User | mamiyoshi |
Upload Date | March 18 2025 10:19 AM |
Views | 9 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A18 |
System Information | |
---|---|
Operating System | iOS 18.3.1 |
Model | iPhone 16 |
Model ID | iPhone17,3 |
Motherboard | D47AP |
CPU Information | |
---|---|
Name | Apple A18 |
Topology | 1 Processor, 6 Cores |
Identifier | ARM |
Base Frequency | 4.04 GHz |
Cluster 1 | 2 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 7.51 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1958
364.2 IPS |
|
Image Classification (HP)
|
100% |
15258
2.84 KIPS |
|
Image Classification (Q)
|
97% |
19839
3.70 KIPS |
|
Image Segmentation (SP)
|
100% |
1794
29.1 IPS |
|
Image Segmentation (HP)
|
100% |
18161
294.4 IPS |
|
Image Segmentation (Q)
|
99% |
23800
385.8 IPS |
|
Pose Estimation (SP)
|
100% |
8693
10.1 IPS |
|
Pose Estimation (HP)
|
100% |
154148
179.9 IPS |
|
Pose Estimation (Q)
|
95% |
294692
345.4 IPS |
|
Object Detection (SP)
|
100% |
2115
167.8 IPS |
|
Object Detection (HP)
|
100% |
16323
1.29 KIPS |
|
Object Detection (Q)
|
91% |
22217
1.78 KIPS |
|
Face Detection (SP)
|
100% |
3319
39.4 IPS |
|
Face Detection (HP)
|
100% |
40309
479.0 IPS |
|
Face Detection (Q)
|
100% |
56007
665.5 IPS |
|
Depth Estimation (SP)
|
100% |
7727
59.5 IPS |
|
Depth Estimation (HP)
|
99% |
95588
736.5 IPS |
|
Depth Estimation (Q)
|
85% |
159850
1.25 KIPS |
|
Style Transfer (SP)
|
100% |
23206
29.8 IPS |
|
Style Transfer (HP)
|
100% |
244747
314.6 IPS |
|
Style Transfer (Q)
|
96% |
302063
389.8 IPS |
|
Image Super-Resolution (SP)
|
100% |
5548
204.8 IPS |
|
Image Super-Resolution (HP)
|
100% |
50602
1.87 KIPS |
|
Image Super-Resolution (Q)
|
99% |
83964
3.10 KIPS |
|
Text Classification (SP)
|
100% |
3428
4.58 KIPS |
|
Text Classification (HP)
|
100% |
4813
6.42 KIPS |
|
Text Classification (Q)
|
93% |
3392
4.55 KIPS |
|
Machine Translation (SP)
|
100% |
3502
60.3 IPS |
|
Machine Translation (HP)
|
100% |
9673
166.6 IPS |
|
Machine Translation (Q)
|
98% |
11530
199.3 IPS |