Upload Date | September 18 2024 09:23 AM |
Views | 1 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A17 Pro |
System Information | |
---|---|
Operating System | iOS 18.0 |
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 | 7.48 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1661
308.9 IPS |
|
Image Classification (HP)
|
100% |
11425
2.12 KIPS |
|
Image Classification (Q)
|
97% |
15225
2.84 KIPS |
|
Image Segmentation (SP)
|
100% |
1537
24.9 IPS |
|
Image Segmentation (HP)
|
100% |
12850
208.3 IPS |
|
Image Segmentation (Q)
|
99% |
16002
259.4 IPS |
|
Pose Estimation (SP)
|
100% |
7521
8.78 IPS |
|
Pose Estimation (HP)
|
100% |
103758
121.1 IPS |
|
Pose Estimation (Q)
|
95% |
202774
237.7 IPS |
|
Object Detection (SP)
|
100% |
1746
138.5 IPS |
|
Object Detection (HP)
|
100% |
13661
1.08 KIPS |
|
Object Detection (Q)
|
91% |
19105
1.53 KIPS |
|
Face Detection (SP)
|
100% |
3071
36.5 IPS |
|
Face Detection (HP)
|
100% |
34261
407.1 IPS |
|
Face Detection (Q)
|
100% |
48910
581.2 IPS |
|
Depth Estimation (SP)
|
100% |
6684
51.5 IPS |
|
Depth Estimation (HP)
|
99% |
78467
604.5 IPS |
|
Depth Estimation (Q)
|
85% |
127980
1.00 KIPS |
|
Style Transfer (SP)
|
100% |
19687
25.3 IPS |
|
Style Transfer (HP)
|
100% |
204453
262.8 IPS |
|
Style Transfer (Q)
|
96% |
245639
317.0 IPS |
|
Image Super-Resolution (SP)
|
100% |
4656
171.9 IPS |
|
Image Super-Resolution (HP)
|
100% |
33922
1.25 KIPS |
|
Image Super-Resolution (Q)
|
99% |
55414
2.05 KIPS |
|
Text Classification (SP)
|
100% |
3188
4.25 KIPS |
|
Text Classification (HP)
|
100% |
3144
4.20 KIPS |
|
Text Classification (Q)
|
93% |
3157
4.24 KIPS |
|
Machine Translation (SP)
|
100% |
3076
53.0 IPS |
|
Machine Translation (HP)
|
100% |
6132
105.6 IPS |
|
Machine Translation (Q)
|
98% |
7389
127.7 IPS |