Upload Date | September 18 2024 10:34 AM |
Views | 1 |
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% |
1332
247.7 IPS |
|
Image Classification (HP)
|
100% |
7872
1.46 KIPS |
|
Image Classification (Q)
|
96% |
11687
2.18 KIPS |
|
Image Segmentation (SP)
|
100% |
1289
20.9 IPS |
|
Image Segmentation (HP)
|
100% |
7611
123.4 IPS |
|
Image Segmentation (Q)
|
99% |
7799
126.4 IPS |
|
Pose Estimation (SP)
|
100% |
5316
6.20 IPS |
|
Pose Estimation (HP)
|
100% |
85324
99.6 IPS |
|
Pose Estimation (Q)
|
95% |
93960
110.1 IPS |
|
Object Detection (SP)
|
100% |
1388
110.1 IPS |
|
Object Detection (HP)
|
99% |
11040
878.2 IPS |
|
Object Detection (Q)
|
91% |
11699
934.8 IPS |
|
Face Detection (SP)
|
100% |
2612
31.0 IPS |
|
Face Detection (HP)
|
100% |
25244
300.0 IPS |
|
Face Detection (Q)
|
100% |
35445
421.2 IPS |
|
Depth Estimation (SP)
|
100% |
5308
40.9 IPS |
|
Depth Estimation (HP)
|
99% |
57842
445.6 IPS |
|
Depth Estimation (Q)
|
85% |
76446
597.4 IPS |
|
Style Transfer (SP)
|
100% |
17203
22.1 IPS |
|
Style Transfer (HP)
|
100% |
156585
201.3 IPS |
|
Style Transfer (Q)
|
96% |
156145
201.5 IPS |
|
Image Super-Resolution (SP)
|
100% |
3832
141.5 IPS |
|
Image Super-Resolution (HP)
|
100% |
26989
996.6 IPS |
|
Image Super-Resolution (Q)
|
99% |
28347
1.05 KIPS |
|
Text Classification (SP)
|
100% |
2427
3.24 KIPS |
|
Text Classification (HP)
|
100% |
2246
3.00 KIPS |
|
Text Classification (Q)
|
93% |
2269
3.05 KIPS |
|
Machine Translation (SP)
|
100% |
3392
58.4 IPS |
|
Machine Translation (HP)
|
100% |
2201
37.9 IPS |
|
Machine Translation (Q)
|
98% |
2211
38.2 IPS |