Skip to content

Latest commit

 

History

History
698 lines (379 loc) · 22.9 KB

File metadata and controls

698 lines (379 loc) · 22.9 KB

Public Models

  • System host: Intel® Core™ i5-9400 CPU @ 2.90GHz
  • Hailo Dataflow Compiler Version v5.3.0
  • Measurement conditions: Measuring from the SoC, room temperature

Classification


Link Legend


Key / Icon Description
Networks used by Hailo-apps.
S Source – Link to the model's open-source repository.
PT Pretrained – Download the pretrained model file (ZIP format).
HEF, NV12, RGBX Compiled Models – Links to models in various formats: - HEF: RGB format - NV12: NV12 format - RGBX: RGBX format
PR Profiler Report – Download the model's performance profiling report.

Imagenet


Network Name float Accuracy (top1) Hardware Accuracy (top1) FPS (Batch Size=1) FPS (Batch Size=8) Links Input Resolution (HxWxC) Params (M) OPS (G)
cas_vit_m 81.2 81.0 50.7 87.9 384x384x3 12.42 10.89
cas_vit_s 79.8 79.6 68.2 122 384x384x3 5.5 5.4
cas_vit_t 81.9 81.5 37.1 61.0 384x384x3 21.76 20.85
deit_base 80.7 78.9 34.5 80.0 224x224x3 80.26 35.22
deit_small 78.1 77.5 82.5 175 224x224x3 20.52 9.4
efficientnet_l 80.5 79.3 66.3 95.9 300x300x3 10.55 19.4
efficientnet_lite0 75.0 74.0 351 711 224x224x3 4.63 0.78
efficientnet_lite1 76.5 76.0 256 524 240x240x3 5.39 1.22
efficientnet_lite2 77.5 76.5 150 271 260x260x3 6.06 1.74
efficientnet_lite3 79.3 78.6 113 197 280x280x3 8.16 2.8
efficientnet_lite4 80.8 80.1 73.2 124 300x300x3 12.95 5.10
efficientnet_m 78.8 78.3 154 252 240x240x3 6.87 7.32
fastvit_sa12⭐ 79.7 76.6 163 352 224x224x3 11.99 3.59
hardnet39ds⭐ 73.3 72.9 364 774 224x224x3 3.48 0.86
hardnet68⭐ 75.3 75.1 123 252 224x224x3 17.56 8.5
inception_v1 69.7 69.4 330 584 224x224x3 6.62 3
mobilenet_v1 70.8 70.1 574 1207 224x224x3 4.22 1.14
mobilenet_v2_1.0 71.6 70.9 453 883 224x224x3 3.49 0.62
mobilenet_v2_1.4 73.8 73.0 335 638 224x224x3 6.09 1.18
mobilenet_v3 72.0 71.7 399 825 224x224x3 4.07 2
regnetx_1.6gf 76.8 76.4 311 674 224x224x3 9.17 3.22
regnetx_800mf 75.0 74.7 498 1316 224x224x3 7.24 1.6
repghost_1_0x 73.0 72.1 272 607 224x224x3 4.1 0.28
repghost_2_0x 77.2 76.9 155 322 224x224x3 9.8 1.04
repvgg_a1 74.4 72.1 285 648 224x224x3 12.79 4.7
repvgg_a2 76.4 74.5 148 296 224x224x3 25.5 10.2
resmlp12_relu 74.9 74.6 114 374 224x224x3 15.77 6.04
resnet_v1_18⭐ 71.1 70.6 377 786 224x224x3 11.68 3.64
resnet_v1_34⭐ 72.6 72.1 176 415 224x224x3 21.79 7.34
resnet_v1_50⭐ 75.2 74.6 159 379 224x224x3 25.53 6.98
resnext26_32x4d 76.0 75.7 200 446 224x224x3 15.37 4.96
resnext50_32x4d 79.3 78.4 133 287 224x224x3 24.99 8.48
squeezenet_v1.1 59.6 59.1 784 1266 224x224x3 1.24 0.78
vit_base 84.2 83.0 34.5 80.0 224x224x3 86.5 35.188
vit_large 83.2 82.0 9.63 21.1 224x224x3 304.2 123.4
vit_small_bn 77.9 77.2 142 351 224x224x3 21.12 8.62
vit_tiny_bn 68.5 67.0 240 629 224x224x3 5.73 2.2