User | welduyeyet |
Upload Date | September 16 2024 06:55 AM |
Views | 5 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A17 Pro |
System Information | |
---|---|
Operating System | iOS 17.6.1 |
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 | 7.44 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1381
256.9 IPS |
|
Image Classification (HP)
|
100% |
6124
1.14 KIPS |
|
Image Classification (Q)
|
97% |
7447
1.39 KIPS |
|
Image Segmentation (SP)
|
100% |
781
12.7 IPS |
|
Image Segmentation (HP)
|
100% |
5223
84.7 IPS |
|
Image Segmentation (Q)
|
99% |
9821
159.2 IPS |
|
Pose Estimation (SP)
|
100% |
6605
7.71 IPS |
|
Pose Estimation (HP)
|
100% |
87609
102.2 IPS |
|
Pose Estimation (Q)
|
95% |
141901
166.3 IPS |
|
Object Detection (SP)
|
100% |
1461
115.9 IPS |
|
Object Detection (HP)
|
100% |
8181
648.9 IPS |
|
Object Detection (Q)
|
93% |
10064
803.0 IPS |
|
Face Detection (SP)
|
100% |
2180
25.9 IPS |
|
Face Detection (HP)
|
100% |
11207
133.2 IPS |
|
Face Detection (Q)
|
100% |
12683
150.7 IPS |
|
Depth Estimation (SP)
|
100% |
4575
35.3 IPS |
|
Depth Estimation (HP)
|
99% |
42243
325.5 IPS |
|
Depth Estimation (Q)
|
85% |
56222
439.6 IPS |
|
Style Transfer (SP)
|
100% |
11830
15.2 IPS |
|
Style Transfer (HP)
|
100% |
128155
164.7 IPS |
|
Style Transfer (Q)
|
96% |
137657
177.6 IPS |
|
Image Super-Resolution (SP)
|
100% |
3941
145.5 IPS |
|
Image Super-Resolution (HP)
|
100% |
18315
676.3 IPS |
|
Image Super-Resolution (Q)
|
99% |
25871
955.3 IPS |
|
Text Classification (SP)
|
100% |
1818
2.43 KIPS |
|
Text Classification (HP)
|
71% |
4411
6.34 KIPS |
|
Text Classification (Q)
|
69% |
4245
6.22 KIPS |
|
Machine Translation (SP)
|
100% |
1888
32.5 IPS |
|
Machine Translation (HP)
|
100% |
2352
40.5 IPS |
|
Machine Translation (Q)
|
98% |
2400
41.5 IPS |