分类：全部列表
一、数据生成1.1手写数组a=np.array([1,2,3,4,5,6,7,8,9,10,11])#一维数组b=np.array([[1,2],[3,4]])#二维数组1.2序列数组numpy.arange(start,stop,step,dtype)，start默认0，step默认1c=np.arange(0,10,1,dtype=int)#=np.arange(10)[0123456789]d=np.array([np.arange(1,3),np.arange(4,6)])#二维数组#不过为了避免麻烦，通常序列二维数组都是通过reshape进行重新组织dd=...
继续阅读 >
一、model.py1.1ChannelShuffledefchannel_shuffle(x:Tensor,groups:int)->Tensor:batch_size,num_channels,height,width=x.size()channels_per_group=num_channels//groups#reshape#[batch_size,num_channels,height,width]->[batch_size,groups,channels_per_group,height,width]x=x.view(batch_size,groups,channels_per_group,height,width)x=torch.transpose(x,...
继续阅读 >
