
return {
'feature': feature_var,
'label' : label_var,
'ce' : ce,
'pe' : pe,
'pe5' : pe5,
'output' : z
}
def create_bn_inception():
# Input variables denoting the features and label data
feature_var = input((num_channels, image_height, image_width))
label_var = input((num_classes))
bn_time_const = 4096
z = bn_inception_model(feature_var, num_classes, bn_time_const)
# loss and metric
ce = cross_entropy_with_softmax(z, label_var)
pe = classification_error(z, label_var)
pe5 = classification_error(z, label_var, topN=5)
log_number_of_parameters(z)
print()
return {
'feature': feature_var,
'label': label_var,
'ce': ce,
'pe': pe,
'pe5': pe5,
'output': z
}
def create_bn_inception():
# Input variables denoting the features and label data
feature_var = input_variable((num_channels, image_height, image_width))
label_var = input_variable((num_classes))
bn_time_const = 4096
z = bn_inception_model(feature_var, num_classes, bn_time_const)
# loss and metric
ce = cross_entropy_with_softmax(z, label_var)
pe = classification_error(z, label_var)
pe5 = classification_error(z, label_var, topN=5)
log_number_of_parameters(z)
print()
return {
'feature': feature_var,
'label' : label_var,
'ce' : ce,
'pe' : pe,
'pe5' : pe5,
'output' : z
}
