Upload Date | December 22 2024 09:43 AM |
Views | 5 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A16 Bionic |
System Information | |
---|---|
Operating System | iOS 18.2 |
Model | iPhone 15 |
Model ID | iPhone15,4 |
Motherboard | D37AP |
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 | 5.56 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1440
267.7 IPS |
|
Image Classification (HP)
|
100% |
10196
1.90 KIPS |
|
Image Classification (Q)
|
97% |
12398
2.31 KIPS |
|
Image Segmentation (SP)
|
100% |
1457
23.6 IPS |
|
Image Segmentation (HP)
|
100% |
14722
238.7 IPS |
|
Image Segmentation (Q)
|
99% |
18377
297.9 IPS |
|
Pose Estimation (SP)
|
100% |
6243
7.29 IPS |
|
Pose Estimation (HP)
|
100% |
98757
115.2 IPS |
|
Pose Estimation (Q)
|
95% |
101829
119.3 IPS |
|
Object Detection (SP)
|
100% |
1548
122.8 IPS |
|
Object Detection (HP)
|
100% |
12934
1.03 KIPS |
|
Object Detection (Q)
|
91% |
14825
1.18 KIPS |
|
Face Detection (SP)
|
100% |
3234
38.4 IPS |
|
Face Detection (HP)
|
100% |
31517
374.5 IPS |
|
Face Detection (Q)
|
100% |
40766
484.4 IPS |
|
Depth Estimation (SP)
|
100% |
5934
45.7 IPS |
|
Depth Estimation (HP)
|
99% |
75009
577.9 IPS |
|
Depth Estimation (Q)
|
85% |
96446
754.1 IPS |
|
Style Transfer (SP)
|
100% |
18123
23.3 IPS |
|
Style Transfer (HP)
|
100% |
177002
227.5 IPS |
|
Style Transfer (Q)
|
96% |
173072
223.3 IPS |
|
Image Super-Resolution (SP)
|
100% |
3934
145.3 IPS |
|
Image Super-Resolution (HP)
|
100% |
32235
1.19 KIPS |
|
Image Super-Resolution (Q)
|
99% |
37371
1.38 KIPS |
|
Text Classification (SP)
|
100% |
2622
3.50 KIPS |
|
Text Classification (HP)
|
100% |
1994
2.66 KIPS |
|
Text Classification (Q)
|
93% |
1823
2.45 KIPS |
|
Machine Translation (SP)
|
100% |
3403
58.6 IPS |
|
Machine Translation (HP)
|
100% |
7385
127.2 IPS |
|
Machine Translation (Q)
|
98% |
7958
137.5 IPS |