decode_from_ternary_gradients

[karatse]

On this code:

terngrad/terngrad/inception/bingrad_common.py

Lines 100 to 107 in ec4f75e

	if gradient is None:
	floating_gradients.append(None)
	# gradient is encoded, so we use variable to check its size
	# We also assume dtype of variable and gradient is the same
	floating_gradient = tf.cond(tf.size(variable) < FLAGS.size_to_binarize,
	lambda: tf.bitcast(gradient, variable.dtype),
	lambda: ternary_decoder(gradient, scaler, shape))
	floating_gradients.append(floating_gradient)

is it intentional you do not continue after line 101?