User | coolcube |
Upload Date | August 15 2024 08:33 PM |
Views | 5 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A14 Bionic |
System Information | |
---|---|
Operating System | iOS 17.6.1 |
Model | iPhone 12 Pro Max |
Model ID | iPhone13,4 |
Motherboard | D54pAP |
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 | 5.52 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
943
175.4 IPS |
|
Image Classification (HP)
|
100% |
4112
764.7 IPS |
|
Image Classification (Q)
|
99% |
5046
941.2 IPS |
|
Image Segmentation (SP)
|
100% |
589
9.55 IPS |
|
Image Segmentation (HP)
|
100% |
3719
60.3 IPS |
|
Image Segmentation (Q)
|
100% |
3616
58.6 IPS |
|
Pose Estimation (SP)
|
100% |
5119
5.97 IPS |
|
Pose Estimation (HP)
|
100% |
59735
69.7 IPS |
|
Pose Estimation (Q)
|
94% |
58917
69.1 IPS |
|
Object Detection (SP)
|
100% |
1013
80.4 IPS |
|
Object Detection (HP)
|
99% |
5354
425.9 IPS |
|
Object Detection (Q)
|
93% |
5034
401.6 IPS |
|
Face Detection (SP)
|
100% |
1687
20.0 IPS |
|
Face Detection (HP)
|
100% |
11318
134.5 IPS |
|
Face Detection (Q)
|
100% |
10582
125.7 IPS |
|
Depth Estimation (SP)
|
100% |
3339
25.7 IPS |
|
Depth Estimation (HP)
|
99% |
31821
245.2 IPS |
|
Depth Estimation (Q)
|
97% |
36501
282.2 IPS |
|
Style Transfer (SP)
|
100% |
9148
11.8 IPS |
|
Style Transfer (HP)
|
100% |
92526
118.9 IPS |
|
Style Transfer (Q)
|
100% |
101078
129.9 IPS |
|
Image Super-Resolution (SP)
|
100% |
2401
88.7 IPS |
|
Image Super-Resolution (HP)
|
100% |
14816
547.1 IPS |
|
Image Super-Resolution (Q)
|
98% |
15905
589.3 IPS |
|
Text Classification (SP)
|
100% |
1154
1.54 KIPS |
|
Text Classification (HP)
|
100% |
2768
3.69 KIPS |
|
Text Classification (Q)
|
93% |
2532
3.40 KIPS |
|
Machine Translation (SP)
|
100% |
658
11.3 IPS |
|
Machine Translation (HP)
|
100% |
1067
18.4 IPS |
|
Machine Translation (Q)
|
98% |
1063
18.4 IPS |