User | Deferare |
Upload Date | August 16 2024 12:32 AM |
Views | 4 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A17 Pro |
System Information | |
---|---|
Operating System | iOS 18.1 |
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% |
1720
319.8 IPS |
|
Image Classification (HP)
|
100% |
10506
1.95 KIPS |
|
Image Classification (Q)
|
99% |
13147
2.45 KIPS |
|
Image Segmentation (SP)
|
100% |
1641
26.6 IPS |
|
Image Segmentation (HP)
|
100% |
10888
176.5 IPS |
|
Image Segmentation (Q)
|
100% |
10788
174.9 IPS |
|
Pose Estimation (SP)
|
100% |
8651
10.1 IPS |
|
Pose Estimation (HP)
|
100% |
103847
121.2 IPS |
|
Pose Estimation (Q)
|
94% |
198761
233.1 IPS |
|
Object Detection (SP)
|
100% |
1829
145.1 IPS |
|
Object Detection (HP)
|
100% |
12830
1.02 KIPS |
|
Object Detection (Q)
|
91% |
18101
1.45 KIPS |
|
Face Detection (SP)
|
100% |
3263
38.8 IPS |
|
Face Detection (HP)
|
100% |
21835
259.4 IPS |
|
Face Detection (Q)
|
100% |
36957
439.1 IPS |
|
Depth Estimation (SP)
|
100% |
7304
56.3 IPS |
|
Depth Estimation (HP)
|
99% |
64203
494.6 IPS |
|
Depth Estimation (Q)
|
97% |
73641
569.4 IPS |
|
Style Transfer (SP)
|
100% |
22034
28.3 IPS |
|
Style Transfer (HP)
|
100% |
139060
178.8 IPS |
|
Style Transfer (Q)
|
100% |
139345
179.1 IPS |
|
Image Super-Resolution (SP)
|
100% |
4987
184.1 IPS |
|
Image Super-Resolution (HP)
|
100% |
35322
1.30 KIPS |
|
Image Super-Resolution (Q)
|
98% |
56841
2.11 KIPS |
|
Text Classification (SP)
|
100% |
3169
4.23 KIPS |
|
Text Classification (HP)
|
100% |
3256
4.35 KIPS |
|
Text Classification (Q)
|
93% |
3245
4.36 KIPS |
|
Machine Translation (SP)
|
100% |
3156
54.4 IPS |
|
Machine Translation (HP)
|
100% |
6595
113.6 IPS |
|
Machine Translation (Q)
|
98% |
7489
129.4 IPS |