User | jwchess |
Upload Date | January 28 2025 02:35 PM |
Views | 3 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A18 Pro |
System Information | |
---|---|
Operating System | iOS 18.2.1 |
Model | iPhone 16 Pro |
Model ID | iPhone17,1 |
Motherboard | D93AP |
CPU Information | |
---|---|
Name | Apple A18 Pro |
Topology | 1 Processor, 6 Cores |
Identifier | ARM |
Base Frequency | 4.04 GHz |
Cluster 1 | 2 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 7.48 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1988
369.7 IPS |
|
Image Classification (HP)
|
100% |
15654
2.91 KIPS |
|
Image Classification (Q)
|
97% |
20766
3.88 KIPS |
|
Image Segmentation (SP)
|
100% |
1953
31.7 IPS |
|
Image Segmentation (HP)
|
100% |
18157
294.3 IPS |
|
Image Segmentation (Q)
|
99% |
23962
388.4 IPS |
|
Pose Estimation (SP)
|
100% |
8854
10.3 IPS |
|
Pose Estimation (HP)
|
100% |
153811
179.5 IPS |
|
Pose Estimation (Q)
|
95% |
293691
344.2 IPS |
|
Object Detection (SP)
|
100% |
2127
168.7 IPS |
|
Object Detection (HP)
|
100% |
16334
1.30 KIPS |
|
Object Detection (Q)
|
91% |
22636
1.81 KIPS |
|
Face Detection (SP)
|
100% |
3546
42.1 IPS |
|
Face Detection (HP)
|
100% |
41270
490.4 IPS |
|
Face Detection (Q)
|
100% |
58812
698.8 IPS |
|
Depth Estimation (SP)
|
100% |
7707
59.4 IPS |
|
Depth Estimation (HP)
|
99% |
95569
736.3 IPS |
|
Depth Estimation (Q)
|
85% |
160780
1.26 KIPS |
|
Style Transfer (SP)
|
100% |
24042
30.9 IPS |
|
Style Transfer (HP)
|
100% |
244583
314.4 IPS |
|
Style Transfer (Q)
|
96% |
300085
387.2 IPS |
|
Image Super-Resolution (SP)
|
100% |
5700
210.5 IPS |
|
Image Super-Resolution (HP)
|
100% |
50859
1.88 KIPS |
|
Image Super-Resolution (Q)
|
99% |
85458
3.16 KIPS |
|
Text Classification (SP)
|
100% |
3444
4.60 KIPS |
|
Text Classification (HP)
|
100% |
4540
6.06 KIPS |
|
Text Classification (Q)
|
93% |
4946
6.64 KIPS |
|
Machine Translation (SP)
|
100% |
3701
63.7 IPS |
|
Machine Translation (HP)
|
100% |
9388
161.7 IPS |
|
Machine Translation (Q)
|
98% |
11420
197.4 IPS |