Upload Date | September 18 2024 12:43 AM |
Views | 1 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A17 Pro |
System Information | |
---|---|
Operating System | iOS 18.1 |
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 | 7.48 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1708
317.6 IPS |
|
Image Classification (HP)
|
100% |
10677
1.99 KIPS |
|
Image Classification (Q)
|
97% |
15424
2.88 KIPS |
|
Image Segmentation (SP)
|
100% |
1605
26.0 IPS |
|
Image Segmentation (HP)
|
100% |
12900
209.1 IPS |
|
Image Segmentation (Q)
|
99% |
15997
259.3 IPS |
|
Pose Estimation (SP)
|
100% |
7794
9.09 IPS |
|
Pose Estimation (HP)
|
100% |
107687
125.7 IPS |
|
Pose Estimation (Q)
|
95% |
205284
240.6 IPS |
|
Object Detection (SP)
|
100% |
1790
142.0 IPS |
|
Object Detection (HP)
|
100% |
13692
1.09 KIPS |
|
Object Detection (Q)
|
91% |
19244
1.54 KIPS |
|
Face Detection (SP)
|
100% |
3151
37.4 IPS |
|
Face Detection (HP)
|
100% |
33487
397.9 IPS |
|
Face Detection (Q)
|
100% |
49033
582.6 IPS |
|
Depth Estimation (SP)
|
100% |
7048
54.3 IPS |
|
Depth Estimation (HP)
|
99% |
78510
604.9 IPS |
|
Depth Estimation (Q)
|
85% |
127430
996.3 IPS |
|
Style Transfer (SP)
|
100% |
20882
26.8 IPS |
|
Style Transfer (HP)
|
100% |
201597
259.2 IPS |
|
Style Transfer (Q)
|
96% |
246704
318.4 IPS |
|
Image Super-Resolution (SP)
|
100% |
4912
181.4 IPS |
|
Image Super-Resolution (HP)
|
100% |
34334
1.27 KIPS |
|
Image Super-Resolution (Q)
|
99% |
57056
2.11 KIPS |
|
Text Classification (SP)
|
100% |
3204
4.28 KIPS |
|
Text Classification (HP)
|
100% |
3229
4.31 KIPS |
|
Text Classification (Q)
|
93% |
2309
3.10 KIPS |
|
Machine Translation (SP)
|
100% |
3114
53.6 IPS |
|
Machine Translation (HP)
|
100% |
6030
103.9 IPS |
|
Machine Translation (Q)
|
98% |
7282
125.8 IPS |