Upload Date | September 13 2024 09:00 PM |
Views | 21 |
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% |
1691
314.6 IPS |
|
Image Classification (HP)
|
100% |
10866
2.02 KIPS |
|
Image Classification (Q)
|
97% |
15199
2.84 KIPS |
|
Image Segmentation (SP)
|
100% |
1595
25.9 IPS |
|
Image Segmentation (HP)
|
100% |
12962
210.1 IPS |
|
Image Segmentation (Q)
|
99% |
16030
259.9 IPS |
|
Pose Estimation (SP)
|
100% |
7622
8.89 IPS |
|
Pose Estimation (HP)
|
100% |
103505
120.8 IPS |
|
Pose Estimation (Q)
|
95% |
204464
239.6 IPS |
|
Object Detection (SP)
|
100% |
1762
139.8 IPS |
|
Object Detection (HP)
|
100% |
13789
1.09 KIPS |
|
Object Detection (Q)
|
91% |
19228
1.54 KIPS |
|
Face Detection (SP)
|
100% |
3146
37.4 IPS |
|
Face Detection (HP)
|
100% |
33378
396.6 IPS |
|
Face Detection (Q)
|
100% |
49114
583.6 IPS |
|
Depth Estimation (SP)
|
100% |
6957
53.6 IPS |
|
Depth Estimation (HP)
|
99% |
78631
605.8 IPS |
|
Depth Estimation (Q)
|
85% |
128905
1.01 KIPS |
|
Style Transfer (SP)
|
100% |
20539
26.4 IPS |
|
Style Transfer (HP)
|
100% |
201561
259.1 IPS |
|
Style Transfer (Q)
|
96% |
245037
316.2 IPS |
|
Image Super-Resolution (SP)
|
100% |
4822
178.0 IPS |
|
Image Super-Resolution (HP)
|
100% |
33621
1.24 KIPS |
|
Image Super-Resolution (Q)
|
99% |
55005
2.03 KIPS |
|
Text Classification (SP)
|
100% |
3186
4.25 KIPS |
|
Text Classification (HP)
|
100% |
3030
4.04 KIPS |
|
Text Classification (Q)
|
93% |
2980
4.00 KIPS |
|
Machine Translation (SP)
|
100% |
3215
55.4 IPS |
|
Machine Translation (HP)
|
100% |
6041
104.1 IPS |
|
Machine Translation (Q)
|
98% |
7330
126.7 IPS |