User | pakitt |
Upload Date | September 19 2024 06:10 AM |
Views | 5 |
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% |
1628
302.8 IPS |
|
Image Classification (HP)
|
100% |
10542
1.96 KIPS |
|
Image Classification (Q)
|
97% |
15450
2.88 KIPS |
|
Image Segmentation (SP)
|
100% |
1580
25.6 IPS |
|
Image Segmentation (HP)
|
100% |
12881
208.8 IPS |
|
Image Segmentation (Q)
|
99% |
16003
259.4 IPS |
|
Pose Estimation (SP)
|
100% |
7052
8.23 IPS |
|
Pose Estimation (HP)
|
100% |
100819
117.6 IPS |
|
Pose Estimation (Q)
|
95% |
202958
237.9 IPS |
|
Object Detection (SP)
|
100% |
1721
136.5 IPS |
|
Object Detection (HP)
|
100% |
13513
1.07 KIPS |
|
Object Detection (Q)
|
91% |
19056
1.52 KIPS |
|
Face Detection (SP)
|
100% |
3108
36.9 IPS |
|
Face Detection (HP)
|
100% |
33477
397.8 IPS |
|
Face Detection (Q)
|
100% |
49085
583.2 IPS |
|
Depth Estimation (SP)
|
100% |
6804
52.4 IPS |
|
Depth Estimation (HP)
|
99% |
78556
605.2 IPS |
|
Depth Estimation (Q)
|
85% |
127073
993.5 IPS |
|
Style Transfer (SP)
|
100% |
19730
25.4 IPS |
|
Style Transfer (HP)
|
100% |
201476
259.0 IPS |
|
Style Transfer (Q)
|
96% |
245280
316.5 IPS |
|
Image Super-Resolution (SP)
|
100% |
4602
169.9 IPS |
|
Image Super-Resolution (HP)
|
100% |
33972
1.25 KIPS |
|
Image Super-Resolution (Q)
|
99% |
54985
2.03 KIPS |
|
Text Classification (SP)
|
100% |
3193
4.26 KIPS |
|
Text Classification (HP)
|
100% |
3092
4.13 KIPS |
|
Text Classification (Q)
|
93% |
3109
4.17 KIPS |
|
Machine Translation (SP)
|
100% |
3110
53.6 IPS |
|
Machine Translation (HP)
|
100% |
6812
117.3 IPS |
|
Machine Translation (Q)
|
98% |
7340
126.8 IPS |