convert to onnx and then convert to CoreML , but the prediction is wrong

[douli9862]

🐞Describe the bug

onnx to CoreML， but onnx's upsample BILINEAR cannot find the corresponding op in CoreML； CoreML :

message UpsampleLayerParams {

/**
 * Scaling Factor.
 * Must be length 2 in order ``[H, W]``.
 * If not set, default value ``[1, 1]`` is used.
 */
repeated uint64 scalingFactor = 1;

enum InterpolationMode {

    NN = 0; /// Nearest Neighbour
    BILINEAR = 1; /// Bilinear

}

InterpolationMode mode = 5;

}

message SamplingMode {

enum Method {

    /**
     * start = 0, end = X-1
     * grid points = numpy.linspace(start, end)
     */
    STRICT_ALIGN_ENDPOINTS_MODE = 0;

    /**
     * if N == 1: start = end = (X-1)/2
     * otherwise, start = 0, end = X-1
     * grid points = numpy.linspace(start, end)
     */
    ALIGN_ENDPOINTS_MODE = 1;

    /**
     * start = 0, end = X - X/N
     * grid points = min(X-1, numpy.linspace(start, end))
     * This is same as the mode used in the upsample layer in this specification, when used with bilinear interpolation. In that case N/X = upsample ratio.
     */
    UPSAMPLE_MODE = 2;

    /**
     * spacing = max(1, X-1)/N
     * start = 0.5 * spacing
     * end = start + (N-1) * spacing
     * grid points = min(X-1, numpy.linspace(start, end))
     */
    ROI_ALIGN_MODE = 3;

}

Method samplingMethod = 1;

}

The effects of the above two methods are not correct；

0.28950363397598267 -0.35252106189727783

[douli9862]

The first picture is the target picture, and the second picture is my converted CoreML effect picture, the third picture is the difference picture; The effect of the previous op is aligned