Benchmarks
See ENOT.ai in Action: Check out how we've boosted the speed and efficiency of some popular open-source neural networks with our tech. For more detailed results, head to our benchmarks section.
Select model:
Choose hardware*:
Select dataset:
Resnet-50
(ImageNet)
(ImageNet)
Accuracy
MMAC
Acceleration
Baseline
0.76
4144.85
1.0x
enot_optimized_v1
0.75
2057.61
2.01x
enot_optimized_v2
0.74
867.94
4.8x
Vision Transformer (ViT)
(ImageNet)
(ImageNet)
Accuracy
MMAC
Acceleration
Baseline
0.76
4413.99
1.0x
enot_optimized_v1
0.76
911.80
4.84x
enot_optimized_v2
0.74
490.78
8.99x
MobileNet_v2
(ImageNet)
(ImageNet)
Accuracy
MMAC
Acceleration
Baseline
0.72
334.23
1.0x
enot.ai_MN_v2_1
0.71
209.24
1.6x
enot.ai_MN_v2_2
0.70
156.80
2.13x
GPT2-XL
(Lambada)
(Lambada)
Accuracy
Latency
Acceleration
Baseline
0.71
1190 ms
1.0x
enot.ai_optimized
0.72
462 ms
2.58x
GPT-J 6B
(Lambada)
(Lambada)
Accuracy
Latency
Acceleration
Baseline
0.80
1610 ms
1.0x
enot.ai_optimized
0.78
1040 ms
1.55x
GPT-J 6B
(Lambada)
(Lambada)
Accuracy
Size
Compression
Baseline
0.80
12.1 Gb
0%
enot.ai_optimized
0.78
8.5 Gb
30%
Yolo_v5s
(COCO)
(COCO)
mAp
FPS
Acceleration
Baseline
0.43
148
1.0x
enot.ai_optimized
0.42
1021
6.9x
Resnet-50
(CIFAR-100)
(CIFAR-100)
Accuracy
MMAC
Acceleration
Baseline
0.76
1178
1.0x
enot.ai_optimized
0.75
170
6.9x
Resnet-50
(CIFAR-100)
(CIFAR-100)
Accuracy, mAp
FPS
Acceleration
Baseline
0.76
49
1.0x
enot.ai_optimized
0.75
406
8.3x
Resnet-50
(Imagenette)
(Imagenette)
Accuracy, mAp
FPS
Acceleration
Baseline
0.89
190
1.0x
enot.ai_optimized
0.88
2128
11.2x
Resnet-18
(CIFAR-100)
(CIFAR-100)
Accuracy
MMAC
Acceleration
Baseline
0.74
547
1.0x
enot.ai_optimized
0.73
92
5.9x
Resnet-18
(CIFAR-100)
(CIFAR-100)
Accuracy
FPS
Acceleration
Baseline
0.74
155
1.0x
enot.ai_optimized
0.73
1272
8.2x
MobileNet_v2
(Imagenette)
(Imagenette)
Accuracy
FPS
Acceleration
Baseline
0.89
190
1.0x
enot.ai_optimized
0.88
2128
11.2x
MobileNet_v2
(Imagenette)
(Imagenette)
Accuracy
MMAC
Acceleration
Baseline
0.89
299
1.0x
enot.ai_optimized
0.88
75
4.0x
MobileNet_v2
(Imagenette)
(Imagenette)
Accuracy
FPS
Acceleration
Baseline
0.89
3.6
1.0x
enot.ai_optimized
0.88
31.4
8.7x
MobileNet_v2
(CIFAR-100)
(CIFAR-100)
Accuracy
MMAC
Acceleration
Baseline
0.68
54.4
1.0x
enot.ai_optimized
0.67
17.3
3.1x
MobileNet_v2
(CIFAR-100)
(CIFAR-100)
Accuracy
FPS
Acceleration
Baseline
0.68
180
1.0x
enot.ai_optimized
0.67
1598
8.9x
MobileNet v2SSD
(Pascal VOC)
(Pascal VOC)
mAP
FPS
Acceleration
Baseline
0.41
124
1.0x
enot.ai_optimized
0.4
1537
12.4x
MobileNet v2SSD
(Pascal VOC)
(Pascal VOC)
mAP
FPS
Acceleration
Baseline
0.41
2
1.0x
enot.ai_optimized
0.4
13.8
6.9x
MobileNet v2SSD
(Pascal VOC)
(Pascal VOC)
mAP
MMAC
Acceleration
Baseline
0.65
1340
1.0x
enot.ai_optimized
0.63
527
2.5x
HR-net
(Mseg)
(Mseg)
MIoU
MMAC
Acceleration
Baseline
0.44
46256
1.0x
enot.ai_optimized
0.43
17731
2.6x
HR-net
(Mseg)
(Mseg)
MIoU
FPS
Acceleration
Baseline
0.44
11
1.0x
enot.ai_optimized
0.43
47.2
4.3x
*Hardware
Edge CPUs include ARM, NPUs, ARC, <1GHz clock
speed
GPUs include Nvidia-based graphical processing
units
Server CPUs include Intel-based CPUs