User | justtea |
Upload Date | November 20 2024 10:36 PM |
Views | 2 |
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% |
1435
266.9 IPS |
|
Image Classification (HP)
|
100% |
10052
1.87 KIPS |
|
Image Classification (Q)
|
97% |
12296
2.29 KIPS |
|
Image Segmentation (SP)
|
100% |
1509
24.5 IPS |
|
Image Segmentation (HP)
|
100% |
13983
226.7 IPS |
|
Image Segmentation (Q)
|
99% |
18226
295.5 IPS |
|
Pose Estimation (SP)
|
100% |
6214
7.25 IPS |
|
Pose Estimation (HP)
|
100% |
98317
114.7 IPS |
|
Pose Estimation (Q)
|
95% |
102010
119.6 IPS |
|
Object Detection (SP)
|
100% |
1571
124.6 IPS |
|
Object Detection (HP)
|
100% |
12952
1.03 KIPS |
|
Object Detection (Q)
|
91% |
14870
1.19 KIPS |
|
Face Detection (SP)
|
100% |
3216
38.2 IPS |
|
Face Detection (HP)
|
100% |
30978
368.1 IPS |
|
Face Detection (Q)
|
100% |
40649
483.0 IPS |
|
Depth Estimation (SP)
|
100% |
5857
45.1 IPS |
|
Depth Estimation (HP)
|
99% |
74971
577.6 IPS |
|
Depth Estimation (Q)
|
85% |
96685
755.9 IPS |
|
Style Transfer (SP)
|
100% |
16614
21.4 IPS |
|
Style Transfer (HP)
|
100% |
171638
220.6 IPS |
|
Style Transfer (Q)
|
96% |
172180
222.2 IPS |
|
Image Super-Resolution (SP)
|
100% |
3899
144.0 IPS |
|
Image Super-Resolution (HP)
|
100% |
31940
1.18 KIPS |
|
Image Super-Resolution (Q)
|
99% |
37191
1.37 KIPS |
|
Text Classification (SP)
|
100% |
2614
3.49 KIPS |
|
Text Classification (HP)
|
100% |
1987
2.65 KIPS |
|
Text Classification (Q)
|
93% |
1764
2.37 KIPS |
|
Machine Translation (SP)
|
100% |
3406
58.7 IPS |
|
Machine Translation (HP)
|
100% |
7315
126.0 IPS |
|
Machine Translation (Q)
|
98% |
8136
140.6 IPS |