User | Hogehoge |
Upload Date | September 10 2024 07:07 PM |
Views | 3 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A17 Pro |
System Information | |
---|---|
Operating System | iOS 17.6.1 |
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 | 7.47 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1484
276.1 IPS |
|
Image Classification (HP)
|
100% |
6218
1.16 KIPS |
|
Image Classification (Q)
|
97% |
7153
1.33 KIPS |
|
Image Segmentation (SP)
|
100% |
832
13.5 IPS |
|
Image Segmentation (HP)
|
100% |
5216
84.6 IPS |
|
Image Segmentation (Q)
|
99% |
10037
162.7 IPS |
|
Pose Estimation (SP)
|
100% |
8100
9.45 IPS |
|
Pose Estimation (HP)
|
100% |
88005
102.7 IPS |
|
Pose Estimation (Q)
|
95% |
151354
177.4 IPS |
|
Object Detection (SP)
|
100% |
1558
123.6 IPS |
|
Object Detection (HP)
|
100% |
8053
638.8 IPS |
|
Object Detection (Q)
|
93% |
9951
794.0 IPS |
|
Face Detection (SP)
|
100% |
2419
28.7 IPS |
|
Face Detection (HP)
|
100% |
11185
132.9 IPS |
|
Face Detection (Q)
|
100% |
13229
157.2 IPS |
|
Depth Estimation (SP)
|
100% |
4997
38.5 IPS |
|
Depth Estimation (HP)
|
99% |
42679
328.8 IPS |
|
Depth Estimation (Q)
|
85% |
59246
463.2 IPS |
|
Style Transfer (SP)
|
100% |
13171
16.9 IPS |
|
Style Transfer (HP)
|
100% |
127749
164.2 IPS |
|
Style Transfer (Q)
|
96% |
137766
177.8 IPS |
|
Image Super-Resolution (SP)
|
100% |
4341
160.3 IPS |
|
Image Super-Resolution (HP)
|
100% |
18374
678.5 IPS |
|
Image Super-Resolution (Q)
|
99% |
25921
957.1 IPS |
|
Text Classification (SP)
|
100% |
1853
2.47 KIPS |
|
Text Classification (HP)
|
71% |
4535
6.52 KIPS |
|
Text Classification (Q)
|
69% |
4492
6.58 KIPS |
|
Machine Translation (SP)
|
100% |
1967
33.9 IPS |
|
Machine Translation (HP)
|
100% |
2659
45.8 IPS |
|
Machine Translation (Q)
|
98% |
2623
45.3 IPS |