Gnuplot not found, using plotters backend
Benchmarking grayscale_u8_rgb/256
Benchmarking grayscale_u8_rgb/256: Warming up for 500.00 ms
Benchmarking grayscale_u8_rgb/256: Collecting 20 samples in estimated 2.0088 s (24k iterations)
Benchmarking grayscale_u8_rgb/256: Analyzing
grayscale_u8_rgb/256    time:   [18.775 µs 23.225 µs 26.558 µs]
                        change: [-8.3890% +7.0621% +25.241%] (p = 0.41 > 0.05)
                        No change in performance detected.
Found 3 outliers among 20 measurements (15.00%)
  3 (15.00%) high severe
Benchmarking grayscale_u8_rgb/512
Benchmarking grayscale_u8_rgb/512: Warming up for 500.00 ms
Benchmarking grayscale_u8_rgb/512: Collecting 20 samples in estimated 2.0401 s (6720 iterations)
Benchmarking grayscale_u8_rgb/512: Analyzing
grayscale_u8_rgb/512    time:   [76.291 µs 79.293 µs 82.230 µs]
                        change: [+12.350% +16.174% +20.570%] (p = 0.00 < 0.05)
                        Performance has regressed.
Found 1 outliers among 20 measurements (5.00%)
  1 (5.00%) high mild
Benchmarking grayscale_u8_rgb/1024
Benchmarking grayscale_u8_rgb/1024: Warming up for 500.00 ms
Benchmarking grayscale_u8_rgb/1024: Collecting 20 samples in estimated 2.1330 s (3150 iterations)
Benchmarking grayscale_u8_rgb/1024: Analyzing
grayscale_u8_rgb/1024   time:   [321.04 µs 325.85 µs 332.57 µs]
                        change: [+17.232% +22.683% +28.021%] (p = 0.00 < 0.05)
                        Performance has regressed.

Benchmarking grayscale_f32_rgb/256
Benchmarking grayscale_f32_rgb/256: Warming up for 500.00 ms
Benchmarking grayscale_f32_rgb/256: Collecting 20 samples in estimated 2.0225 s (17k iterations)
Benchmarking grayscale_f32_rgb/256: Analyzing
grayscale_f32_rgb/256   time:   [65.959 µs 67.463 µs 69.216 µs]
                        change: [-35.242% -32.381% -29.704%] (p = 0.00 < 0.05)
                        Performance has improved.
Found 2 outliers among 20 measurements (10.00%)
  1 (5.00%) low mild
  1 (5.00%) high mild
Benchmarking grayscale_f32_rgb/512
Benchmarking grayscale_f32_rgb/512: Warming up for 500.00 ms
Benchmarking grayscale_f32_rgb/512: Collecting 20 samples in estimated 2.0702 s (3150 iterations)
Benchmarking grayscale_f32_rgb/512: Analyzing
grayscale_f32_rgb/512   time:   [286.52 µs 289.97 µs 293.73 µs]
                        change: [-32.177% -29.147% -25.413%] (p = 0.00 < 0.05)
                        Performance has improved.
Found 1 outliers among 20 measurements (5.00%)
  1 (5.00%) high severe
Benchmarking grayscale_f32_rgb/1024
Benchmarking grayscale_f32_rgb/1024: Warming up for 500.00 ms
Benchmarking grayscale_f32_rgb/1024: Collecting 20 samples in estimated 2.2701 s (420 iterations)
Benchmarking grayscale_f32_rgb/1024: Analyzing
grayscale_f32_rgb/1024  time:   [2.0277 ms 2.1202 ms 2.2097 ms]
                        change: [-21.536% -14.808% -7.2363%] (p = 0.00 < 0.05)
                        Performance has improved.
Found 1 outliers among 20 measurements (5.00%)
  1 (5.00%) high severe

Benchmarking threshold_u8/256
Benchmarking threshold_u8/256: Warming up for 500.00 ms
Benchmarking threshold_u8/256: Collecting 20 samples in estimated 2.0011 s (287k iterations)
Benchmarking threshold_u8/256: Analyzing
threshold_u8/256        time:   [2.9689 µs 3.2225 µs 3.3795 µs]
                        change: [-13.651% -2.0639% +11.848%] (p = 0.76 > 0.05)
                        No change in performance detected.
Benchmarking threshold_u8/512
Benchmarking threshold_u8/512: Warming up for 500.00 ms
Benchmarking threshold_u8/512: Collecting 20 samples in estimated 2.0017 s (79k iterations)
Benchmarking threshold_u8/512: Analyzing
threshold_u8/512        time:   [10.547 µs 11.747 µs 12.655 µs]
                        change: [-18.284% -6.0075% +8.9901%] (p = 0.42 > 0.05)
                        No change in performance detected.
Benchmarking threshold_u8/1024
Benchmarking threshold_u8/1024: Warming up for 500.00 ms
Benchmarking threshold_u8/1024: Collecting 20 samples in estimated 2.0233 s (16k iterations)
Benchmarking threshold_u8/1024: Analyzing
threshold_u8/1024       time:   [44.029 µs 45.899 µs 47.108 µs]
                        change: [-8.0004% -2.6755% +2.5679%] (p = 0.34 > 0.05)
                        No change in performance detected.

Benchmarking threshold_u8_cropped/256
Benchmarking threshold_u8_cropped/256: Warming up for 500.00 ms
Benchmarking threshold_u8_cropped/256: Collecting 20 samples in estimated 2.0023 s (148k iterations)
Benchmarking threshold_u8_cropped/256: Analyzing
threshold_u8_cropped/256
                        time:   [8.7202 µs 9.0815 µs 9.4911 µs]
                        change: [+12.491% +19.411% +26.193%] (p = 0.00 < 0.05)
                        Performance has regressed.
Found 3 outliers among 20 measurements (15.00%)
  2 (10.00%) high mild
  1 (5.00%) high severe
Benchmarking threshold_u8_cropped/512
Benchmarking threshold_u8_cropped/512: Warming up for 500.00 ms
Benchmarking threshold_u8_cropped/512: Collecting 20 samples in estimated 2.0006 s (58k iterations)
Benchmarking threshold_u8_cropped/512: Analyzing
threshold_u8_cropped/512
                        time:   [21.198 µs 22.950 µs 24.798 µs]
                        change: [+1.8047% +10.689% +21.448%] (p = 0.03 < 0.05)
                        Performance has regressed.
Found 2 outliers among 20 measurements (10.00%)
  1 (5.00%) high mild
  1 (5.00%) high severe
Benchmarking threshold_u8_cropped/1024
Benchmarking threshold_u8_cropped/1024: Warming up for 500.00 ms
Benchmarking threshold_u8_cropped/1024: Collecting 20 samples in estimated 2.0046 s (11k iterations)
Benchmarking threshold_u8_cropped/1024: Analyzing
threshold_u8_cropped/1024
                        time:   [95.917 µs 97.149 µs 98.505 µs]
                        change: [+3.4282% +5.1587% +6.7853%] (p = 0.00 < 0.05)
                        Performance has regressed.
Found 1 outliers among 20 measurements (5.00%)
  1 (5.00%) high mild

Benchmarking cast_f32_to_u8/256
Benchmarking cast_f32_to_u8/256: Warming up for 500.00 ms
Benchmarking cast_f32_to_u8/256: Collecting 20 samples in estimated 2.0362 s (9870 iterations)
Benchmarking cast_f32_to_u8/256: Analyzing
cast_f32_to_u8/256      time:   [139.82 µs 144.50 µs 149.11 µs]
                        change: [+0.5605% +3.5501% +6.4707%] (p = 0.03 < 0.05)
                        Change within noise threshold.
Benchmarking cast_f32_to_u8/512
Benchmarking cast_f32_to_u8/512: Warming up for 500.00 ms
Benchmarking cast_f32_to_u8/512: Collecting 20 samples in estimated 2.0740 s (2310 iterations)
Benchmarking cast_f32_to_u8/512: Analyzing
cast_f32_to_u8/512      time:   [577.20 µs 588.48 µs 602.27 µs]
                        change: [+6.3441% +8.8902% +11.974%] (p = 0.00 < 0.05)
                        Performance has regressed.
Benchmarking cast_f32_to_u8/1024
Benchmarking cast_f32_to_u8/1024: Warming up for 500.00 ms
Benchmarking cast_f32_to_u8/1024: Collecting 20 samples in estimated 2.9452 s (420 iterations)
Benchmarking cast_f32_to_u8/1024: Analyzing
cast_f32_to_u8/1024     time:   [3.0091 ms 3.0903 ms 3.1593 ms]
                        change: [+1.9328% +6.7315% +11.252%] (p = 0.01 < 0.05)
                        Performance has regressed.
Found 1 outliers among 20 measurements (5.00%)
  1 (5.00%) low mild

Benchmarking cast_u8_to_f32/256
Benchmarking cast_u8_to_f32/256: Warming up for 500.00 ms
Benchmarking cast_u8_to_f32/256: Collecting 20 samples in estimated 2.0064 s (33k iterations)
Benchmarking cast_u8_to_f32/256: Analyzing
cast_u8_to_f32/256      time:   [44.821 µs 46.385 µs 47.531 µs]
                        change: [-6.9689% +1.4418% +11.456%] (p = 0.76 > 0.05)
                        No change in performance detected.
Benchmarking cast_u8_to_f32/512
Benchmarking cast_u8_to_f32/512: Warming up for 500.00 ms
Benchmarking cast_u8_to_f32/512: Collecting 20 samples in estimated 2.0133 s (7980 iterations)
Benchmarking cast_u8_to_f32/512: Analyzing
cast_u8_to_f32/512      time:   [181.31 µs 182.98 µs 185.08 µs]
                        change: [+2.9678% +5.5017% +7.8226%] (p = 0.00 < 0.05)
                        Performance has regressed.
Found 2 outliers among 20 measurements (10.00%)
  2 (10.00%) high mild
Benchmarking cast_u8_to_f32/1024
Benchmarking cast_u8_to_f32/1024: Warming up for 500.00 ms
Benchmarking cast_u8_to_f32/1024: Collecting 20 samples in estimated 2.0713 s (1050 iterations)
Benchmarking cast_u8_to_f32/1024: Analyzing
cast_u8_to_f32/1024     time:   [1.2608 ms 1.3072 ms 1.3639 ms]
                        change: [+11.923% +20.207% +29.113%] (p = 0.00 < 0.05)
                        Performance has regressed.
Found 1 outliers among 20 measurements (5.00%)
  1 (5.00%) high mild

Benchmarking materialize_flip_h_u8/256
Benchmarking materialize_flip_h_u8/256: Warming up for 500.00 ms
Benchmarking materialize_flip_h_u8/256: Collecting 20 samples in estimated 2.0214 s (5250 iterations)
Benchmarking materialize_flip_h_u8/256: Analyzing
materialize_flip_h_u8/256
                        time:   [376.81 µs 401.94 µs 435.63 µs]
                        change: [+603.49% +649.29% +701.80%] (p = 0.00 < 0.05)
                        Performance has regressed.
Found 3 outliers among 20 measurements (15.00%)
  2 (10.00%) high mild
  1 (5.00%) high severe
Benchmarking materialize_flip_h_u8/512
Benchmarking materialize_flip_h_u8/512: Warming up for 500.00 ms
Benchmarking materialize_flip_h_u8/512: Collecting 20 samples in estimated 2.0600 s (1260 iterations)
Benchmarking materialize_flip_h_u8/512: Analyzing
materialize_flip_h_u8/512
                        time:   [1.5047 ms 1.5559 ms 1.6306 ms]
                        change: [+543.27% +560.65% +579.92%] (p = 0.00 < 0.05)
                        Performance has regressed.
Found 1 outliers among 20 measurements (5.00%)
  1 (5.00%) high severe
Benchmarking materialize_flip_h_u8/1024
Benchmarking materialize_flip_h_u8/1024: Warming up for 500.00 ms
Benchmarking materialize_flip_h_u8/1024: Collecting 20 samples in estimated 3.1249 s (420 iterations)
Benchmarking materialize_flip_h_u8/1024: Analyzing
materialize_flip_h_u8/1024
                        time:   [6.3037 ms 6.4731 ms 6.8373 ms]
                        change: [+443.26% +471.95% +506.46%] (p = 0.00 < 0.05)
                        Performance has regressed.
Found 1 outliers among 20 measurements (5.00%)
  1 (5.00%) high severe

Benchmarking materialize_flip_v_u8/256
Benchmarking materialize_flip_v_u8/256: Warming up for 500.00 ms
Benchmarking materialize_flip_v_u8/256: Collecting 20 samples in estimated 2.0534 s (5250 iterations)
Benchmarking materialize_flip_v_u8/256: Analyzing
materialize_flip_v_u8/256
                        time:   [372.61 µs 376.22 µs 381.40 µs]
                        change: [+3723.9% +4044.5% +4443.8%] (p = 0.00 < 0.05)
                        Performance has regressed.
Found 2 outliers among 20 measurements (10.00%)
  2 (10.00%) high severe
Benchmarking materialize_flip_v_u8/512
Benchmarking materialize_flip_v_u8/512: Warming up for 500.00 ms
Benchmarking materialize_flip_v_u8/512: Collecting 20 samples in estimated 2.2260 s (1260 iterations)
Benchmarking materialize_flip_v_u8/512: Analyzing
materialize_flip_v_u8/512
                        time:   [1.5024 ms 1.5214 ms 1.5457 ms]
                        change: [+2405.1% +2465.9% +2530.1%] (p = 0.00 < 0.05)
                        Performance has regressed.
Found 1 outliers among 20 measurements (5.00%)
  1 (5.00%) high mild
Benchmarking materialize_flip_v_u8/1024
Benchmarking materialize_flip_v_u8/1024: Warming up for 500.00 ms
Benchmarking materialize_flip_v_u8/1024: Collecting 20 samples in estimated 3.0248 s (420 iterations)
Benchmarking materialize_flip_v_u8/1024: Analyzing
materialize_flip_v_u8/1024
                        time:   [6.3516 ms 6.4574 ms 6.5711 ms]
                        change: [+2141.3% +2369.3% +2680.2%] (p = 0.00 < 0.05)
                        Performance has regressed.
Found 2 outliers among 20 measurements (10.00%)
  2 (10.00%) high severe

Benchmarking materialize_transpose_u8/256
Benchmarking materialize_transpose_u8/256: Warming up for 500.00 ms
Benchmarking materialize_transpose_u8/256: Collecting 20 samples in estimated 2.0690 s (4200 iterations)
Benchmarking materialize_transpose_u8/256: Analyzing
materialize_transpose_u8/256
                        time:   [373.98 µs 381.71 µs 389.10 µs]
                        change: [+498.65% +528.64% +555.61%] (p = 0.00 < 0.05)
                        Performance has regressed.
Found 3 outliers among 20 measurements (15.00%)
  2 (10.00%) high mild
  1 (5.00%) high severe
Benchmarking materialize_transpose_u8/512
Benchmarking materialize_transpose_u8/512: Warming up for 500.00 ms
Benchmarking materialize_transpose_u8/512: Collecting 20 samples in estimated 2.1131 s (1260 iterations)
Benchmarking materialize_transpose_u8/512: Analyzing
materialize_transpose_u8/512
                        time:   [1.6973 ms 1.7918 ms 1.8759 ms]
                        change: [+375.81% +416.61% +457.08%] (p = 0.00 < 0.05)
                        Performance has regressed.
Benchmarking materialize_transpose_u8/1024
Benchmarking materialize_transpose_u8/1024: Warming up for 500.00 ms

Warning: Unable to complete 20 samples in 2.0s. You may wish to increase target time to 3.3s, enable flat sampling, or reduce sample count to 10.
Benchmarking materialize_transpose_u8/1024: Collecting 20 samples in estimated 3.3147 s (210 iterations)
Benchmarking materialize_transpose_u8/1024: Analyzing
materialize_transpose_u8/1024
                        time:   [13.515 ms 14.082 ms 14.927 ms]
                        change: [+227.66% +248.01% +269.54%] (p = 0.00 < 0.05)
                        Performance has regressed.
Found 3 outliers among 20 measurements (15.00%)
  3 (15.00%) high mild

Benchmarking cast_u8_to_f32_flip_h/256
Benchmarking cast_u8_to_f32_flip_h/256: Warming up for 500.00 ms
Benchmarking cast_u8_to_f32_flip_h/256: Collecting 20 samples in estimated 2.1027 s (4200 iterations)
Benchmarking cast_u8_to_f32_flip_h/256: Analyzing
cast_u8_to_f32_flip_h/256
                        time:   [484.81 µs 504.36 µs 531.14 µs]
                        change: [+436.90% +458.36% +480.64%] (p = 0.00 < 0.05)
                        Performance has regressed.
Found 3 outliers among 20 measurements (15.00%)
  1 (5.00%) high mild
  2 (10.00%) high severe
Benchmarking cast_u8_to_f32_flip_h/512
Benchmarking cast_u8_to_f32_flip_h/512: Warming up for 500.00 ms
Benchmarking cast_u8_to_f32_flip_h/512: Collecting 20 samples in estimated 2.0459 s (1050 iterations)
Benchmarking cast_u8_to_f32_flip_h/512: Analyzing
cast_u8_to_f32_flip_h/512
                        time:   [1.8420 ms 1.9299 ms 2.0646 ms]
                        change: [+367.37% +384.99% +405.63%] (p = 0.00 < 0.05)
                        Performance has regressed.
Found 1 outliers among 20 measurements (5.00%)
  1 (5.00%) high severe
Benchmarking cast_u8_to_f32_flip_h/1024
Benchmarking cast_u8_to_f32_flip_h/1024: Warming up for 500.00 ms

Warning: Unable to complete 20 samples in 2.0s. You may wish to increase target time to 2.1s, enable flat sampling, or reduce sample count to 10.
Benchmarking cast_u8_to_f32_flip_h/1024: Collecting 20 samples in estimated 2.0924 s (210 iterations)
Benchmarking cast_u8_to_f32_flip_h/1024: Analyzing
cast_u8_to_f32_flip_h/1024
                        time:   [8.8441 ms 9.3967 ms 9.9738 ms]
                        change: [+256.43% +272.99% +290.13%] (p = 0.00 < 0.05)
                        Performance has regressed.
Found 1 outliers among 20 measurements (5.00%)
  1 (5.00%) high mild

Benchmarking scale_f32_transposed/256
Benchmarking scale_f32_transposed/256: Warming up for 500.00 ms
Benchmarking scale_f32_transposed/256: Collecting 20 samples in estimated 2.2200 s (1680 iterations)
Benchmarking scale_f32_transposed/256: Analyzing
scale_f32_transposed/256
                        time:   [1.2060 ms 1.2195 ms 1.2342 ms]
                        change: [+485.12% +518.82% +549.76%] (p = 0.00 < 0.05)
                        Performance has regressed.
Benchmarking scale_f32_transposed/512
Benchmarking scale_f32_transposed/512: Warming up for 500.00 ms
Benchmarking scale_f32_transposed/512: Collecting 20 samples in estimated 3.4469 s (420 iterations)
Benchmarking scale_f32_transposed/512: Analyzing
scale_f32_transposed/512
                        time:   [7.6052 ms 8.0400 ms 8.5042 ms]
                        change: [+413.38% +455.23% +510.48%] (p = 0.00 < 0.05)
                        Performance has regressed.
Found 1 outliers among 20 measurements (5.00%)
  1 (5.00%) high severe
Benchmarking scale_f32_transposed/1024
Benchmarking scale_f32_transposed/1024: Warming up for 500.00 ms
Benchmarking scale_f32_transposed/1024: Collecting 20 samples in estimated 3.0416 s (40 iterations)
Benchmarking scale_f32_transposed/1024: Analyzing
scale_f32_transposed/1024
                        time:   [56.476 ms 57.659 ms 58.998 ms]
                        change: [+219.35% +228.83% +238.31%] (p = 0.00 < 0.05)
                        Performance has regressed.
Found 2 outliers among 20 measurements (10.00%)
  2 (10.00%) high mild

Benchmarking grayscale_u8_flip_h/256
Benchmarking grayscale_u8_flip_h/256: Warming up for 500.00 ms
Benchmarking grayscale_u8_flip_h/256: Collecting 20 samples in estimated 2.0953 s (4410 iterations)
Benchmarking grayscale_u8_flip_h/256: Analyzing
grayscale_u8_flip_h/256 time:   [470.97 µs 481.46 µs 493.97 µs]
                        change: [+541.23% +559.45% +576.87%] (p = 0.00 < 0.05)
                        Performance has regressed.
Found 1 outliers among 20 measurements (5.00%)
  1 (5.00%) high mild
Benchmarking grayscale_u8_flip_h/512
Benchmarking grayscale_u8_flip_h/512: Warming up for 500.00 ms
Benchmarking grayscale_u8_flip_h/512: Collecting 20 samples in estimated 2.2352 s (1260 iterations)
Benchmarking grayscale_u8_flip_h/512: Analyzing
grayscale_u8_flip_h/512 time:   [1.5963 ms 1.6913 ms 1.8247 ms]
                        change: [+446.25% +470.99% +505.16%] (p = 0.00 < 0.05)
                        Performance has regressed.
Found 3 outliers among 20 measurements (15.00%)
  3 (15.00%) high severe
Benchmarking grayscale_u8_flip_h/1024
Benchmarking grayscale_u8_flip_h/1024: Warming up for 500.00 ms
Benchmarking grayscale_u8_flip_h/1024: Collecting 20 samples in estimated 3.1521 s (420 iterations)
Benchmarking grayscale_u8_flip_h/1024: Analyzing
grayscale_u8_flip_h/1024
                        time:   [6.7954 ms 6.9706 ms 7.2871 ms]
                        change: [+397.00% +415.37% +436.48%] (p = 0.00 < 0.05)
                        Performance has regressed.
Found 2 outliers among 20 measurements (10.00%)
  2 (10.00%) high severe

Benchmarking resize_224_u8/256
Benchmarking resize_224_u8/256: Warming up for 500.00 ms
Benchmarking resize_224_u8/256: Collecting 20 samples in estimated 2.0025 s (7560 iterations)
Benchmarking resize_224_u8/256: Analyzing
resize_224_u8/256       time:   [248.23 µs 249.27 µs 250.45 µs]
                        change: [-15.082% -9.7581% -5.1991%] (p = 0.00 < 0.05)
                        Performance has improved.
Benchmarking resize_224_u8/512
Benchmarking resize_224_u8/512: Warming up for 500.00 ms
Benchmarking resize_224_u8/512: Collecting 20 samples in estimated 2.0905 s (4830 iterations)
Benchmarking resize_224_u8/512: Analyzing
resize_224_u8/512       time:   [383.72 µs 401.45 µs 419.75 µs]
                        change: [-4.6036% -2.4127% +0.1841%] (p = 0.06 > 0.05)
                        No change in performance detected.
Found 4 outliers among 20 measurements (20.00%)
  3 (15.00%) high mild
  1 (5.00%) high severe
Benchmarking resize_224_u8/1024
Benchmarking resize_224_u8/1024: Warming up for 500.00 ms
Benchmarking resize_224_u8/1024: Collecting 20 samples in estimated 2.0248 s (1680 iterations)
Benchmarking resize_224_u8/1024: Analyzing
resize_224_u8/1024      time:   [884.85 µs 910.36 µs 937.74 µs]
                        change: [+4.8708% +7.7001% +10.848%] (p = 0.00 < 0.05)
                        Performance has regressed.
Found 1 outliers among 20 measurements (5.00%)
  1 (5.00%) high mild

Benchmarking crop_then_resize_224_u8/256
Benchmarking crop_then_resize_224_u8/256: Warming up for 500.00 ms
Benchmarking crop_then_resize_224_u8/256: Collecting 20 samples in estimated 2.0075 s (4410 iterations)
Benchmarking crop_then_resize_224_u8/256: Analyzing
crop_then_resize_224_u8/256
                        time:   [425.15 µs 427.64 µs 431.58 µs]
                        change: [+79.423% +98.704% +124.30%] (p = 0.00 < 0.05)
                        Performance has regressed.
Found 3 outliers among 20 measurements (15.00%)
  3 (15.00%) high severe
Benchmarking crop_then_resize_224_u8/512
Benchmarking crop_then_resize_224_u8/512: Warming up for 500.00 ms
Benchmarking crop_then_resize_224_u8/512: Collecting 20 samples in estimated 2.1742 s (1680 iterations)
Benchmarking crop_then_resize_224_u8/512: Analyzing
crop_then_resize_224_u8/512
                        time:   [1.2113 ms 1.2413 ms 1.2841 ms]
                        change: [+192.44% +210.13% +233.91%] (p = 0.00 < 0.05)
                        Performance has regressed.
Found 1 outliers among 20 measurements (5.00%)
  1 (5.00%) high severe
Benchmarking crop_then_resize_224_u8/1024
Benchmarking crop_then_resize_224_u8/1024: Warming up for 500.00 ms
Benchmarking crop_then_resize_224_u8/1024: Collecting 20 samples in estimated 2.0290 s (420 iterations)
Benchmarking crop_then_resize_224_u8/1024: Analyzing
crop_then_resize_224_u8/1024
                        time:   [4.2075 ms 4.3878 ms 4.6099 ms]
                        change: [+361.57% +395.27% +429.98%] (p = 0.00 < 0.05)
                        Performance has regressed.
Found 3 outliers among 20 measurements (15.00%)
  2 (10.00%) high mild
  1 (5.00%) high severe
