User | Xabla |
Upload Date | September 21 2024 09:48 PM |
Views | 3 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A16 Bionic |
System Information | |
---|---|
Operating System | iOS 17.7 |
Model | iPhone 15 Plus |
Model ID | iPhone15,5 |
Motherboard | D38AP |
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% |
1257
233.7 IPS |
|
Image Classification (HP)
|
100% |
5861
1.09 KIPS |
|
Image Classification (Q)
|
97% |
6502
1.21 KIPS |
|
Image Segmentation (SP)
|
100% |
758
12.3 IPS |
|
Image Segmentation (HP)
|
100% |
5115
82.9 IPS |
|
Image Segmentation (Q)
|
99% |
9666
156.7 IPS |
|
Pose Estimation (SP)
|
100% |
5955
6.95 IPS |
|
Pose Estimation (HP)
|
100% |
83534
97.5 IPS |
|
Pose Estimation (Q)
|
95% |
87603
102.7 IPS |
|
Object Detection (SP)
|
100% |
1286
102.0 IPS |
|
Object Detection (HP)
|
100% |
7221
572.8 IPS |
|
Object Detection (Q)
|
93% |
8224
656.2 IPS |
|
Face Detection (SP)
|
100% |
2193
26.1 IPS |
|
Face Detection (HP)
|
100% |
10994
130.6 IPS |
|
Face Detection (Q)
|
100% |
12887
153.1 IPS |
|
Depth Estimation (SP)
|
100% |
4009
30.9 IPS |
|
Depth Estimation (HP)
|
99% |
42941
330.8 IPS |
|
Depth Estimation (Q)
|
85% |
50107
391.8 IPS |
|
Style Transfer (SP)
|
100% |
10753
13.8 IPS |
|
Style Transfer (HP)
|
100% |
126760
163.0 IPS |
|
Style Transfer (Q)
|
96% |
118070
152.4 IPS |
|
Image Super-Resolution (SP)
|
100% |
3191
117.8 IPS |
|
Image Super-Resolution (HP)
|
100% |
16051
592.7 IPS |
|
Image Super-Resolution (Q)
|
99% |
20989
775.0 IPS |
|
Text Classification (SP)
|
100% |
1374
1.83 KIPS |
|
Text Classification (HP)
|
100% |
3149
4.20 KIPS |
|
Text Classification (Q)
|
93% |
3071
4.12 KIPS |
|
Machine Translation (SP)
|
100% |
1663
28.6 IPS |
|
Machine Translation (HP)
|
100% |
2256
38.9 IPS |
|
Machine Translation (Q)
|
98% |
2308
39.9 IPS |