Upload Date | September 17 2024 06:40 PM |
Views | 1 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A16 Bionic |
System Information | |
---|---|
Operating System | iOS 18.0 |
Model | iPhone 14 Pro |
Model ID | iPhone15,2 |
Motherboard | D73AP |
CPU Information | |
---|---|
Name | Apple A16 Bionic |
Topology | 1 Processor, 6 Cores |
Identifier | ARM |
Base Frequency | 3.46 GHz |
Cluster 1 | 2 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 5.53 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1445
268.7 IPS |
|
Image Classification (HP)
|
100% |
10300
1.92 KIPS |
|
Image Classification (Q)
|
97% |
12109
2.26 KIPS |
|
Image Segmentation (SP)
|
100% |
1446
23.4 IPS |
|
Image Segmentation (HP)
|
100% |
11425
185.2 IPS |
|
Image Segmentation (Q)
|
99% |
13260
215.0 IPS |
|
Pose Estimation (SP)
|
100% |
7126
8.31 IPS |
|
Pose Estimation (HP)
|
100% |
97844
114.2 IPS |
|
Pose Estimation (Q)
|
95% |
102001
119.6 IPS |
|
Object Detection (SP)
|
100% |
1576
125.0 IPS |
|
Object Detection (HP)
|
100% |
12995
1.03 KIPS |
|
Object Detection (Q)
|
91% |
14943
1.19 KIPS |
|
Face Detection (SP)
|
100% |
3073
36.5 IPS |
|
Face Detection (HP)
|
100% |
30380
361.0 IPS |
|
Face Detection (Q)
|
100% |
39153
465.2 IPS |
|
Depth Estimation (SP)
|
100% |
6278
48.4 IPS |
|
Depth Estimation (HP)
|
99% |
74395
573.2 IPS |
|
Depth Estimation (Q)
|
85% |
95636
747.7 IPS |
|
Style Transfer (SP)
|
100% |
18997
24.4 IPS |
|
Style Transfer (HP)
|
100% |
171046
219.9 IPS |
|
Style Transfer (Q)
|
96% |
171508
221.3 IPS |
|
Image Super-Resolution (SP)
|
100% |
4211
155.5 IPS |
|
Image Super-Resolution (HP)
|
100% |
32389
1.20 KIPS |
|
Image Super-Resolution (Q)
|
99% |
37907
1.40 KIPS |
|
Text Classification (SP)
|
100% |
2610
3.48 KIPS |
|
Text Classification (HP)
|
100% |
2663
3.55 KIPS |
|
Text Classification (Q)
|
93% |
2714
3.64 KIPS |
|
Machine Translation (SP)
|
100% |
3410
58.7 IPS |
|
Machine Translation (HP)
|
100% |
2391
41.2 IPS |
|
Machine Translation (Q)
|
98% |
2379
41.1 IPS |