Upload Date | September 18 2024 12:44 PM |
Views | 1 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A17 Pro |
System Information | |
---|---|
Operating System | iOS 18.0 |
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% |
1712
318.3 IPS |
|
Image Classification (HP)
|
100% |
10663
1.98 KIPS |
|
Image Classification (Q)
|
99% |
13373
2.49 KIPS |
|
Image Segmentation (SP)
|
100% |
1616
26.2 IPS |
|
Image Segmentation (HP)
|
100% |
10738
174.1 IPS |
|
Image Segmentation (Q)
|
100% |
10764
174.5 IPS |
|
Pose Estimation (SP)
|
100% |
8561
9.99 IPS |
|
Pose Estimation (HP)
|
100% |
102549
119.7 IPS |
|
Pose Estimation (Q)
|
94% |
197969
232.2 IPS |
|
Object Detection (SP)
|
100% |
1828
145.0 IPS |
|
Object Detection (HP)
|
100% |
13084
1.04 KIPS |
|
Object Detection (Q)
|
91% |
18867
1.51 KIPS |
|
Face Detection (SP)
|
100% |
3201
38.0 IPS |
|
Face Detection (HP)
|
100% |
21851
259.6 IPS |
|
Face Detection (Q)
|
100% |
37154
441.5 IPS |
|
Depth Estimation (SP)
|
100% |
7257
55.9 IPS |
|
Depth Estimation (HP)
|
99% |
64288
495.3 IPS |
|
Depth Estimation (Q)
|
97% |
74090
572.9 IPS |
|
Style Transfer (SP)
|
100% |
21745
28.0 IPS |
|
Style Transfer (HP)
|
100% |
138385
177.9 IPS |
|
Style Transfer (Q)
|
100% |
139282
179.0 IPS |
|
Image Super-Resolution (SP)
|
100% |
5107
188.6 IPS |
|
Image Super-Resolution (HP)
|
100% |
34934
1.29 KIPS |
|
Image Super-Resolution (Q)
|
98% |
55074
2.04 KIPS |
|
Text Classification (SP)
|
100% |
3200
4.27 KIPS |
|
Text Classification (HP)
|
100% |
2692
3.59 KIPS |
|
Text Classification (Q)
|
93% |
2350
3.15 KIPS |
|
Machine Translation (SP)
|
100% |
3111
53.6 IPS |
|
Machine Translation (HP)
|
100% |
6207
106.9 IPS |
|
Machine Translation (Q)
|
98% |
7371
127.4 IPS |