User | Risto3 |
Upload Date | September 19 2024 01:24 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% |
1564
290.9 IPS |
|
Image Classification (HP)
|
100% |
11543
2.15 KIPS |
|
Image Classification (Q)
|
97% |
8788
1.64 KIPS |
|
Image Segmentation (SP)
|
100% |
282
4.58 IPS |
|
Image Segmentation (HP)
|
100% |
6715
108.9 IPS |
|
Image Segmentation (Q)
|
99% |
7968
129.2 IPS |
|
Pose Estimation (SP)
|
100% |
1535
1.79 IPS |
|
Pose Estimation (HP)
|
100% |
63152
73.7 IPS |
|
Pose Estimation (Q)
|
95% |
93715
109.8 IPS |
|
Object Detection (SP)
|
100% |
853
67.7 IPS |
|
Object Detection (HP)
|
100% |
10428
827.1 IPS |
|
Object Detection (Q)
|
91% |
9457
755.7 IPS |
|
Face Detection (SP)
|
100% |
1813
21.5 IPS |
|
Face Detection (HP)
|
100% |
23326
277.2 IPS |
|
Face Detection (Q)
|
100% |
30769
365.6 IPS |
|
Depth Estimation (SP)
|
100% |
4821
37.1 IPS |
|
Depth Estimation (HP)
|
99% |
60035
462.5 IPS |
|
Depth Estimation (Q)
|
85% |
70472
551.0 IPS |
|
Style Transfer (SP)
|
100% |
9416
12.1 IPS |
|
Style Transfer (HP)
|
100% |
153143
196.9 IPS |
|
Style Transfer (Q)
|
96% |
174001
224.5 IPS |
|
Image Super-Resolution (SP)
|
100% |
4291
158.4 IPS |
|
Image Super-Resolution (HP)
|
100% |
27485
1.01 KIPS |
|
Image Super-Resolution (Q)
|
99% |
47444
1.75 KIPS |
|
Text Classification (SP)
|
100% |
2653
3.54 KIPS |
|
Text Classification (HP)
|
100% |
2843
3.79 KIPS |
|
Text Classification (Q)
|
93% |
3095
4.15 KIPS |
|
Machine Translation (SP)
|
100% |
2676
46.1 IPS |
|
Machine Translation (HP)
|
100% |
5821
100.3 IPS |
|
Machine Translation (Q)
|
98% |
5516
95.3 IPS |