Config in MaxPooling 1d

[renph]

Hi Awni Y. Hannun, I have been reproducing you paper published on Nature medicine.

I am confused about your settings of MaxPooling 1d.

Here is the function for building the whole network.

ecg/ecg/network.py

Lines 42 to 81 in c97bb96

	def resnet_block(
	layer,
	num_filters,
	subsample_length,
	block_index,
	**params):
	from keras.layers import Add
	from keras.layers import MaxPooling1D
	from keras.layers.core import Lambda
	def zeropad(x):
	y = K.zeros_like(x)
	return K.concatenate([x, y], axis=2)
	def zeropad_output_shape(input_shape):
	shape = list(input_shape)
	assert len(shape) == 3
	shape[2] *= 2
	return tuple(shape)
	shortcut = MaxPooling1D(pool_size=subsample_length)(layer)
	zero_pad = (block_index % params["conv_increase_channels_at"]) == 0 \
	and block_index > 0
	if zero_pad is True:
	shortcut = Lambda(zeropad, output_shape=zeropad_output_shape)(shortcut)
	for i in range(params["conv_num_skip"]):
	if not (block_index == 0 and i == 0):
	layer = _bn_relu(
	layer,
	dropout=params["conv_dropout"] if i > 0 else 0,
	**params)
	layer = add_conv_weight(
	layer,
	params["conv_filter_length"],
	num_filters,
	subsample_length if i == 0 else 1,
	**params)
	layer = Add()([shortcut, layer])
	return layer

You created the shortcut on line 62, where the subsample_length can only be 1 or 2 in your settings.

    shortcut = MaxPooling1D(pool_size=subsample_length)(layer) 

when subsample_length = 1, MaxPooling1D applies 1x1 window on input data, therefore, no change made to the input.
Is this intended?