User | tesme33 |
Upload Date | September 11 2024 05:56 AM |
Views | 4 |
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% |
1244
231.4 IPS |
|
Image Classification (HP)
|
100% |
5831
1.08 KIPS |
|
Image Classification (Q)
|
97% |
6222
1.16 KIPS |
|
Image Segmentation (SP)
|
100% |
750
12.2 IPS |
|
Image Segmentation (HP)
|
100% |
5062
82.1 IPS |
|
Image Segmentation (Q)
|
99% |
9344
151.5 IPS |
|
Pose Estimation (SP)
|
100% |
6549
7.64 IPS |
|
Pose Estimation (HP)
|
100% |
79106
92.3 IPS |
|
Pose Estimation (Q)
|
95% |
86377
101.2 IPS |
|
Object Detection (SP)
|
100% |
1341
106.3 IPS |
|
Object Detection (HP)
|
100% |
7466
592.2 IPS |
|
Object Detection (Q)
|
93% |
8177
652.5 IPS |
|
Face Detection (SP)
|
100% |
2308
27.4 IPS |
|
Face Detection (HP)
|
100% |
10820
128.6 IPS |
|
Face Detection (Q)
|
100% |
12996
154.4 IPS |
|
Depth Estimation (SP)
|
100% |
4211
32.4 IPS |
|
Depth Estimation (HP)
|
99% |
40471
311.8 IPS |
|
Depth Estimation (Q)
|
85% |
51975
406.4 IPS |
|
Style Transfer (SP)
|
100% |
11449
14.7 IPS |
|
Style Transfer (HP)
|
100% |
121738
156.5 IPS |
|
Style Transfer (Q)
|
96% |
114903
148.3 IPS |
|
Image Super-Resolution (SP)
|
100% |
3383
124.9 IPS |
|
Image Super-Resolution (HP)
|
100% |
16714
617.2 IPS |
|
Image Super-Resolution (Q)
|
99% |
21653
799.5 IPS |
|
Text Classification (SP)
|
100% |
1380
1.84 KIPS |
|
Text Classification (HP)
|
100% |
3164
4.22 KIPS |
|
Text Classification (Q)
|
93% |
3274
4.39 KIPS |
|
Machine Translation (SP)
|
100% |
1638
28.2 IPS |
|
Machine Translation (HP)
|
100% |
2377
41.0 IPS |
|
Machine Translation (Q)
|
98% |
2357
40.7 IPS |