Me gustaría explicar la diferencia visualmente y en detalle (comentarios en código) y en un enfoque muy muy fácil.
Primero revisemos el Conv2D en TensorFlow .
c1 = [[0, 0, 1, 0, 2], [1, 0, 2, 0, 1], [1, 0, 2, 2, 0], [2, 0, 0, 2, 0], [2, 1, 2, 2, 0]]
c2 = [[2, 1, 2, 1, 1], [2, 1, 2, 0, 1], [0, 2, 1, 0, 1], [1, 2, 2, 2, 2], [0, 1, 2, 0, 1]]
c3 = [[2, 1, 1, 2, 0], [1, 0, 0, 1, 0], [0, 1, 0, 0, 0], [1, 0, 2, 1, 0], [2, 2, 1, 1, 1]]
data = tf.transpose(tf.constant([[c1, c2, c3]], dtype=tf.float32), (0, 2, 3, 1))
# we transfer [batch, in_channels, in_height, in_width] to [batch, in_height, in_width, in_channels]
# where batch = 1, in_channels = 3 (c1, c2, c3 or the x[:, :, 0], x[:, :, 1], x[:, :, 2] in the gif), in_height and in_width are all 5(the sizes of the blue matrices without padding)
f2c1 = [[0, 1, -1], [0, -1, 0], [0, -1, 1]]
f2c2 = [[-1, 0, 0], [1, -1, 0], [1, -1, 0]]
f2c3 = [[-1, 1, -1], [0, -1, -1], [1, 0, 0]]
filters = tf.transpose(tf.constant([[f2c1, f2c2, f2c3]], dtype=tf.float32), (2, 3, 1, 0))
# we transfer the [out_channels, in_channels, filter_height, filter_width] to [filter_height, filter_width, in_channels, out_channels]
# out_channels is 1(in the gif it is 2 since here we only use one filter W1), in_channels is 3 because data has three channels(c1, c2, c3), filter_height and filter_width are all 3(the sizes of the filter W1)
# f2c1, f2c2, f2c3 are the w1[:, :, 0], w1[:, :, 1] and w1[:, :, 2] in the gif
output = tf.squeeze(tf.nn.conv2d(data, filters, strides=2, padding=[[0, 0], [1, 1], [1, 1], [0, 0]]))
# this is just the o[:,:,1] in the gif
# <tf.Tensor: id=93, shape=(3, 3), dtype=float32, numpy=
# array([[-8., -8., -3.],
# [-3., 1., 0.],
# [-3., -8., -5.]], dtype=float32)>
Y el Conv1D es un caso especial de Conv2D como se indica en este párrafo del documento TensorFlow de Conv1D .
Internamente, esta operación da nueva forma a los tensores de entrada e invoca tf.nn.conv2d. Por ejemplo, si data_format no comienza con "NC", un tensor de forma [batch, in_width, in_channels] se reforma a [batch, 1, in_width, in_channels], y el filtro se reforma a [1, filter_width, in_channels, canales_salida]. El resultado se vuelve a dar forma a [lote, out_width, out_channels] (donde out_width es una función del paso y el relleno como en conv2d) y se devuelve a la persona que llama.
Veamos cómo podemos transferir Conv1D también un problema Conv2D. Dado que Conv1D se usa generalmente en escenarios de PNL, podemos ilustrar eso en el siguiente problema de PNL.
cat = [0.7, 0.4, 0.5]
sitting = [0.2, -0.1, 0.1]
there = [-0.5, 0.4, 0.1]
dog = [0.6, 0.3, 0.5]
resting = [0.3, -0.1, 0.2]
here = [-0.5, 0.4, 0.1]
sentence = tf.constant([[cat, sitting, there, dog, resting, here]]
# sentence[:,:,0] is equivalent to x[:,:,0] or c1 in the first example and the same for sentence[:,:,1] and sentence[:,:,2]
data = tf.reshape(sentence), (1, 1, 6, 3))
# we reshape [batch, in_width, in_channels] to [batch, 1, in_width, in_channels] according to the quote above
# each dimension in the embedding is a channel(three in_channels)
f3c1 = [0.6, 0.2]
# equivalent to f2c1 in the first code snippet or w1[:,:,0] in the gif
f3c2 = [0.4, -0.1]
# equivalent to f2c2 in the first code snippet or w1[:,:,1] in the gif
f3c3 = [0.5, 0.2]
# equivalent to f2c3 in the first code snippet or w1[:,:,2] in the gif
# filters = tf.constant([[f3c1, f3c2, f3c3]])
# [out_channels, in_channels, filter_width]: [1, 3, 2]
# here we have also only one filter and also three channels in it. please compare these three with the three channels in W1 for the Conv2D in the gif
filter1D = tf.transpose(tf.constant([[f3c1, f3c2, f3c3]]), (2, 1, 0))
# shape: [2, 3, 1] for the conv1d example
filters = tf.reshape(filter1D, (1, 2, 3, 1)) # this should be expand_dim actually
# transpose [out_channels, in_channels, filter_width] to [filter_width, in_channels, out_channels]] and then reshape the result to [1, filter_width, in_channels, out_channels] as we described in the text snippet from Tensorflow doc of conv1doutput
output = tf.squeeze(tf.nn.conv2d(data, filters, strides=(1, 1, 2, 1), padding="VALID"))
# the numbers for strides are for [batch, 1, in_width, in_channels] of the data input
# <tf.Tensor: id=119, shape=(3,), dtype=float32, numpy=array([0.9 , 0.09999999, 0.12 ], dtype=float32)>
Hagámoslo usando Conv1D (también en TensorFlow):
output = tf.squeeze(tf.nn.conv1d(sentence, filter1D, stride=2, padding="VALID"))
# <tf.Tensor: id=135, shape=(3,), dtype=float32, numpy=array([0.9 , 0.09999999, 0.12 ], dtype=float32)>
# here stride defaults to be for the in_width
Podemos ver que el 2D en Conv2D significa que cada canal en la entrada y el filtro es bidimensional (como vemos en el ejemplo de gif) y 1D en Conv1D significa que cada canal en la entrada y el filtro es 1 dimensional (como vemos en el gato y perro NLP ejemplo).