Upload Date | September 17 2024 02:29 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% |
1361
253.2 IPS |
|
Image Classification (HP)
|
100% |
8234
1.53 KIPS |
|
Image Classification (Q)
|
96% |
9275
1.73 KIPS |
|
Image Segmentation (SP)
|
100% |
1315
21.3 IPS |
|
Image Segmentation (HP)
|
100% |
6851
111.1 IPS |
|
Image Segmentation (Q)
|
99% |
7409
120.1 IPS |
|
Pose Estimation (SP)
|
100% |
6650
7.76 IPS |
|
Pose Estimation (HP)
|
100% |
85873
100.2 IPS |
|
Pose Estimation (Q)
|
95% |
92580
108.5 IPS |
|
Object Detection (SP)
|
100% |
1487
118.0 IPS |
|
Object Detection (HP)
|
99% |
10301
819.5 IPS |
|
Object Detection (Q)
|
91% |
11107
887.5 IPS |
|
Face Detection (SP)
|
100% |
2713
32.2 IPS |
|
Face Detection (HP)
|
100% |
25133
298.6 IPS |
|
Face Detection (Q)
|
100% |
32101
381.4 IPS |
|
Depth Estimation (SP)
|
100% |
5596
43.1 IPS |
|
Depth Estimation (HP)
|
99% |
52357
403.4 IPS |
|
Depth Estimation (Q)
|
85% |
73554
574.8 IPS |
|
Style Transfer (SP)
|
100% |
17882
23.0 IPS |
|
Style Transfer (HP)
|
100% |
149877
192.7 IPS |
|
Style Transfer (Q)
|
96% |
148321
191.4 IPS |
|
Image Super-Resolution (SP)
|
100% |
3989
147.3 IPS |
|
Image Super-Resolution (HP)
|
100% |
25758
951.1 IPS |
|
Image Super-Resolution (Q)
|
99% |
27284
1.01 KIPS |
|
Text Classification (SP)
|
100% |
2426
3.24 KIPS |
|
Text Classification (HP)
|
100% |
1518
2.03 KIPS |
|
Text Classification (Q)
|
93% |
2197
2.95 KIPS |
|
Machine Translation (SP)
|
100% |
3419
58.9 IPS |
|
Machine Translation (HP)
|
100% |
2196
37.8 IPS |
|
Machine Translation (Q)
|
98% |
2186
37.8 IPS |