User | funskeen |
Upload Date | December 08 2024 07:46 PM |
Views | 8 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A17 Pro |
System Information | |
---|---|
Operating System | iOS 18.1.1 |
Model | iPhone 15 Pro |
Model ID | iPhone16,1 |
Motherboard | D83AP |
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 | 7.51 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1736
322.8 IPS |
|
Image Classification (HP)
|
100% |
10901
2.03 KIPS |
|
Image Classification (Q)
|
97% |
14856
2.77 KIPS |
|
Image Segmentation (SP)
|
100% |
1636
26.5 IPS |
|
Image Segmentation (HP)
|
100% |
16002
259.4 IPS |
|
Image Segmentation (Q)
|
99% |
20926
339.2 IPS |
|
Pose Estimation (SP)
|
100% |
8141
9.50 IPS |
|
Pose Estimation (HP)
|
100% |
106600
124.4 IPS |
|
Pose Estimation (Q)
|
95% |
203394
238.4 IPS |
|
Object Detection (SP)
|
100% |
1827
144.9 IPS |
|
Object Detection (HP)
|
100% |
13609
1.08 KIPS |
|
Object Detection (Q)
|
91% |
19045
1.52 KIPS |
|
Face Detection (SP)
|
100% |
3277
38.9 IPS |
|
Face Detection (HP)
|
100% |
34847
414.1 IPS |
|
Face Detection (Q)
|
100% |
50881
604.6 IPS |
|
Depth Estimation (SP)
|
100% |
7174
55.3 IPS |
|
Depth Estimation (HP)
|
99% |
78892
607.8 IPS |
|
Depth Estimation (Q)
|
85% |
128026
1.00 KIPS |
|
Style Transfer (SP)
|
100% |
21372
27.5 IPS |
|
Style Transfer (HP)
|
100% |
202952
260.9 IPS |
|
Style Transfer (Q)
|
96% |
247206
319.0 IPS |
|
Image Super-Resolution (SP)
|
100% |
5026
185.6 IPS |
|
Image Super-Resolution (HP)
|
100% |
34653
1.28 KIPS |
|
Image Super-Resolution (Q)
|
99% |
58993
2.18 KIPS |
|
Text Classification (SP)
|
100% |
3249
4.34 KIPS |
|
Text Classification (HP)
|
100% |
3217
4.29 KIPS |
|
Text Classification (Q)
|
93% |
3092
4.15 KIPS |
|
Machine Translation (SP)
|
100% |
3145
54.2 IPS |
|
Machine Translation (HP)
|
100% |
6249
107.6 IPS |
|
Machine Translation (Q)
|
98% |
7301
126.2 IPS |