DCTNet
DCTNet copied to clipboard
jpeg2dct or cv2.dct
This is a wonderful research idea and thought process. But I have a question now: Are there many differences between jpeg2dct and cv2.dct with blockwise? I have used them to do classification on Cifar10, but they have the same results almostly.
您好,请问cv2.dct 具体是怎么操作的呀?
您好,请问cv2.dct 具体是怎么操作的呀?
貌似是利用到了fft,反正两者计算结果是有差别的,但是最终的效果差不多
您好,jpeg2dct后得到的dct_y、dct_cr、dct_cb ,他是(M,N,64)大小的,这个64维度是不是按照低频到高频排列的,有没有ZigZag呢?
@LBJ23233 请问你利用OpenCV实现的,有对DCT输入进行Normalize进行归一化吗?
Why does the model trained using data returned from jpeg2dct have such poor accuracy? It only achieves 66% accuracy on CIFAR-100