Upload Date | November 17 2024 09:22 PM |
Views | 1 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A15 Bionic |
System Information | |
---|---|
Operating System | iOS 18.1 |
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% |
1368
254.4 IPS |
|
Image Classification (HP)
|
100% |
8076
1.50 KIPS |
|
Image Classification (Q)
|
96% |
9743
1.82 KIPS |
|
Image Segmentation (SP)
|
100% |
1348
21.9 IPS |
|
Image Segmentation (HP)
|
100% |
11907
193.0 IPS |
|
Image Segmentation (Q)
|
99% |
15009
243.3 IPS |
|
Pose Estimation (SP)
|
100% |
6532
7.62 IPS |
|
Pose Estimation (HP)
|
100% |
90925
106.1 IPS |
|
Pose Estimation (Q)
|
95% |
94528
110.8 IPS |
|
Object Detection (SP)
|
100% |
1476
117.1 IPS |
|
Object Detection (HP)
|
99% |
11093
882.4 IPS |
|
Object Detection (Q)
|
91% |
12027
961.0 IPS |
|
Face Detection (SP)
|
100% |
2700
32.1 IPS |
|
Face Detection (HP)
|
100% |
29327
348.5 IPS |
|
Face Detection (Q)
|
100% |
37206
442.1 IPS |
|
Depth Estimation (SP)
|
100% |
5514
42.5 IPS |
|
Depth Estimation (HP)
|
99% |
55548
428.0 IPS |
|
Depth Estimation (Q)
|
85% |
75548
590.4 IPS |
|
Style Transfer (SP)
|
100% |
18109
23.3 IPS |
|
Style Transfer (HP)
|
100% |
159348
204.8 IPS |
|
Style Transfer (Q)
|
96% |
165918
214.1 IPS |
|
Image Super-Resolution (SP)
|
100% |
4098
151.3 IPS |
|
Image Super-Resolution (HP)
|
100% |
28740
1.06 KIPS |
|
Image Super-Resolution (Q)
|
99% |
33982
1.25 KIPS |
|
Text Classification (SP)
|
100% |
2442
3.26 KIPS |
|
Text Classification (HP)
|
100% |
2347
3.13 KIPS |
|
Text Classification (Q)
|
93% |
2325
3.12 KIPS |
|
Machine Translation (SP)
|
100% |
3432
59.1 IPS |
|
Machine Translation (HP)
|
100% |
5069
87.3 IPS |
|
Machine Translation (Q)
|
98% |
5656
97.7 IPS |