keras-team/keras · error · ValueError

When backend.image_data_format()=channels_first, input_shape

Error message

When backend.image_data_format()=channels_first, input_shape[1] must equal input_tensor.shape[1].  Received input_shape={input_shape}, input_tensor.shape={input_tensor.shape}

What it means

Error "When backend.image_data_format()=channels_first, input_shape[1] must equal input_tensor.shape[1]. Received input_shape={input_shape}, input_tensor.shape={input_tensor.shape}" thrown in keras-team/keras.

Source

Thrown at keras/src/applications/mobilenet_v3.py:206

    if input_shape is not None and input_tensor is not None:
        try:
            is_input_t_tensor = backend.is_keras_tensor(input_tensor)
        except ValueError:
            try:
                is_input_t_tensor = backend.is_keras_tensor(
                    operation_utils.get_source_inputs(input_tensor)
                )
            except ValueError:
                raise ValueError(
                    "input_tensor: ",
                    input_tensor,
                    "is not type input_tensor.  "
                    f"Received type(input_tensor)={type(input_tensor)}",
                )
        if is_input_t_tensor:
            if backend.image_data_format() == "channels_first":
                if input_tensor.shape[1] != input_shape[1]:
                    raise ValueError(
                        "When backend.image_data_format()=channels_first, "
                        "input_shape[1] must equal "
                        "input_tensor.shape[1].  Received "
                        f"input_shape={input_shape}, "
                        "input_tensor.shape="
                        f"{input_tensor.shape}"
                    )
            else:
                if input_tensor.shape[2] != input_shape[1]:
                    raise ValueError(
                        "input_shape[1] must equal "
                        "input_tensor.shape[2].  Received "
                        f"input_shape={input_shape}, "
                        "input_tensor.shape="
                        f"{input_tensor.shape}"
                    )
        else:
            raise ValueError(

View on GitHub (pinned to 7a34a03db6)

When it happens

Trigger: Thrown at keras/src/applications/mobilenet_v3.py:206 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/76a44b2ce37c9ca2. Report an issue: GitHub.