User | virtuatony95 |
Upload Date | August 16 2024 01:19 PM |
Views | 9 |
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% |
1413
262.7 IPS |
|
Image Classification (HP)
|
100% |
6102
1.13 KIPS |
|
Image Classification (Q)
|
99% |
7393
1.38 KIPS |
|
Image Segmentation (SP)
|
100% |
826
13.4 IPS |
|
Image Segmentation (HP)
|
100% |
5200
84.3 IPS |
|
Image Segmentation (Q)
|
100% |
5211
84.5 IPS |
|
Pose Estimation (SP)
|
100% |
8100
9.45 IPS |
|
Pose Estimation (HP)
|
100% |
89240
104.1 IPS |
|
Pose Estimation (Q)
|
94% |
141733
166.2 IPS |
|
Object Detection (SP)
|
100% |
1477
117.2 IPS |
|
Object Detection (HP)
|
100% |
8200
650.4 IPS |
|
Object Detection (Q)
|
93% |
10009
798.6 IPS |
|
Face Detection (SP)
|
100% |
2292
27.2 IPS |
|
Face Detection (HP)
|
100% |
11234
133.5 IPS |
|
Face Detection (Q)
|
100% |
13353
158.7 IPS |
|
Depth Estimation (SP)
|
100% |
4737
36.5 IPS |
|
Depth Estimation (HP)
|
99% |
42639
328.5 IPS |
|
Depth Estimation (Q)
|
97% |
47769
369.4 IPS |
|
Style Transfer (SP)
|
100% |
12376
15.9 IPS |
|
Style Transfer (HP)
|
100% |
128057
164.6 IPS |
|
Style Transfer (Q)
|
100% |
128585
165.3 IPS |
|
Image Super-Resolution (SP)
|
100% |
4144
153.0 IPS |
|
Image Super-Resolution (HP)
|
100% |
18619
687.5 IPS |
|
Image Super-Resolution (Q)
|
98% |
25923
960.4 IPS |
|
Text Classification (SP)
|
100% |
1830
2.44 KIPS |
|
Text Classification (HP)
|
71% |
3933
5.66 KIPS |
|
Text Classification (Q)
|
69% |
3885
5.70 KIPS |
|
Machine Translation (SP)
|
100% |
1934
33.3 IPS |
|
Machine Translation (HP)
|
100% |
2453
42.2 IPS |
|
Machine Translation (Q)
|
98% |
2430
42.0 IPS |