Upload Date | January 06 2025 10:12 PM |
Views | 1 |
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% |
2024
376.4 IPS |
|
Image Classification (HP)
|
100% |
15166
2.82 KIPS |
|
Image Classification (Q)
|
97% |
20189
3.77 KIPS |
|
Image Segmentation (SP)
|
100% |
1924
31.2 IPS |
|
Image Segmentation (HP)
|
100% |
18338
297.3 IPS |
|
Image Segmentation (Q)
|
99% |
24015
389.3 IPS |
|
Pose Estimation (SP)
|
100% |
8664
10.1 IPS |
|
Pose Estimation (HP)
|
100% |
149429
174.4 IPS |
|
Pose Estimation (Q)
|
95% |
293915
344.5 IPS |
|
Object Detection (SP)
|
100% |
2144
170.1 IPS |
|
Object Detection (HP)
|
100% |
16231
1.29 KIPS |
|
Object Detection (Q)
|
91% |
22863
1.83 KIPS |
|
Face Detection (SP)
|
100% |
3623
43.0 IPS |
|
Face Detection (HP)
|
100% |
41238
490.0 IPS |
|
Face Detection (Q)
|
100% |
57099
678.5 IPS |
|
Depth Estimation (SP)
|
100% |
7691
59.3 IPS |
|
Depth Estimation (HP)
|
99% |
95274
734.0 IPS |
|
Depth Estimation (Q)
|
85% |
160161
1.25 KIPS |
|
Style Transfer (SP)
|
100% |
23816
30.6 IPS |
|
Style Transfer (HP)
|
100% |
244506
314.3 IPS |
|
Style Transfer (Q)
|
96% |
300647
388.0 IPS |
|
Image Super-Resolution (SP)
|
100% |
5570
205.7 IPS |
|
Image Super-Resolution (HP)
|
100% |
50318
1.86 KIPS |
|
Image Super-Resolution (Q)
|
99% |
84143
3.11 KIPS |
|
Text Classification (SP)
|
100% |
3425
4.57 KIPS |
|
Text Classification (HP)
|
100% |
4434
5.92 KIPS |
|
Text Classification (Q)
|
93% |
4674
6.27 KIPS |
|
Machine Translation (SP)
|
100% |
3634
62.6 IPS |
|
Machine Translation (HP)
|
100% |
9543
164.4 IPS |
|
Machine Translation (Q)
|
98% |
11487
198.5 IPS |