User | M91 |
Upload Date | November 15 2024 02:08 PM |
Views | 2 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A16 Bionic |
System Information | |
---|---|
Operating System | iOS 18.2 |
Model | iPhone 14 Pro Max |
Model ID | iPhone15,3 |
Motherboard | D74AP |
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 | 5.51 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1413
262.8 IPS |
|
Image Classification (HP)
|
100% |
10350
1.92 KIPS |
|
Image Classification (Q)
|
97% |
12702
2.37 KIPS |
|
Image Segmentation (SP)
|
100% |
1414
22.9 IPS |
|
Image Segmentation (HP)
|
100% |
13787
223.5 IPS |
|
Image Segmentation (Q)
|
99% |
15722
254.9 IPS |
|
Pose Estimation (SP)
|
100% |
4218
4.92 IPS |
|
Pose Estimation (HP)
|
100% |
72262
84.3 IPS |
|
Pose Estimation (Q)
|
95% |
95385
111.8 IPS |
|
Object Detection (SP)
|
100% |
1563
124.0 IPS |
|
Object Detection (HP)
|
100% |
11346
900.0 IPS |
|
Object Detection (Q)
|
91% |
13574
1.08 KIPS |
|
Face Detection (SP)
|
100% |
3076
36.5 IPS |
|
Face Detection (HP)
|
100% |
20725
246.3 IPS |
|
Face Detection (Q)
|
100% |
29156
346.4 IPS |
|
Depth Estimation (SP)
|
100% |
5908
45.5 IPS |
|
Depth Estimation (HP)
|
99% |
63718
490.9 IPS |
|
Depth Estimation (Q)
|
85% |
80315
627.9 IPS |
|
Style Transfer (SP)
|
100% |
17850
22.9 IPS |
|
Style Transfer (HP)
|
100% |
150960
194.1 IPS |
|
Style Transfer (Q)
|
96% |
157397
203.1 IPS |
|
Image Super-Resolution (SP)
|
100% |
4156
153.4 IPS |
|
Image Super-Resolution (HP)
|
100% |
26251
969.3 IPS |
|
Image Super-Resolution (Q)
|
99% |
37262
1.38 KIPS |
|
Text Classification (SP)
|
100% |
2611
3.49 KIPS |
|
Text Classification (HP)
|
100% |
2180
2.91 KIPS |
|
Text Classification (Q)
|
93% |
2440
3.28 KIPS |
|
Machine Translation (SP)
|
100% |
3383
58.3 IPS |
|
Machine Translation (HP)
|
100% |
6511
112.2 IPS |
|
Machine Translation (Q)
|
98% |
6299
108.9 IPS |