Are there obvious differences in the experimental results brought about by different DCT implementations?

[PeiqinSun]

Thank you for your amazing works. I has some questions. In my cifar-10 experiments, i use 4x4 blocks, and cv2.dct. which like:

    def run_DCT(self, signal):
        rows = (signal.shape[0] // 4)
        cols = (signal.shape[1] // 4)
        patch_matrix = np.zeros((rows, cols, 4, 4))
        for r in range(rows):
            for c in range(cols):
                patch = cv2.dct(signal[r*4 : (r+1)*4, c*4 : (c+1)*4] / 255.)
                patch_matrix[r, c] = patch
        return patch_matrix.reshape(rows, cols, 4*4)

but the performance is worse than in spatial-domain. you just try imageNet? Do you try other dataset of classification? Is a problem of my preprocess data?

[kaix90]

Thank you for posting your question. The degraded performance may be raised by not properly normalizing your DCT data in the preprocessing stage. Thanks.

[B-JackMao]

你好我也遇到了相同的问题，请问您当时的实验效果如何？