Convolution forward

conv_frorward.py

def forward_pass(self, a_prev: np.array) -> np.array:
    n, h_in, w_in, _ = a_prev.shape
    _, h_out, w_out, _ = output_shape
    h_f, w_f, _, n_f = self._w.shape
    
    output_shape = self.calculate_output_dims(input_dims=a_prev.shape)
    output = np.zeros(output_shape)
    
    for i in range(h_out):
        for j in range(w_out):
            h_start, w_start = i, j
            h_end, w_end = h_start + h_f, w_start + w_f

            output[:, i, j, :] = np.sum(
                a_prev[:, h_start:h_end, w_start:w_end, :, np.newaxis] *
                self._w[np.newaxis, :, :, :],
                axis=(1, 2, 3)
            )

    return output + self._b