User | ragnarokchan |
Upload Date | August 16 2024 02:08 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% |
1232
229.1 IPS |
|
Image Classification (HP)
|
100% |
5734
1.07 KIPS |
|
Image Classification (Q)
|
99% |
6166
1.15 KIPS |
|
Image Segmentation (SP)
|
100% |
750
12.2 IPS |
|
Image Segmentation (HP)
|
100% |
5099
82.7 IPS |
|
Image Segmentation (Q)
|
100% |
5075
82.3 IPS |
|
Pose Estimation (SP)
|
100% |
6334
7.39 IPS |
|
Pose Estimation (HP)
|
100% |
80398
93.8 IPS |
|
Pose Estimation (Q)
|
94% |
84546
99.2 IPS |
|
Object Detection (SP)
|
100% |
1315
104.3 IPS |
|
Object Detection (HP)
|
100% |
7639
605.9 IPS |
|
Object Detection (Q)
|
93% |
8254
658.6 IPS |
|
Face Detection (SP)
|
100% |
2228
26.5 IPS |
|
Face Detection (HP)
|
100% |
10966
130.3 IPS |
|
Face Detection (Q)
|
100% |
13150
156.3 IPS |
|
Depth Estimation (SP)
|
100% |
4158
32.0 IPS |
|
Depth Estimation (HP)
|
99% |
41248
317.8 IPS |
|
Depth Estimation (Q)
|
97% |
46830
362.1 IPS |
|
Style Transfer (SP)
|
100% |
11308
14.5 IPS |
|
Style Transfer (HP)
|
100% |
121695
156.4 IPS |
|
Style Transfer (Q)
|
100% |
124511
160.1 IPS |
|
Image Super-Resolution (SP)
|
100% |
3251
120.0 IPS |
|
Image Super-Resolution (HP)
|
100% |
16909
624.4 IPS |
|
Image Super-Resolution (Q)
|
98% |
20768
769.4 IPS |
|
Text Classification (SP)
|
100% |
1379
1.84 KIPS |
|
Text Classification (HP)
|
100% |
3247
4.33 KIPS |
|
Text Classification (Q)
|
93% |
3139
4.21 KIPS |
|
Machine Translation (SP)
|
100% |
1660
28.6 IPS |
|
Machine Translation (HP)
|
100% |
2345
40.4 IPS |
|
Machine Translation (Q)
|
98% |
2326
40.2 IPS |