keras-team/keras · error · ValueError

Input size must be at least

Error message

Input size must be at least {min_size}x{min_size}; Received: input_shape={input_shape}

What it means

obtain_input_shape in keras/src/applications/imagenet_utils.py: each spatial dimension of input_shape must be at least `min_size` (model-specific, e.g. 32 or 71) because the stack of stride-2 convolutions/pooling would otherwise reduce the feature maps below a usable size. Fires when a declared width or height is smaller than that minimum (or None-checks pass but the value is too small).

Solutions

1. Resize input images to at least min_size x min_size, e.g. 32x32 or the model's default 224x224
2. Update the input_shape tuple to meet the minimum rather than the data
3. Choose a smaller/backbone-free model if your inputs are inherently tiny

When it happens

Trigger: Thrown at keras/src/applications/imagenet_utils.py:386 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/d09f49bb5a3489cb. Report an issue: GitHub.

Appendix: source

Thrown at keras/src/applications/imagenet_utils.py:386

                        "The input must have 3 channels; Received "
                        f"`input_shape={input_shape}`"
                    )
                if (
                    input_shape[1] is not None and input_shape[1] < min_size
                ) or (input_shape[2] is not None and input_shape[2] < min_size):
                    raise ValueError(
                        f"Input size must be at least {min_size}"
                        f"x{min_size}; Received: "
                        f"input_shape={input_shape}"
                    )
        else:
            if input_shape is not None:
                if len(input_shape) != 3:
                    raise ValueError(
                        "`input_shape` must be a tuple of three integers."
                    )
                if input_shape[-1] != 3 and weights == "imagenet":
                    raise ValueError(
                        "The input must have 3 channels; Received "
                        f"`input_shape={input_shape}`"
                    )
                if (
                    input_shape[0] is not None and input_shape[0] < min_size
                ) or (input_shape[1] is not None and input_shape[1] < min_size):
                    raise ValueError(
                        "Input size must be at least "
                        f"{min_size}x{min_size}; Received: "
                        f"input_shape={input_shape}"
                    )
    else:
        if require_flatten:
            input_shape = default_shape
        else:
            if data_format == "channels_first":
                input_shape = (3, None, None)
            else:

View on GitHub (pinned to 7a34a03db6)