torch.bincount#

torch.bincount(input,weights=None,minlength=0)→Tensor#

Count the frequency of each value in an array of non-negative ints.

The number of bins (size 1) is one larger than the largest value ininput unlessinput is empty, in which case the result is atensor of size 0. Ifminlength is specified, the number of bins is at leastminlength and ifinput is empty, then the result is tensor of sizeminlength filled with zeros. Ifn is the value at positioni,out[n]+=weights[i] ifweights is specified elseout[n]+=1.

Note

This operation may produce nondeterministic gradients when given tensors on a CUDA device. SeeReproducibility for more information.

Parameters:

• input (Tensor) – 1-d int tensor

• weights (Tensor) – optional, weight for each value in the input tensor.Should be of same size as input tensor.

• minlength (int) – optional, minimum number of bins. Should be non-negative.

Returns:

a tensor of shapeSize([max(input)+1]) ifinput is non-empty, elseSize(0)

Return type:

output (Tensor)

Example:

>>>input=torch.randint(0,8,(5,),dtype=torch.int64)>>>weights=torch.linspace(0,1,steps=5)>>>input,weights(tensor([4, 3, 6, 3, 4]), tensor([ 0.0000,  0.2500,  0.5000,  0.7500,  1.0000])>>>torch.bincount(input)tensor([0, 0, 0, 2, 2, 0, 1])>>>input.bincount(weights)tensor([0.0000, 0.0000, 0.0000, 1.0000, 1.0000, 0.0000, 0.5000])