User | toygoon |
Upload Date | August 31 2024 03:20 PM |
Views | 4 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A16 Bionic |
System Information | |
---|---|
Operating System | iOS 17.0 |
Model | iPhone 14 Pro Max |
Model ID | iPhone15,3 |
Motherboard | D74AP |
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 | 5.49 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1233
229.3 IPS |
|
Image Classification (HP)
|
100% |
5895
1.10 KIPS |
|
Image Classification (Q)
|
99% |
6184
1.15 KIPS |
|
Image Segmentation (SP)
|
100% |
732
11.9 IPS |
|
Image Segmentation (HP)
|
100% |
5154
83.6 IPS |
|
Image Segmentation (Q)
|
100% |
5127
83.1 IPS |
|
Pose Estimation (SP)
|
100% |
5875
6.86 IPS |
|
Pose Estimation (HP)
|
100% |
82042
95.7 IPS |
|
Pose Estimation (Q)
|
94% |
80996
95.0 IPS |
|
Object Detection (SP)
|
100% |
1303
103.3 IPS |
|
Object Detection (HP)
|
100% |
7087
562.2 IPS |
|
Object Detection (Q)
|
93% |
8259
659.0 IPS |
|
Face Detection (SP)
|
100% |
2195
26.1 IPS |
|
Face Detection (HP)
|
100% |
13587
161.4 IPS |
|
Face Detection (Q)
|
100% |
641
7.62 IPS |
|
Depth Estimation (SP)
|
100% |
4020
31.0 IPS |
|
Depth Estimation (HP)
|
99% |
39680
305.7 IPS |
|
Depth Estimation (Q)
|
97% |
44388
343.2 IPS |
|
Style Transfer (SP)
|
100% |
11317
14.5 IPS |
|
Style Transfer (HP)
|
100% |
122428
157.4 IPS |
|
Style Transfer (Q)
|
100% |
122620
157.6 IPS |
|
Image Super-Resolution (SP)
|
100% |
3097
114.4 IPS |
|
Image Super-Resolution (HP)
|
100% |
17381
641.8 IPS |
|
Image Super-Resolution (Q)
|
98% |
17474
647.4 IPS |
|
Text Classification (SP)
|
100% |
1383
1.85 KIPS |
|
Text Classification (HP)
|
100% |
3197
4.27 KIPS |
|
Text Classification (Q)
|
93% |
3182
4.27 KIPS |
|
Machine Translation (SP)
|
100% |
1582
27.2 IPS |
|
Machine Translation (HP)
|
100% |
2300
39.6 IPS |
|
Machine Translation (Q)
|
98% |
2188
37.8 IPS |