User | Tom34772 |
Upload Date | September 06 2024 12:28 AM |
Views | 4 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A15 Bionic |
System Information | |
---|---|
Operating System | iOS 18.0 |
Model | iPhone 13 Pro Max |
Model ID | iPhone14,3 |
Motherboard | D64AP |
CPU Information | |
---|---|
Name | Apple A15 Bionic |
Topology | 1 Processor, 6 Cores |
Identifier | ARM |
Base Frequency | 3.23 GHz |
Cluster 1 | 2 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 5.51 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1352
251.4 IPS |
|
Image Classification (HP)
|
100% |
8300
1.54 KIPS |
|
Image Classification (Q)
|
96% |
10477
1.96 KIPS |
|
Image Segmentation (SP)
|
100% |
1305
21.1 IPS |
|
Image Segmentation (HP)
|
100% |
6794
110.1 IPS |
|
Image Segmentation (Q)
|
99% |
7760
125.8 IPS |
|
Pose Estimation (SP)
|
100% |
6491
7.57 IPS |
|
Pose Estimation (HP)
|
100% |
84993
99.2 IPS |
|
Pose Estimation (Q)
|
95% |
93385
109.5 IPS |
|
Object Detection (SP)
|
100% |
1470
116.6 IPS |
|
Object Detection (HP)
|
99% |
10433
829.9 IPS |
|
Object Detection (Q)
|
91% |
11661
931.8 IPS |
|
Face Detection (SP)
|
100% |
2715
32.3 IPS |
|
Face Detection (HP)
|
100% |
26242
311.8 IPS |
|
Face Detection (Q)
|
100% |
32229
383.0 IPS |
|
Depth Estimation (SP)
|
100% |
5512
42.5 IPS |
|
Depth Estimation (HP)
|
99% |
55792
429.8 IPS |
|
Depth Estimation (Q)
|
85% |
73460
574.1 IPS |
|
Style Transfer (SP)
|
100% |
17809
22.9 IPS |
|
Style Transfer (HP)
|
100% |
155577
200.0 IPS |
|
Style Transfer (Q)
|
96% |
152711
197.1 IPS |
|
Image Super-Resolution (SP)
|
100% |
3967
146.5 IPS |
|
Image Super-Resolution (HP)
|
100% |
26959
995.5 IPS |
|
Image Super-Resolution (Q)
|
99% |
30453
1.12 KIPS |
|
Text Classification (SP)
|
100% |
2422
3.23 KIPS |
|
Text Classification (HP)
|
100% |
2326
3.11 KIPS |
|
Text Classification (Q)
|
93% |
2371
3.18 KIPS |
|
Machine Translation (SP)
|
100% |
3505
60.4 IPS |
|
Machine Translation (HP)
|
100% |
2276
39.2 IPS |
|
Machine Translation (Q)
|
98% |
2257
39.0 IPS |