from mxnet import gluon,initfrom mxnet import autograd,ndfrom mxnet.gluon import nn,loss as glossfrom mxnet.gluon import data as gdata# 二维卷积层def corr2d(X,K):    h, w = K.shape    Y = nd.zeros((X.shape[0] - h + 1,X.shape[1] - w + 1))    for i in range(Y.shape[0]):        for j in range(Y.shape[1]):            Y[i,j] = (X[i: i+h,j:j+w]*K).sum()    return Y# 多通道输入def corr2d_multi_in(X,K):    return nd.add_n(*[corr2d(x,k) for x,k in zip(X,K)])def corr2d_multi_in_out(X,K):    return nd.stack(*[corr2d_multi_in(X,k) for k in K])# 1 * 1 卷积层def corr2d_multi_in_out_1x1(X,K):    c_i, h, w = X.shape    c_o = K.shape[0]    X = X.reshape((c_i,h*w))    K = K.reshape((c_o,c_i))    Y = nd.dot(K,X)    return Y.reshape((c_o,h,w))X = nd.random.uniform(shape=(3,3,3))K = nd.random.uniform(shape=(2,3,1,1))Y1 = corr2d_multi_in_out_1x1(X, K)Y2 = corr2d_multi_in_out(X,K)print((Y1-Y2).norm().asscalar() < 1e-6)