Tutorial by Examples

Update: TensorFlow now supports 1D convolution since version r0.11, using tf.nn.conv1d. Consider a basic example with an input of length 10, and dimension 16. The batch size is 32. We therefore have a placeholder with input shape [batch_size, 10, 16]. batch_size = 32 x = tf.placeholder(tf.float...

`To calculate 1D convolution by hand, you slide your kernel over the input, calculate the element-wise multiplications and sum them up. The easiest way is for padding=0, stride=1 So if your input = [1, 0, 2, 3, 0, 1, 1] and kernel = [2, 1, 3] the result of the convolution is [8, 11, 7, 9, 4], whic...