Upload Date | September 18 2024 07:37 AM |
Views | 2 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A17 Pro |
System Information | |
---|---|
Operating System | iOS 18.1 |
Model | iPhone 15 Pro Max |
Model ID | iPhone16,2 |
Motherboard | D84AP |
CPU Information | |
---|---|
Name | Apple A17 Pro |
Topology | 1 Processor, 6 Cores |
Identifier | ARM |
Base Frequency | 3.78 GHz |
Cluster 1 | 2 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 7.48 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1650
306.9 IPS |
|
Image Classification (HP)
|
100% |
11439
2.13 KIPS |
|
Image Classification (Q)
|
97% |
15918
2.97 KIPS |
|
Image Segmentation (SP)
|
100% |
1624
26.3 IPS |
|
Image Segmentation (HP)
|
100% |
12863
208.5 IPS |
|
Image Segmentation (Q)
|
99% |
16096
260.9 IPS |
|
Pose Estimation (SP)
|
100% |
7354
8.58 IPS |
|
Pose Estimation (HP)
|
100% |
100212
116.9 IPS |
|
Pose Estimation (Q)
|
95% |
202097
236.9 IPS |
|
Object Detection (SP)
|
100% |
1729
137.1 IPS |
|
Object Detection (HP)
|
100% |
13880
1.10 KIPS |
|
Object Detection (Q)
|
91% |
19103
1.53 KIPS |
|
Face Detection (SP)
|
100% |
3051
36.3 IPS |
|
Face Detection (HP)
|
100% |
34588
411.0 IPS |
|
Face Detection (Q)
|
100% |
49038
582.7 IPS |
|
Depth Estimation (SP)
|
100% |
6741
51.9 IPS |
|
Depth Estimation (HP)
|
99% |
78448
604.4 IPS |
|
Depth Estimation (Q)
|
85% |
129403
1.01 KIPS |
|
Style Transfer (SP)
|
100% |
17734
22.8 IPS |
|
Style Transfer (HP)
|
100% |
199333
256.2 IPS |
|
Style Transfer (Q)
|
96% |
251488
324.5 IPS |
|
Image Super-Resolution (SP)
|
100% |
4535
167.5 IPS |
|
Image Super-Resolution (HP)
|
100% |
33570
1.24 KIPS |
|
Image Super-Resolution (Q)
|
99% |
55287
2.04 KIPS |
|
Text Classification (SP)
|
100% |
3170
4.23 KIPS |
|
Text Classification (HP)
|
100% |
2083
2.78 KIPS |
|
Text Classification (Q)
|
93% |
2005
2.69 KIPS |
|
Machine Translation (SP)
|
100% |
3099
53.4 IPS |
|
Machine Translation (HP)
|
100% |
6090
104.9 IPS |
|
Machine Translation (Q)
|
98% |
7511
129.8 IPS |