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 10-0.1582  0.3884 -1.5632  0.7196 -0.2205 -1.7835 -0.6661 -1.7264  0.1628 -0.8758
#> -0.3737 -0.8115 -2.1005  0.0627 -0.3045  1.4506 -0.6305  1.2214  0.4031 -1.6824
#>  1.1758 -0.2578  1.1765  1.2256  0.1560  1.0866  0.4820  1.2603 -1.0302  0.6107
#> -0.7562 -0.7093  1.2052  0.4085  0.6378  1.0945  0.4667 -1.4432  0.0582  1.4798
#>  1.4722  0.4526 -0.9765 -0.6692  0.0418  1.0749  0.1325  0.3376 -0.3633 -1.5026
#> -1.0053  0.1446 -0.9803  0.9713 -0.2840  1.2749 -0.1783  0.5447 -1.1221  0.7340
#> -1.2648  0.9723  1.3332 -0.0302 -1.3932 -1.4991 -0.5200  0.4604 -1.3608 -1.3589
#> -0.2860  0.6719 -0.3339 -0.4222 -0.7139  0.4702  0.7931  0.7817  1.8080  0.5962
#> -0.7100 -0.8923 -0.8414 -0.3466  0.4923  1.5249  0.2795 -0.9273 -1.4795  0.7444
#> -0.3146 -0.2754  0.2926 -1.1596  0.9416  0.1110 -1.1205 -0.0890  0.9170  0.1624
#>  0.5040 -0.6209 -0.9784  0.5903  1.1282  0.3059 -0.8232  0.3094  2.3989  0.6833
#> -1.4770  0.5607  1.1840  0.1885  0.5920 -0.9191 -0.2165  0.8742  0.1817  0.4407
#>  0.2939  1.0579 -0.0253  0.6725  0.3855  1.3043  0.4780 -1.5100  1.8916  2.4278
#> -0.4487 -0.0617 -0.4693  0.5218  0.9512  0.4957 -0.8041  1.4929  1.1711  0.7071
#> -1.0296  0.4278  0.0945  1.2844 -0.7579 -0.6359  0.2901  0.8405  1.1472  0.9583
#> -0.9763 -0.5246 -0.7397 -0.9174 -0.0160  0.3348  0.1694  0.7063 -1.0036  0.2076
#> -1.0737 -0.4928  0.9640 -1.3019 -1.1108 -0.0942 -1.2271 -1.8290 -1.2871  0.0771
#>  0.2720  0.9329 -0.5919 -0.3185 -0.7456  0.6240  0.3579  0.0569 -0.8417  0.6781
#>  1.7852 -0.6460 -0.5031 -1.0371 -1.7999 -1.2863  0.3383  1.6757  0.6968  0.5534
#> -0.3035  0.5520 -0.0614  0.3078 -1.8848  0.7427  0.5582  1.0494 -0.1631 -0.3791
#> -0.3747  0.5794  0.8071  0.3757 -1.1108  1.1686 -0.2095  0.8592 -0.1231  1.0735
#> -0.8813  1.5114  0.2924  0.6129 -0.3881 -2.2573  0.5214  0.1533 -0.0338  0.8590
#>  1.2781  0.0083 -0.1498 -1.0427  0.7484  1.3472  0.9627  0.0325  1.1607  1.1250
#> -1.2298  1.9843  0.2211 -0.5208  1.9371 -0.3642 -1.7374  0.2583 -1.6167  1.4653
#> -0.4712  0.2489 -1.9094  0.2164 -0.0392  1.2666 -1.3128  0.1085  0.0182 -0.9435
#>  0.8778  0.8302 -0.6882  0.9876 -1.6937 -1.1158  0.3376  0.3564  1.3662 -0.7732
#> -0.6029 -0.5634 -0.8599  0.2626 -0.2676  0.4334  1.5757  0.6957 -0.9872 -0.5347
#> -0.5906  0.4191  0.6298 -0.7377 -0.6402 -1.8309 -0.0990 -0.8398 -0.7977 -0.5158
#>  0.8678 -0.5494  1.0362 -0.5457  1.0546  0.2354 -0.9924 -0.5687 -2.5281 -0.0860
#> -1.8493 -1.8100  0.1872  0.6671  0.9744 -0.3209  0.3568  0.5125 -1.2613 -0.9642
#> ... [the output was truncated (use n=-1 to disable)]
#> [ CPUFloatType{32,25} ]