User | M91 |
Upload Date | September 30 2024 11:31 AM |
Views | 2 |
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% |
1656
307.9 IPS |
|
Image Classification (HP)
|
100% |
11482
2.14 KIPS |
|
Image Classification (Q)
|
97% |
14678
2.74 KIPS |
|
Image Segmentation (SP)
|
100% |
1598
25.9 IPS |
|
Image Segmentation (HP)
|
100% |
15749
255.3 IPS |
|
Image Segmentation (Q)
|
99% |
20771
336.7 IPS |
|
Pose Estimation (SP)
|
100% |
7529
8.79 IPS |
|
Pose Estimation (HP)
|
100% |
106221
123.9 IPS |
|
Pose Estimation (Q)
|
95% |
203886
239.0 IPS |
|
Object Detection (SP)
|
100% |
1747
138.6 IPS |
|
Object Detection (HP)
|
100% |
13853
1.10 KIPS |
|
Object Detection (Q)
|
91% |
18640
1.49 KIPS |
|
Face Detection (SP)
|
100% |
3150
37.4 IPS |
|
Face Detection (HP)
|
100% |
35160
417.8 IPS |
|
Face Detection (Q)
|
100% |
51303
609.6 IPS |
|
Depth Estimation (SP)
|
100% |
6856
52.8 IPS |
|
Depth Estimation (HP)
|
99% |
79587
613.2 IPS |
|
Depth Estimation (Q)
|
85% |
131649
1.03 KIPS |
|
Style Transfer (SP)
|
100% |
19939
25.6 IPS |
|
Style Transfer (HP)
|
100% |
204430
262.8 IPS |
|
Style Transfer (Q)
|
96% |
249197
321.6 IPS |
|
Image Super-Resolution (SP)
|
100% |
4720
174.3 IPS |
|
Image Super-Resolution (HP)
|
100% |
34032
1.26 KIPS |
|
Image Super-Resolution (Q)
|
99% |
54258
2.00 KIPS |
|
Text Classification (SP)
|
100% |
3199
4.27 KIPS |
|
Text Classification (HP)
|
100% |
2802
3.74 KIPS |
|
Text Classification (Q)
|
93% |
1745
2.34 KIPS |
|
Machine Translation (SP)
|
100% |
3144
54.2 IPS |
|
Machine Translation (HP)
|
100% |
6046
104.2 IPS |
|
Machine Translation (Q)
|
98% |
7651
132.2 IPS |