User | ju83 |
Upload Date | January 12 2025 12:05 PM |
Views | 2 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A18 Pro |
System Information | |
---|---|
Operating System | iOS 18.2 |
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% |
2016
375.0 IPS |
|
Image Classification (HP)
|
100% |
15440
2.87 KIPS |
|
Image Classification (Q)
|
97% |
20248
3.78 KIPS |
|
Image Segmentation (SP)
|
100% |
1964
31.8 IPS |
|
Image Segmentation (HP)
|
100% |
18361
297.6 IPS |
|
Image Segmentation (Q)
|
99% |
24202
392.3 IPS |
|
Pose Estimation (SP)
|
100% |
9057
10.6 IPS |
|
Pose Estimation (HP)
|
100% |
152731
178.2 IPS |
|
Pose Estimation (Q)
|
95% |
294076
344.7 IPS |
|
Object Detection (SP)
|
100% |
2149
170.5 IPS |
|
Object Detection (HP)
|
100% |
16455
1.31 KIPS |
|
Object Detection (Q)
|
91% |
22561
1.80 KIPS |
|
Face Detection (SP)
|
100% |
3619
43.0 IPS |
|
Face Detection (HP)
|
100% |
41212
489.7 IPS |
|
Face Detection (Q)
|
100% |
58647
696.8 IPS |
|
Depth Estimation (SP)
|
100% |
7909
60.9 IPS |
|
Depth Estimation (HP)
|
99% |
96065
740.1 IPS |
|
Depth Estimation (Q)
|
85% |
161885
1.27 KIPS |
|
Style Transfer (SP)
|
100% |
24489
31.5 IPS |
|
Style Transfer (HP)
|
100% |
244235
314.0 IPS |
|
Style Transfer (Q)
|
96% |
303044
391.1 IPS |
|
Image Super-Resolution (SP)
|
100% |
5679
209.7 IPS |
|
Image Super-Resolution (HP)
|
100% |
50922
1.88 KIPS |
|
Image Super-Resolution (Q)
|
99% |
86702
3.20 KIPS |
|
Text Classification (SP)
|
100% |
3450
4.60 KIPS |
|
Text Classification (HP)
|
100% |
4392
5.86 KIPS |
|
Text Classification (Q)
|
93% |
4336
5.82 KIPS |
|
Machine Translation (SP)
|
100% |
3818
65.8 IPS |
|
Machine Translation (HP)
|
100% |
9552
164.5 IPS |
|
Machine Translation (Q)
|
98% |
11511
198.9 IPS |