search

furiosa-ai / furiosa-models

FuriosaAI Model Zoo Project
https://furiosa-ai.github.io/furiosa-models/
Apache License 2.0
10 stars 6 forks source link

Remove timm dependency #149

Closed furiosamg closed 1 year ago

furiosamg commented 1 year ago

Remove timm as it's unused

furiosa-infra commented 1 year ago

aefedfb ci: remove timm dependency


--------------------------------------------------------------------------------------------------------- benchmark: 9 tests ---------------------------------------------------------------------------------------------------------
Name (time in ms)                                                 Min                   Max                Mean             StdDev              Median                 IQR            Outliers       OPS            Rounds  Iterations
--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
test_mlcommons_resnet50_accuracy                               1.1322 (1.0)        494.7560 (15.57)      5.9675 (1.0)       5.2240 (2.70)       4.3930 (1.0)        1.5018 (1.82)    4157;6658  167.5733 (1.0)       50000           1
test_efficientnetb0_accuracy                                   4.3452 (3.84)     1,043.1289 (32.83)     11.5197 (1.93)      9.0363 (4.67)      10.8360 (2.47)       1.8892 (2.29)     825;3132   86.8078 (0.52)      50000           1
test_mlcommons_ssd_mobilenet_with_native_rust_pp_accuracy      6.9760 (6.16)        31.7707 (1.0)       12.2741 (2.06)      1.9338 (1.0)       12.0570 (2.74)       0.8258 (1.0)       714;752   81.4726 (0.49)       5000           1
test_efficientnetv2s_accuracy                                  7.0695 (6.24)       231.6319 (7.29)      13.6127 (2.28)      5.4640 (2.83)      13.0647 (2.97)       2.0724 (2.51)    1152;2200   73.4608 (0.44)      50000           1
test_mlcommons_ssd_mobilenet_accuracy                          7.5184 (6.64)       174.0021 (5.48)      13.1258 (2.20)      2.8191 (1.46)      13.4770 (3.07)       1.1722 (1.42)     584;1003   76.1856 (0.45)       5000           1
test_yolov5m_accuracy                                          8.4664 (7.48)       196.9866 (6.20)      14.3896 (2.41)      8.7580 (4.53)      12.6614 (2.88)       2.5162 (3.05)      441;938   69.4945 (0.41)      10000           1
test_yolov5l_accuracy                                         11.9093 (10.52)      548.0688 (17.25)     16.0363 (2.69)      8.8978 (4.60)      15.2053 (3.46)       1.6694 (2.02)       72;577   62.3587 (0.37)      10000           1
test_mlcommons_ssd_resnet34_with_native_rust_pp_accuracy      45.4027 (40.10)      746.5673 (23.50)     55.5669 (9.31)     13.0831 (6.77)      55.1854 (12.56)      2.0624 (2.50)       18;266   17.9963 (0.11)       5000           1
test_mlcommons_ssd_resnet34_accuracy                          96.5059 (85.24)    1,802.0015 (56.72)    253.9632 (42.56)    94.1140 (48.67)    214.2267 (48.77)    100.5828 (121.80)    728;129    3.9376 (0.02)       5000           1
--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------

Legend:
  Outliers: 1 Standard Deviation from Mean; 1.5 IQR (InterQuartile Range) from 1st Quartile and 3rd Quartile.
  OPS: Operations Per Second, computed as 1 / Mean