User | adhame95 |
Upload Date | August 15 2024 11:31 PM |
Views | 4 |
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% |
1262
234.7 IPS |
|
Image Classification (HP)
|
100% |
6208
1.15 KIPS |
|
Image Classification (Q)
|
99% |
6852
1.28 KIPS |
|
Image Segmentation (SP)
|
100% |
782
12.7 IPS |
|
Image Segmentation (HP)
|
100% |
5198
84.3 IPS |
|
Image Segmentation (Q)
|
100% |
5185
84.1 IPS |
|
Pose Estimation (SP)
|
100% |
7316
8.54 IPS |
|
Pose Estimation (HP)
|
100% |
87424
102.0 IPS |
|
Pose Estimation (Q)
|
94% |
133416
156.5 IPS |
|
Object Detection (SP)
|
100% |
1469
116.5 IPS |
|
Object Detection (HP)
|
100% |
8197
650.2 IPS |
|
Object Detection (Q)
|
93% |
9036
721.0 IPS |
|
Face Detection (SP)
|
100% |
2149
25.5 IPS |
|
Face Detection (HP)
|
100% |
11192
133.0 IPS |
|
Face Detection (Q)
|
100% |
13487
160.3 IPS |
|
Depth Estimation (SP)
|
100% |
4679
36.1 IPS |
|
Depth Estimation (HP)
|
99% |
42264
325.6 IPS |
|
Depth Estimation (Q)
|
97% |
48003
371.2 IPS |
|
Style Transfer (SP)
|
100% |
12000
15.4 IPS |
|
Style Transfer (HP)
|
100% |
128245
164.9 IPS |
|
Style Transfer (Q)
|
100% |
128332
165.0 IPS |
|
Image Super-Resolution (SP)
|
100% |
3864
142.7 IPS |
|
Image Super-Resolution (HP)
|
100% |
18418
680.1 IPS |
|
Image Super-Resolution (Q)
|
98% |
26494
981.6 IPS |
|
Text Classification (SP)
|
100% |
1691
2.26 KIPS |
|
Text Classification (HP)
|
71% |
4189
6.02 KIPS |
|
Text Classification (Q)
|
69% |
4158
6.10 KIPS |
|
Machine Translation (SP)
|
100% |
1834
31.6 IPS |
|
Machine Translation (HP)
|
100% |
2497
43.0 IPS |
|
Machine Translation (Q)
|
98% |
2378
41.1 IPS |