| User | mcx |
| Upload Date | August 15 2024 06:50 PM |
| Views | 13 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | Neural Engine |
| Device | Apple A17 Pro |
| System Information | |
|---|---|
| Operating System | iOS 17.6.1 |
| Model | iPhone 15 Pro Max |
| Model ID | iPhone16,2 |
| Motherboard | D84AP |
| CPU Information | |
|---|---|
| Name | Apple A17 Pro |
| Topology | 1 Processor, 6 Cores |
| Identifier | ARM |
| Base Frequency | 3.78 GHz |
| Cluster 1 | 2 Cores |
| Cluster 2 | 4 Cores |
| Memory Information | |
|---|---|
| Size | 7.44 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
1457
271.0 IPS |
|
|
Image Classification (HP)
|
100% |
6285
1.17 KIPS |
|
|
Image Classification (Q)
|
99% |
7439
1.39 KIPS |
|
|
Image Segmentation (SP)
|
100% |
819
13.3 IPS |
|
|
Image Segmentation (HP)
|
100% |
5227
84.7 IPS |
|
|
Image Segmentation (Q)
|
100% |
5478
88.8 IPS |
|
|
Pose Estimation (SP)
|
100% |
7811
9.11 IPS |
|
|
Pose Estimation (HP)
|
100% |
88176
102.9 IPS |
|
|
Pose Estimation (Q)
|
94% |
140328
164.6 IPS |
|
|
Object Detection (SP)
|
100% |
1241
98.4 IPS |
|
|
Object Detection (HP)
|
100% |
7984
633.3 IPS |
|
|
Object Detection (Q)
|
93% |
9070
723.7 IPS |
|
|
Face Detection (SP)
|
100% |
1928
22.9 IPS |
|
|
Face Detection (HP)
|
100% |
10824
128.6 IPS |
|
|
Face Detection (Q)
|
100% |
14266
169.5 IPS |
|
|
Depth Estimation (SP)
|
100% |
3919
30.2 IPS |
|
|
Depth Estimation (HP)
|
99% |
42950
330.9 IPS |
|
|
Depth Estimation (Q)
|
97% |
47949
370.8 IPS |
|
|
Style Transfer (SP)
|
100% |
12059
15.5 IPS |
|
|
Style Transfer (HP)
|
100% |
128809
165.6 IPS |
|
|
Style Transfer (Q)
|
100% |
126117
162.1 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
3639
134.4 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
18835
695.5 IPS |
|
|
Image Super-Resolution (Q)
|
98% |
28011
1.04 KIPS |
|
|
Text Classification (SP)
|
100% |
1531
2.04 KIPS |
|
|
Text Classification (HP)
|
71% |
5037
7.24 KIPS |
|
|
Text Classification (Q)
|
69% |
4556
6.68 KIPS |
|
|
Machine Translation (SP)
|
100% |
1880
32.4 IPS |
|
|
Machine Translation (HP)
|
100% |
2452
42.2 IPS |
|
|
Machine Translation (Q)
|
98% |
2442
42.2 IPS |