keras-team/keras · error · ValueError

Input to `.fit()` should have rank 4. Got array with shape:

Error message

Input to `.fit()` should have rank 4. Got array with shape: {x.shape}

What it means

ImageDataGenerator.fit(x) requires a rank-4 array representing a sample of images (N, H, W, C) so it can compute statistics (mean/std/PCA) per channel.

Source

Thrown at keras/src/legacy/preprocessing/image.py:1489

        When `rescale` is set to a value, rescaling is applied to
        sample data before computing the internal data stats.

        Args:
            x: Sample data. Should have rank 4.
             In case of grayscale data,
             the channels axis should have value 1, in case
             of RGB data, it should have value 3, and in case
             of RGBA data, it should have value 4.
            augment: Boolean (default: False).
                Whether to fit on randomly augmented samples.
            rounds: Int (default: 1).
                If using data augmentation (`augment=True`),
                this is how many augmentation passes over the data to use.
            seed: Int (default: None). Random seed.
        """
        x = np.asarray(x, dtype=self.dtype)
        if x.ndim != 4:
            raise ValueError(
                "Input to `.fit()` should have rank 4. Got array with shape: "
                + str(x.shape)
            )
        if x.shape[self.channel_axis] not in {1, 3, 4}:
            warnings.warn(
                "Expected input to be images (as Numpy array) "
                f'following the data format convention "{self.data_format}'
                f'" (channels on axis {self.channel_axis})'
                ", i.e. expected either 1, 3 or 4 channels on axis "
                f"{self.channel_axis}. However, it was passed an array with"
                f" shape {x.shape} ({x.shape[self.channel_axis]} channels)."
            )

        if seed is not None:
            np.random.seed(seed)

        x = np.copy(x)
        if self.rescale:

View on GitHub (pinned to 7a34a03db6)

Solutions

1. Reshape to (N, H, W, C): x = x.reshape(-1, 28, 28, 1)
2. For one image: np.expand_dims(img, 0)
3. Ensure channel count is 1, 3, or 4 (warning otherwise)

Example fix

// before
gen.fit(x_train_flat)  # (N, 784)
// after
gen.fit(x_train_flat.reshape(-1, 28, 28, 1))

x = np.asarray(x)
assert x.ndim == 4, x.shape

def rank4(a): return np.asarray(a).ndim == 4

try: gen.fit(x)
except ValueError as e: if 'rank 4' in str(e): x = np.expand_dims(x, 0) if x.ndim == 3 else x

When it happens

Trigger: gen.fit(single_image) with shape (H, W, C), or gen.fit(x_flat) with (N, 784).

Common situations: Forgetting to batch a single image; passing flattened data.

Related errors

• Input data in `NumpyArrayIterator` should have rank 4. You p
• Found bounding_boxes['boxes'].shape={boxes_shape} and expect
• Found bounding_boxes['boxes'].shape={boxes_shape} and expect
• Expected `bounding_boxes['boxes']` to have rank 2 or 3, with
• Expected the input image to be rank 3 or 4. Received inputs.

AI-assisted analysis of keras-team/keras@7a34a03db6 (2026-08-25). Data as JSON: /api/errors/9984f76117fb1187. Report an issue: GitHub.