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 0.7815 -0.9216  0.1699  0.1152  2.1548 -0.5407 -0.3781  0.7615  0.3182 -0.8574
#> -0.9832  0.6793  0.8675  0.4983 -1.2282 -0.3332 -0.4461 -0.9655  0.4759 -0.1023
#>  0.0062  0.7361  1.8338  1.1024  0.3314 -1.2581 -1.8184 -1.7320  1.0691 -2.3011
#> -1.8084  1.6769 -0.1621 -0.2397  1.0932 -1.1170  0.0641  2.1635  0.8254 -0.7496
#> -0.6719 -0.7508  1.0796  1.5209 -0.5946 -0.1089  0.3717 -1.5812 -1.1147 -0.7584
#> -1.1140  0.0435 -1.1688  0.7608  0.6744  1.3830  0.8573 -0.3455  0.1661 -0.0531
#>  1.0143  1.5191 -0.1228 -0.1656  0.8978 -1.7626  0.8285  1.1289 -0.3004 -2.5304
#> -0.1843  0.1523  0.3696  0.2722  1.0013 -1.1634 -0.8178 -1.5524  0.7161 -1.1393
#>  0.4387 -1.8466  0.1480 -0.1267  0.4098  0.2664 -1.9241  1.1243 -1.7671  0.1651
#>  0.7291  2.8501 -0.8329  0.4269 -0.0730 -0.1439 -3.2483  0.3002 -0.3955 -0.8389
#> -0.7059  1.2505  0.8071 -0.2948  0.7957 -0.2239  0.3800 -0.9673 -1.3529 -0.9846
#>  0.5126 -1.8847 -1.0562 -0.6032 -0.1634  0.8142  1.5208  0.6206  1.0496  0.1410
#>  1.5942  1.7963 -1.2319  0.6606 -0.5661  0.7338  0.4615 -0.2527  3.0247 -1.8704
#> -0.6375 -1.9146 -1.3290 -0.6898 -0.3093 -0.1283 -0.5299 -0.5063  0.7312 -0.3211
#>  1.1043  0.0018 -0.8729  0.7998 -0.3671  0.4180 -1.4457  0.1789  1.5404 -1.0855
#> -0.1175 -1.1628 -1.3193 -1.4217  0.4870  0.1131 -0.9156  0.6825 -1.2871  1.7007
#> -0.1429 -1.4132 -2.2495 -0.2851  1.9462 -0.4697 -1.9250 -0.1375 -0.1547 -0.4731
#> -1.0298 -1.5706  0.6897  0.5915  0.6087  0.1700 -0.1790 -0.8947 -1.4112  0.5943
#> -0.7398 -1.1171 -0.9756 -0.0213 -2.4743  1.3341 -0.9720  1.3449 -1.1762 -0.8379
#> -0.1971  0.4570  0.5956 -1.5039  0.4385  0.5537 -0.1144  0.2210  0.3769  1.6898
#>  0.2711  0.3167 -0.5235 -0.0366 -1.4653 -0.4550 -0.2064 -0.6326  0.9467 -0.6903
#>  0.1789 -0.6414  0.9133 -0.4242 -1.2109 -0.4718  1.0265 -1.3170  1.0668  1.5787
#> -0.9770 -0.0390  1.0604  0.6794 -0.2683 -0.5172  0.8470  0.2523  0.4452 -0.5226
#> -1.0192  0.3601 -1.4602 -0.0017 -0.1359  0.9426  1.9003 -0.2165  0.1125 -1.2849
#>  0.0197 -1.0769 -0.4867  0.6205 -0.8576 -0.5264 -1.5079  1.0182 -1.3411  0.2347
#>  0.2687  0.5811  1.3578  1.1773  0.1349  0.2014 -0.5129 -0.3566 -0.9541  0.0267
#> -0.3314 -1.0426 -1.3992  0.5741  0.6680 -0.0576 -0.9622  1.1348  1.5647  1.1856
#>  0.8979 -0.7524 -0.0222 -0.0366 -0.1139 -1.7778  0.3693  1.2656 -0.2839 -0.8981
#>  0.5922  0.1434 -2.0587 -0.8918  0.7347  1.4906 -1.1578  1.5241 -0.9877  0.2097
#>  0.6374 -0.1268  1.6524 -0.6022 -1.0846  0.2305 -1.1407 -1.0602  0.1957  0.2920
#> ... [the output was truncated (use n=-1 to disable)]
#> [ CPUFloatType{32,25} ]