Upload Date | October 13 2024 11:19 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% |
1577
293.2 IPS |
|
Image Classification (HP)
|
100% |
11346
2.11 KIPS |
|
Image Classification (Q)
|
97% |
15522
2.90 KIPS |
|
Image Segmentation (SP)
|
100% |
1564
25.4 IPS |
|
Image Segmentation (HP)
|
100% |
15742
255.2 IPS |
|
Image Segmentation (Q)
|
99% |
20872
338.4 IPS |
|
Pose Estimation (SP)
|
100% |
7141
8.33 IPS |
|
Pose Estimation (HP)
|
100% |
101334
118.2 IPS |
|
Pose Estimation (Q)
|
95% |
203002
237.9 IPS |
|
Object Detection (SP)
|
100% |
1723
136.7 IPS |
|
Object Detection (HP)
|
100% |
13845
1.10 KIPS |
|
Object Detection (Q)
|
91% |
19188
1.53 KIPS |
|
Face Detection (SP)
|
100% |
3091
36.7 IPS |
|
Face Detection (HP)
|
100% |
34404
408.8 IPS |
|
Face Detection (Q)
|
100% |
51508
612.0 IPS |
|
Depth Estimation (SP)
|
100% |
6676
51.4 IPS |
|
Depth Estimation (HP)
|
99% |
78523
605.0 IPS |
|
Depth Estimation (Q)
|
85% |
127457
996.5 IPS |
|
Style Transfer (SP)
|
100% |
19748
25.4 IPS |
|
Style Transfer (HP)
|
100% |
203183
261.2 IPS |
|
Style Transfer (Q)
|
96% |
249923
322.5 IPS |
|
Image Super-Resolution (SP)
|
100% |
4648
171.6 IPS |
|
Image Super-Resolution (HP)
|
100% |
34132
1.26 KIPS |
|
Image Super-Resolution (Q)
|
99% |
58135
2.15 KIPS |
|
Text Classification (SP)
|
100% |
3179
4.24 KIPS |
|
Text Classification (HP)
|
100% |
3122
4.17 KIPS |
|
Text Classification (Q)
|
93% |
3349
4.49 KIPS |
|
Machine Translation (SP)
|
100% |
3105
53.5 IPS |
|
Machine Translation (HP)
|
100% |
6441
110.9 IPS |
|
Machine Translation (Q)
|
98% |
7385
127.6 IPS |