User | ragnarokchan |
Upload Date | August 16 2024 02:26 AM |
Views | 9 |
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% |
1248
232.1 IPS |
|
Image Classification (HP)
|
100% |
5881
1.09 KIPS |
|
Image Classification (Q)
|
99% |
6195
1.16 KIPS |
|
Image Segmentation (SP)
|
100% |
752
12.2 IPS |
|
Image Segmentation (HP)
|
100% |
5143
83.4 IPS |
|
Image Segmentation (Q)
|
100% |
5089
82.5 IPS |
|
Pose Estimation (SP)
|
100% |
6364
7.43 IPS |
|
Pose Estimation (HP)
|
100% |
78548
91.7 IPS |
|
Pose Estimation (Q)
|
94% |
85086
99.8 IPS |
|
Object Detection (SP)
|
100% |
1335
105.9 IPS |
|
Object Detection (HP)
|
100% |
7692
610.2 IPS |
|
Object Detection (Q)
|
93% |
8271
660.0 IPS |
|
Face Detection (SP)
|
100% |
2271
27.0 IPS |
|
Face Detection (HP)
|
100% |
10998
130.7 IPS |
|
Face Detection (Q)
|
100% |
12912
153.4 IPS |
|
Depth Estimation (SP)
|
100% |
4205
32.4 IPS |
|
Depth Estimation (HP)
|
99% |
42678
328.8 IPS |
|
Depth Estimation (Q)
|
97% |
46200
357.2 IPS |
|
Style Transfer (SP)
|
100% |
11400
14.7 IPS |
|
Style Transfer (HP)
|
100% |
120873
155.4 IPS |
|
Style Transfer (Q)
|
100% |
120790
155.3 IPS |
|
Image Super-Resolution (SP)
|
100% |
3342
123.4 IPS |
|
Image Super-Resolution (HP)
|
100% |
16104
594.6 IPS |
|
Image Super-Resolution (Q)
|
98% |
21060
780.2 IPS |
|
Text Classification (SP)
|
100% |
1382
1.84 KIPS |
|
Text Classification (HP)
|
100% |
3202
4.27 KIPS |
|
Text Classification (Q)
|
93% |
3202
4.30 KIPS |
|
Machine Translation (SP)
|
100% |
1658
28.6 IPS |
|
Machine Translation (HP)
|
100% |
2364
40.7 IPS |
|
Machine Translation (Q)
|
98% |
2402
41.5 IPS |