Upload Date | September 19 2024 11:13 AM |
Views | 2 |
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% |
1717
319.3 IPS |
|
Image Classification (HP)
|
100% |
10885
2.02 KIPS |
|
Image Classification (Q)
|
97% |
15428
2.88 KIPS |
|
Image Segmentation (SP)
|
100% |
1595
25.9 IPS |
|
Image Segmentation (HP)
|
100% |
12952
210.0 IPS |
|
Image Segmentation (Q)
|
99% |
16027
259.8 IPS |
|
Pose Estimation (SP)
|
100% |
7790
9.09 IPS |
|
Pose Estimation (HP)
|
100% |
106004
123.7 IPS |
|
Pose Estimation (Q)
|
95% |
203580
238.6 IPS |
|
Object Detection (SP)
|
100% |
1780
141.2 IPS |
|
Object Detection (HP)
|
100% |
13603
1.08 KIPS |
|
Object Detection (Q)
|
91% |
19267
1.54 KIPS |
|
Face Detection (SP)
|
100% |
3172
37.7 IPS |
|
Face Detection (HP)
|
100% |
33614
399.4 IPS |
|
Face Detection (Q)
|
100% |
49563
588.9 IPS |
|
Depth Estimation (SP)
|
100% |
6943
53.5 IPS |
|
Depth Estimation (HP)
|
99% |
78855
607.5 IPS |
|
Depth Estimation (Q)
|
85% |
127373
995.9 IPS |
|
Style Transfer (SP)
|
100% |
20552
26.4 IPS |
|
Style Transfer (HP)
|
100% |
204947
263.5 IPS |
|
Style Transfer (Q)
|
96% |
245496
316.8 IPS |
|
Image Super-Resolution (SP)
|
100% |
4855
179.3 IPS |
|
Image Super-Resolution (HP)
|
100% |
33816
1.25 KIPS |
|
Image Super-Resolution (Q)
|
99% |
56167
2.07 KIPS |
|
Text Classification (SP)
|
100% |
3192
4.26 KIPS |
|
Text Classification (HP)
|
100% |
3075
4.10 KIPS |
|
Text Classification (Q)
|
93% |
3140
4.21 KIPS |
|
Machine Translation (SP)
|
100% |
3137
54.0 IPS |
|
Machine Translation (HP)
|
100% |
6225
107.2 IPS |
|
Machine Translation (Q)
|
98% |
7251
125.3 IPS |