User | Ramonndafonseca |
Upload Date | October 27 2024 03:57 PM |
Views | 3 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A16 Bionic |
System Information | |
---|---|
Operating System | iOS 18.0.1 |
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% |
1456
270.7 IPS |
|
Image Classification (HP)
|
100% |
10620
1.98 KIPS |
|
Image Classification (Q)
|
97% |
12026
2.24 KIPS |
|
Image Segmentation (SP)
|
100% |
1490
24.1 IPS |
|
Image Segmentation (HP)
|
100% |
11656
188.9 IPS |
|
Image Segmentation (Q)
|
99% |
13725
222.5 IPS |
|
Pose Estimation (SP)
|
100% |
7053
8.23 IPS |
|
Pose Estimation (HP)
|
100% |
97770
114.1 IPS |
|
Pose Estimation (Q)
|
95% |
102512
120.1 IPS |
|
Object Detection (SP)
|
100% |
1590
126.1 IPS |
|
Object Detection (HP)
|
100% |
12816
1.02 KIPS |
|
Object Detection (Q)
|
91% |
14449
1.15 KIPS |
|
Face Detection (SP)
|
100% |
3063
36.4 IPS |
|
Face Detection (HP)
|
100% |
29368
349.0 IPS |
|
Face Detection (Q)
|
100% |
38368
455.9 IPS |
|
Depth Estimation (SP)
|
100% |
6260
48.2 IPS |
|
Depth Estimation (HP)
|
99% |
74589
574.7 IPS |
|
Depth Estimation (Q)
|
85% |
97703
763.9 IPS |
|
Style Transfer (SP)
|
100% |
18840
24.2 IPS |
|
Style Transfer (HP)
|
100% |
165247
212.4 IPS |
|
Style Transfer (Q)
|
96% |
167507
216.2 IPS |
|
Image Super-Resolution (SP)
|
100% |
4231
156.2 IPS |
|
Image Super-Resolution (HP)
|
100% |
31429
1.16 KIPS |
|
Image Super-Resolution (Q)
|
99% |
36258
1.34 KIPS |
|
Text Classification (SP)
|
100% |
2626
3.50 KIPS |
|
Text Classification (HP)
|
100% |
2319
3.10 KIPS |
|
Text Classification (Q)
|
93% |
2073
2.78 KIPS |
|
Machine Translation (SP)
|
100% |
3488
60.1 IPS |
|
Machine Translation (HP)
|
100% |
2430
41.9 IPS |
|
Machine Translation (Q)
|
98% |
2401
41.5 IPS |