Upload Date | September 17 2024 01:13 PM |
Views | 2 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A17 Pro |
System Information | |
---|---|
Operating System | iOS 18.0 |
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% |
1726
320.9 IPS |
|
Image Classification (HP)
|
100% |
10727
1.99 KIPS |
|
Image Classification (Q)
|
97% |
14970
2.79 KIPS |
|
Image Segmentation (SP)
|
100% |
1617
26.2 IPS |
|
Image Segmentation (HP)
|
100% |
12884
208.9 IPS |
|
Image Segmentation (Q)
|
99% |
15996
259.3 IPS |
|
Pose Estimation (SP)
|
100% |
7800
9.10 IPS |
|
Pose Estimation (HP)
|
100% |
106797
124.6 IPS |
|
Pose Estimation (Q)
|
95% |
203924
239.0 IPS |
|
Object Detection (SP)
|
100% |
1778
141.0 IPS |
|
Object Detection (HP)
|
100% |
13570
1.08 KIPS |
|
Object Detection (Q)
|
91% |
19229
1.54 KIPS |
|
Face Detection (SP)
|
100% |
3177
37.8 IPS |
|
Face Detection (HP)
|
100% |
33677
400.2 IPS |
|
Face Detection (Q)
|
100% |
49097
583.4 IPS |
|
Depth Estimation (SP)
|
100% |
7042
54.3 IPS |
|
Depth Estimation (HP)
|
99% |
78937
608.2 IPS |
|
Depth Estimation (Q)
|
85% |
129552
1.01 KIPS |
|
Style Transfer (SP)
|
100% |
20629
26.5 IPS |
|
Style Transfer (HP)
|
100% |
202120
259.8 IPS |
|
Style Transfer (Q)
|
96% |
247123
318.9 IPS |
|
Image Super-Resolution (SP)
|
100% |
4837
178.6 IPS |
|
Image Super-Resolution (HP)
|
100% |
34704
1.28 KIPS |
|
Image Super-Resolution (Q)
|
99% |
55135
2.04 KIPS |
|
Text Classification (SP)
|
100% |
3189
4.26 KIPS |
|
Text Classification (HP)
|
100% |
3091
4.13 KIPS |
|
Text Classification (Q)
|
93% |
3123
4.19 KIPS |
|
Machine Translation (SP)
|
100% |
3112
53.6 IPS |
|
Machine Translation (HP)
|
100% |
6309
108.7 IPS |
|
Machine Translation (Q)
|
98% |
7190
124.2 IPS |