| Upload Date | January 23 2025 03:53 PM |
| Views | 54 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | Neural Engine |
| Device | Apple A18 Pro |
| System Information | |
|---|---|
| Operating System | iOS 18.2.1 |
| Model | iPhone 16 Pro Max |
| Model ID | iPhone17,2 |
| Motherboard | D94AP |
| 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 | 7.45 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
2024
376.4 IPS |
|
|
Image Classification (HP)
|
100% |
15304
2.85 KIPS |
|
|
Image Classification (Q)
|
97% |
19462
3.63 KIPS |
|
|
Image Segmentation (SP)
|
100% |
1940
31.5 IPS |
|
|
Image Segmentation (HP)
|
100% |
18129
293.9 IPS |
|
|
Image Segmentation (Q)
|
99% |
24125
391.1 IPS |
|
|
Pose Estimation (SP)
|
100% |
8554
9.98 IPS |
|
|
Pose Estimation (HP)
|
100% |
152426
177.9 IPS |
|
|
Pose Estimation (Q)
|
95% |
292525
342.9 IPS |
|
|
Object Detection (SP)
|
100% |
2143
170.0 IPS |
|
|
Object Detection (HP)
|
100% |
16189
1.28 KIPS |
|
|
Object Detection (Q)
|
91% |
22437
1.79 KIPS |
|
|
Face Detection (SP)
|
100% |
3542
42.1 IPS |
|
|
Face Detection (HP)
|
100% |
41229
489.9 IPS |
|
|
Face Detection (Q)
|
100% |
58313
692.9 IPS |
|
|
Depth Estimation (SP)
|
100% |
7747
59.7 IPS |
|
|
Depth Estimation (HP)
|
99% |
94904
731.2 IPS |
|
|
Depth Estimation (Q)
|
85% |
159603
1.25 KIPS |
|
|
Style Transfer (SP)
|
100% |
23563
30.3 IPS |
|
|
Style Transfer (HP)
|
100% |
244830
314.7 IPS |
|
|
Style Transfer (Q)
|
96% |
301094
388.5 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
5211
192.4 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
50288
1.86 KIPS |
|
|
Image Super-Resolution (Q)
|
99% |
83814
3.09 KIPS |
|
|
Text Classification (SP)
|
100% |
3415
4.56 KIPS |
|
|
Text Classification (HP)
|
100% |
4582
6.12 KIPS |
|
|
Text Classification (Q)
|
93% |
4739
6.36 KIPS |
|
|
Machine Translation (SP)
|
100% |
3746
64.5 IPS |
|
|
Machine Translation (HP)
|
100% |
9451
162.8 IPS |
|
|
Machine Translation (Q)
|
98% |
11266
194.7 IPS |