Upload Date | September 14 2024 11:07 PM |
Views | 13 |
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% |
1642
305.5 IPS |
|
Image Classification (HP)
|
100% |
11144
2.07 KIPS |
|
Image Classification (Q)
|
97% |
15491
2.89 KIPS |
|
Image Segmentation (SP)
|
100% |
1618
26.2 IPS |
|
Image Segmentation (HP)
|
100% |
12899
209.1 IPS |
|
Image Segmentation (Q)
|
99% |
16104
261.1 IPS |
|
Pose Estimation (SP)
|
100% |
7600
8.87 IPS |
|
Pose Estimation (HP)
|
100% |
106038
123.7 IPS |
|
Pose Estimation (Q)
|
95% |
204006
239.1 IPS |
|
Object Detection (SP)
|
100% |
1776
140.9 IPS |
|
Object Detection (HP)
|
100% |
13941
1.11 KIPS |
|
Object Detection (Q)
|
91% |
19253
1.54 KIPS |
|
Face Detection (SP)
|
100% |
3186
37.9 IPS |
|
Face Detection (HP)
|
100% |
33346
396.2 IPS |
|
Face Detection (Q)
|
100% |
49214
584.8 IPS |
|
Depth Estimation (SP)
|
100% |
6991
53.9 IPS |
|
Depth Estimation (HP)
|
99% |
78164
602.2 IPS |
|
Depth Estimation (Q)
|
85% |
129047
1.01 KIPS |
|
Style Transfer (SP)
|
100% |
20598
26.5 IPS |
|
Style Transfer (HP)
|
100% |
139140
178.9 IPS |
|
Style Transfer (Q)
|
96% |
165259
213.3 IPS |
|
Image Super-Resolution (SP)
|
100% |
4841
178.7 IPS |
|
Image Super-Resolution (HP)
|
100% |
35686
1.32 KIPS |
|
Image Super-Resolution (Q)
|
99% |
56826
2.10 KIPS |
|
Text Classification (SP)
|
100% |
3180
4.24 KIPS |
|
Text Classification (HP)
|
100% |
2786
3.72 KIPS |
|
Text Classification (Q)
|
93% |
1888
2.53 KIPS |
|
Machine Translation (SP)
|
100% |
3131
53.9 IPS |
|
Machine Translation (HP)
|
100% |
6160
106.1 IPS |
|
Machine Translation (Q)
|
98% |
7368
127.3 IPS |