User | sfoskett |
Upload Date | August 15 2024 07:29 PM |
Views | 4 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A16 Bionic |
System Information | |
---|---|
Operating System | iOS 17.5.1 |
Model | iPhone 14 Pro |
Model ID | iPhone15,2 |
Motherboard | D73AP |
CPU Information | |
---|---|
Name | Apple A16 Bionic |
Topology | 1 Processor, 6 Cores |
Identifier | ARM |
Base Frequency | 3.46 GHz |
Cluster 1 | 2 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 5.50 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1240
230.6 IPS |
|
Image Classification (HP)
|
100% |
5906
1.10 KIPS |
|
Image Classification (Q)
|
99% |
6181
1.15 KIPS |
|
Image Segmentation (SP)
|
100% |
751
12.2 IPS |
|
Image Segmentation (HP)
|
100% |
5153
83.5 IPS |
|
Image Segmentation (Q)
|
100% |
5080
82.4 IPS |
|
Pose Estimation (SP)
|
100% |
6414
7.48 IPS |
|
Pose Estimation (HP)
|
100% |
78866
92.0 IPS |
|
Pose Estimation (Q)
|
94% |
82885
97.2 IPS |
|
Object Detection (SP)
|
100% |
1305
103.5 IPS |
|
Object Detection (HP)
|
100% |
7835
621.5 IPS |
|
Object Detection (Q)
|
93% |
7218
575.9 IPS |
|
Face Detection (SP)
|
100% |
2227
26.5 IPS |
|
Face Detection (HP)
|
100% |
11046
131.2 IPS |
|
Face Detection (Q)
|
100% |
12539
149.0 IPS |
|
Depth Estimation (SP)
|
100% |
4203
32.4 IPS |
|
Depth Estimation (HP)
|
99% |
44125
340.0 IPS |
|
Depth Estimation (Q)
|
97% |
46584
360.2 IPS |
|
Style Transfer (SP)
|
100% |
11329
14.6 IPS |
|
Style Transfer (HP)
|
100% |
123037
158.2 IPS |
|
Style Transfer (Q)
|
100% |
120128
154.4 IPS |
|
Image Super-Resolution (SP)
|
100% |
3304
122.0 IPS |
|
Image Super-Resolution (HP)
|
100% |
17056
629.8 IPS |
|
Image Super-Resolution (Q)
|
98% |
21519
797.2 IPS |
|
Text Classification (SP)
|
100% |
1385
1.85 KIPS |
|
Text Classification (HP)
|
100% |
3417
4.56 KIPS |
|
Text Classification (Q)
|
93% |
3188
4.28 KIPS |
|
Machine Translation (SP)
|
100% |
1646
28.4 IPS |
|
Machine Translation (HP)
|
100% |
2344
40.4 IPS |
|
Machine Translation (Q)
|
98% |
2330
40.3 IPS |