keras-team/keras · error · TypeError

Invalid input type. Expected `float16`, `float32` or `float6

Error message

Invalid input type. Expected `float16`, `float32` or `float64`. Received: input type={dtype}

What it means

Error "Invalid input type. Expected `float16`, `float32` or `float64`. Received: input type={dtype}" thrown in keras-team/keras.

Source

Thrown at keras/src/layers/preprocessing/stft_spectrogram.py:297

                outputs,
                [batch_size, channels, freq_channels, time_seq],
            )
        else:
            _, freq_channels, time_seq = ops.shape(outputs)
            outputs = ops.reshape(
                outputs,
                [batch_size, channels, freq_channels, time_seq],
            )
        return outputs

    def call(self, inputs):
        dtype = inputs.dtype
        if backend.standardize_dtype(dtype) not in {
            "float16",
            "float32",
            "float64",
        }:
            raise TypeError(
                "Invalid input type. Expected `float16`, `float32` or "
                f"`float64`. Received: input type={dtype}"
            )

        real_signal = None
        imag_signal = None
        power = None

        if self.mode != "imag":
            real_signal = self._apply_conv(inputs, self.real_kernel)
        if self.mode != "real":
            imag_signal = self._apply_conv(inputs, self.imag_kernel)

        if self.mode == "real":
            return self._adjust_shapes(real_signal)
        elif self.mode == "imag":
            return self._adjust_shapes(imag_signal)
        elif self.mode == "angle":

View on GitHub (pinned to 7a34a03db6)

When it happens

Trigger: Thrown at keras/src/layers/preprocessing/stft_spectrogram.py:297 when the library encounters an invalid state.

Common situations: See trigger scenarios.

AI-assisted analysis of keras-team/keras@7a34a03db6 (2026-08-25). Data as JSON: /api/errors/b46c189a60ff42f0. Report an issue: GitHub.