Upload Date | September 17 2024 10:59 PM |
Views | 2 |
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% |
1704
316.8 IPS |
|
Image Classification (HP)
|
100% |
11147
2.07 KIPS |
|
Image Classification (Q)
|
97% |
14968
2.79 KIPS |
|
Image Segmentation (SP)
|
100% |
1614
26.2 IPS |
|
Image Segmentation (HP)
|
100% |
12909
209.3 IPS |
|
Image Segmentation (Q)
|
99% |
16027
259.8 IPS |
|
Pose Estimation (SP)
|
100% |
7877
9.19 IPS |
|
Pose Estimation (HP)
|
100% |
105984
123.7 IPS |
|
Pose Estimation (Q)
|
95% |
204343
239.5 IPS |
|
Object Detection (SP)
|
100% |
1801
142.8 IPS |
|
Object Detection (HP)
|
100% |
13868
1.10 KIPS |
|
Object Detection (Q)
|
91% |
19046
1.52 KIPS |
|
Face Detection (SP)
|
100% |
3189
37.9 IPS |
|
Face Detection (HP)
|
100% |
34599
411.1 IPS |
|
Face Detection (Q)
|
100% |
48991
582.1 IPS |
|
Depth Estimation (SP)
|
100% |
7130
54.9 IPS |
|
Depth Estimation (HP)
|
99% |
78415
604.1 IPS |
|
Depth Estimation (Q)
|
85% |
129021
1.01 KIPS |
|
Style Transfer (SP)
|
100% |
21004
27.0 IPS |
|
Style Transfer (HP)
|
100% |
202541
260.4 IPS |
|
Style Transfer (Q)
|
96% |
246884
318.6 IPS |
|
Image Super-Resolution (SP)
|
100% |
4957
183.0 IPS |
|
Image Super-Resolution (HP)
|
100% |
34077
1.26 KIPS |
|
Image Super-Resolution (Q)
|
99% |
56660
2.09 KIPS |
|
Text Classification (SP)
|
100% |
3190
4.26 KIPS |
|
Text Classification (HP)
|
100% |
3111
4.15 KIPS |
|
Text Classification (Q)
|
93% |
2391
3.21 KIPS |
|
Machine Translation (SP)
|
100% |
3243
55.9 IPS |
|
Machine Translation (HP)
|
100% |
6141
105.8 IPS |
|
Machine Translation (Q)
|
98% |
7198
124.4 IPS |