Jaaaackson 施

…inputs = inputs / 255

# set batch norm params
batch_norm_params = {
'decay': _BATCH_NORM_DECAY,
'epsilon': _BATCH_NORM_EPSILON,
'scale': True,
'is_training': is_training,
'fused': None, # Use fused batch norm if possible.
}

# Set activation_fn and parameters for conv2d, batch_norm.
with slim.arg_scope([slim.conv2d, slim.batch_norm, _fixed_padding], data_format=data_format, reuse=reuse):
with slim.arg_scope([slim.conv2d], normalizer_fn=slim.batch_norm, normalizer_params=batch_norm_params,
biases_…

…ram will only calculate that when you actually need to use the resultant. We’ll explore laziness in Python soon.