Skip to contents

Flattens a contiguous range of dims into a tensor.

Source: R/nn-flatten.R
nn_flatten.Rd

For use with nn_sequential.

Usage

nn_flatten(start_dim = 2, end_dim = -1)

Arguments

start_dim

first dim to flatten (default = 2).

end_dim

last dim to flatten (default = -1).

Shape

  • Input: (*, S_start,..., S_i, ..., S_end, *), where S_i is the size at dimension i and * means any number of dimensions including none.

  • Output: (*, S_start*...*S_i*...S_end, *).

See also

nn_unflatten

Examples

if (torch_is_installed()) {
input <- torch_randn(32, 1, 5, 5)
m <- nn_flatten()
m(input)
}
#> torch_tensor
#> Columns 1 to 10-0.3199 -0.5470  0.6900 -0.4410  0.7617  0.1433 -0.9380  0.3535 -1.2080  0.1720
#>  0.3672  0.3245  2.4987  0.0329 -0.2421  1.7749 -0.3858  0.0299 -1.5719 -1.0935
#>  0.1906  1.1518 -0.8113  0.7621 -0.2383  0.6764 -1.0068  0.3444 -0.9040  0.3299
#>  0.5682  1.0434 -1.4358 -0.6868  0.1968  0.9005 -0.0376  1.1348 -0.4826 -1.2142
#> -0.1885  1.0115  0.0010  0.3205 -0.9197 -2.8422  0.0036 -1.0949 -0.4103 -2.4228
#> -0.1616  0.9570 -0.9730 -0.5115 -0.7795 -0.6466  1.2477  1.9586  1.5921  0.3300
#> -0.2595  1.1271 -0.5637 -0.2949 -1.3485  0.6355  1.6048  0.0823 -1.3432  1.5985
#> -0.0718 -0.4439  1.4137  0.3199  0.4508 -1.1021 -0.7063  0.1385  0.1935 -0.0515
#>  0.4836 -1.0455 -0.0227  0.0323  2.5342  0.5683  0.6712  1.1591 -1.5967  0.7863
#>  0.0818 -1.7147 -0.4228 -0.6275  0.3657 -1.3283  0.2849  1.2881  0.0971  1.0030
#> -0.1574  0.3463 -0.1375  0.8296 -1.7232 -0.7998 -1.2898  0.7290 -0.3915 -0.0916
#>  1.4269 -1.1700  1.5849  1.6556 -0.2754  2.1463 -0.4575  0.1554  1.1298 -1.4076
#> -0.2696 -0.2911  1.5270  0.0218 -0.1632  0.6899 -0.5760 -0.4658  1.7844 -0.7699
#>  0.9222 -0.6399 -1.0585  1.7109 -0.5417  0.5917 -0.0074  1.2141 -0.0365 -0.6880
#> -0.5276 -0.2794 -1.1153 -1.7366  0.0878  2.1912  0.1281 -0.2582  0.3688 -0.6942
#>  0.1641 -1.8687  0.2645 -1.0567  0.8558  1.7184  0.1966 -0.4893  1.3731 -0.2916
#> -0.2796 -0.0801 -2.6216  1.2877 -0.7383  1.4559 -0.7376 -0.8191  0.9838 -0.2870
#> -0.5289  0.2997  0.3484  0.4236  2.0946 -0.5954 -0.9860  1.9025  1.1765  2.6436
#> -0.6257  0.7267 -1.3255 -1.3947  0.3862  0.4103  0.1376 -0.3802 -1.6978 -0.8255
#>  0.1994  1.1267 -0.5165  0.2751  0.3473 -0.2350 -2.8236  0.4303  0.1155  0.1129
#> -1.1642 -0.2489  0.1635 -1.0925  0.6888 -0.7258 -0.4762 -0.4694 -0.3709 -0.4298
#>  0.7046 -0.1109 -0.0571  0.2755  1.1823 -0.2505  0.4844 -0.0388  0.8161  0.0671
#>  0.1539  1.1621 -0.4768 -0.2405  1.7020  1.4349  1.3076 -0.0111  0.6385  1.2546
#>  0.2940 -0.5328  0.2567 -1.5142 -2.0561 -0.1865 -0.1219  0.9133 -0.2866 -0.7963
#> -1.6937 -0.0177 -0.7141 -0.9364 -1.3136 -0.8536 -0.8504 -0.5033  0.1461  0.9744
#>  0.5276 -0.4393  0.8308  1.0943  0.1384 -0.4463  0.8638  0.4720  0.5617 -0.6370
#>  0.4416 -0.0977 -0.4188  0.0910  0.4841 -1.3073 -0.7666 -0.2519 -1.9687 -0.2757
#>  1.4955 -0.4640  0.4704  0.0696  0.7688  2.1967 -0.0799 -1.0043 -1.7932  0.0867
#> -0.5049 -1.3557  0.7561  0.8408 -0.8754  0.2716  0.0061  0.0291 -0.7523 -1.2831
#> -0.1470 -1.1432 -0.5351 -0.7528 -0.4445 -0.5141  0.7747  1.7050  0.7797 -0.8719
#> ... [the output was truncated (use n=-1 to disable)]
#> [ CPUFloatType{32,25} ]