User | NikitaSolovey |
Upload Date | August 16 2024 11:50 PM |
Views | 7 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A14 Bionic |
System Information | |
---|---|
Operating System | iOS 17.6.1 |
Model | iPhone 12 Pro |
Model ID | iPhone13,3 |
Motherboard | D53pAP |
CPU Information | |
---|---|
Name | Apple A14 Bionic |
Topology | 1 Processor, 6 Cores |
Identifier | ARM |
Base Frequency | 2.99 GHz |
Cluster 1 | 2 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 5.54 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
933
173.6 IPS |
|
Image Classification (HP)
|
100% |
4159
773.5 IPS |
|
Image Classification (Q)
|
99% |
5193
968.6 IPS |
|
Image Segmentation (SP)
|
100% |
573
9.30 IPS |
|
Image Segmentation (HP)
|
100% |
3637
59.0 IPS |
|
Image Segmentation (Q)
|
100% |
3622
58.7 IPS |
|
Pose Estimation (SP)
|
100% |
3880
4.53 IPS |
|
Pose Estimation (HP)
|
100% |
55875
65.2 IPS |
|
Pose Estimation (Q)
|
94% |
54491
63.9 IPS |
|
Object Detection (SP)
|
100% |
894
70.9 IPS |
|
Object Detection (HP)
|
99% |
4634
368.6 IPS |
|
Object Detection (Q)
|
93% |
4524
361.0 IPS |
|
Face Detection (SP)
|
100% |
1493
17.7 IPS |
|
Face Detection (HP)
|
100% |
8430
100.2 IPS |
|
Face Detection (Q)
|
100% |
8780
104.3 IPS |
|
Depth Estimation (SP)
|
100% |
2172
16.7 IPS |
|
Depth Estimation (HP)
|
99% |
26470
203.9 IPS |
|
Depth Estimation (Q)
|
97% |
26023
201.2 IPS |
|
Style Transfer (SP)
|
100% |
5301
6.81 IPS |
|
Style Transfer (HP)
|
100% |
72359
93.0 IPS |
|
Style Transfer (Q)
|
100% |
80311
103.2 IPS |
|
Image Super-Resolution (SP)
|
100% |
2037
75.2 IPS |
|
Image Super-Resolution (HP)
|
100% |
13152
485.6 IPS |
|
Image Super-Resolution (Q)
|
98% |
14369
532.4 IPS |
|
Text Classification (SP)
|
100% |
1142
1.52 KIPS |
|
Text Classification (HP)
|
100% |
2360
3.15 KIPS |
|
Text Classification (Q)
|
93% |
2326
3.12 KIPS |
|
Machine Translation (SP)
|
100% |
959
16.5 IPS |
|
Machine Translation (HP)
|
100% |
1286
22.1 IPS |
|
Machine Translation (Q)
|
98% |
1295
22.4 IPS |