for input size [1, 1, 768] , how can we calculate the o/p of the following layers?
and can anyone help to code this block in pytorch (this one belongs to wav2vec2) ?
(pos_conv_embed): ConvolutionalPositionalEmbedding(
(conv): ParametrizedConv1d(
768, 768, kernel_size=(128,), stride=(1,), padding=(64,), groups=16
(parametrizations): ModuleDict(
(weight): ParametrizationList(
(0): _WeightNorm()
)
)
)
)