User | tyc0746 |
Upload Date | August 15 2024 10:08 PM |
Views | 8 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A16 Bionic |
System Information | |
---|---|
Operating System | iOS 17.6.1 |
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% |
1239
230.4 IPS |
|
Image Classification (HP)
|
100% |
5805
1.08 KIPS |
|
Image Classification (Q)
|
99% |
6163
1.15 KIPS |
|
Image Segmentation (SP)
|
100% |
746
12.1 IPS |
|
Image Segmentation (HP)
|
100% |
5101
82.7 IPS |
|
Image Segmentation (Q)
|
100% |
5122
83.0 IPS |
|
Pose Estimation (SP)
|
100% |
6260
7.30 IPS |
|
Pose Estimation (HP)
|
100% |
79952
93.3 IPS |
|
Pose Estimation (Q)
|
94% |
85730
100.6 IPS |
|
Object Detection (SP)
|
100% |
1303
103.3 IPS |
|
Object Detection (HP)
|
100% |
7234
573.8 IPS |
|
Object Detection (Q)
|
93% |
8209
655.0 IPS |
|
Face Detection (SP)
|
100% |
2187
26.0 IPS |
|
Face Detection (HP)
|
100% |
10903
129.6 IPS |
|
Face Detection (Q)
|
100% |
12972
154.1 IPS |
|
Depth Estimation (SP)
|
100% |
4111
31.7 IPS |
|
Depth Estimation (HP)
|
99% |
39130
301.5 IPS |
|
Depth Estimation (Q)
|
97% |
44110
341.1 IPS |
|
Style Transfer (SP)
|
100% |
11156
14.3 IPS |
|
Style Transfer (HP)
|
100% |
121279
155.9 IPS |
|
Style Transfer (Q)
|
100% |
122182
157.1 IPS |
|
Image Super-Resolution (SP)
|
100% |
3255
120.2 IPS |
|
Image Super-Resolution (HP)
|
100% |
16521
610.1 IPS |
|
Image Super-Resolution (Q)
|
98% |
21351
791.0 IPS |
|
Text Classification (SP)
|
100% |
1377
1.84 KIPS |
|
Text Classification (HP)
|
100% |
3272
4.37 KIPS |
|
Text Classification (Q)
|
93% |
3207
4.30 KIPS |
|
Machine Translation (SP)
|
100% |
1658
28.6 IPS |
|
Machine Translation (HP)
|
100% |
2301
39.6 IPS |
|
Machine Translation (Q)
|
98% |
2227
38.5 IPS |