def call()

in basic_pitch/layers/nnaudio.py [0:0]

• 30 lines of code
• 10 McCabe index (conditional complexity)

    def call(self, x: tf.Tensor) -> tf.Tensor:
        x = self.reshape_input(x)  # type: ignore

        if self.earlydownsample is True:
            x = downsampling_by_n(x, self.early_downsample_filter, self.downsample_factor, self.match_torch_exactly)

        hop = self.hop_length

        # Getting the top octave CQT
        CQT = get_cqt_complex(x, self.cqt_kernels_real, self.cqt_kernels_imag, hop, self.padding)

        x_down = x  # Preparing a new variable for downsampling

        for _ in range(self.n_octaves - 1):
            hop = hop // 2
            x_down = downsampling_by_n(x_down, self.lowpass_filter, 2, self.match_torch_exactly)
            CQT1 = get_cqt_complex(x_down, self.cqt_kernels_real, self.cqt_kernels_imag, hop, self.padding)
            CQT = tf.concat((CQT1, CQT), axis=1)

        CQT = CQT[:, -self.n_bins :, :]  # Removing unwanted bottom bins

        # Normalizing the output with the downsampling factor, 2**(self.n_octaves-1) is make it
        # same mag as 1992
        CQT = CQT * self.downsample_factor

        # Normalize again to get same result as librosa
        if self.normalization_type == "librosa":
            CQT *= tf.math.sqrt(tf.cast(self.lengths.reshape((-1, 1, 1)), self.dtype))
        elif self.normalization_type == "convolutional":
            pass
        elif self.normalization_type == "wrap":
            CQT *= 2
        else:
            raise ValueError("The normalization_type %r is not part of our current options." % self.normalization_type)

        # Transpose the output to match the output of the other spectrogram layers.
        if self.output_format.lower() == "magnitude":
            # Getting CQT Amplitude
            return tf.transpose(tf.math.sqrt(tf.math.reduce_sum(tf.math.pow(CQT, 2), axis=-1)), [0, 2, 1])

        elif self.output_format.lower() == "complex":
            return CQT

        elif self.output_format.lower() == "phase":
            phase_real = tf.math.cos(tf.math.atan2(CQT[:, :, :, 1], CQT[:, :, :, 0]))
            phase_imag = tf.math.sin(tf.math.atan2(CQT[:, :, :, 1], CQT[:, :, :, 0]))
            return tf.stack((phase_real, phase_imag), axis=-1)