Upload Date | December 26 2024 01:41 PM |
Views | 1 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M4 |
System Information | |
---|---|
Operating System | iOS 18.2 |
Model | iPad Pro 13-inch (M4) |
Model ID | iPad16,6 |
Motherboard | J721AP |
CPU Information | |
---|---|
Name | Apple M4 |
Topology | 1 Processor, 10 Cores |
Identifier | ARM |
Base Frequency | 4.41 GHz |
Cluster 1 | 4 Cores |
Cluster 2 | 6 Cores |
Memory Information | |
---|---|
Size | 15.06 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1990
370.1 IPS |
|
Image Classification (HP)
|
100% |
17077
3.18 KIPS |
|
Image Classification (Q)
|
97% |
23927
4.47 KIPS |
|
Image Segmentation (SP)
|
100% |
2137
34.6 IPS |
|
Image Segmentation (HP)
|
100% |
21869
354.5 IPS |
|
Image Segmentation (Q)
|
99% |
30125
488.3 IPS |
|
Pose Estimation (SP)
|
100% |
10028
11.7 IPS |
|
Pose Estimation (HP)
|
100% |
123347
143.9 IPS |
|
Pose Estimation (Q)
|
95% |
232436
272.4 IPS |
|
Object Detection (SP)
|
100% |
2241
177.7 IPS |
|
Object Detection (HP)
|
100% |
18124
1.44 KIPS |
|
Object Detection (Q)
|
91% |
26110
2.09 KIPS |
|
Face Detection (SP)
|
100% |
3959
47.0 IPS |
|
Face Detection (HP)
|
100% |
41845
497.2 IPS |
|
Face Detection (Q)
|
100% |
62571
743.5 IPS |
|
Depth Estimation (SP)
|
100% |
8273
63.7 IPS |
|
Depth Estimation (HP)
|
99% |
98281
757.2 IPS |
|
Depth Estimation (Q)
|
85% |
169337
1.32 KIPS |
|
Style Transfer (SP)
|
100% |
24925
32.0 IPS |
|
Style Transfer (HP)
|
100% |
234615
301.6 IPS |
|
Style Transfer (Q)
|
96% |
295631
381.5 IPS |
|
Image Super-Resolution (SP)
|
100% |
5842
215.7 IPS |
|
Image Super-Resolution (HP)
|
100% |
48566
1.79 KIPS |
|
Image Super-Resolution (Q)
|
99% |
82563
3.05 KIPS |
|
Text Classification (SP)
|
100% |
2959
3.95 KIPS |
|
Text Classification (HP)
|
100% |
5884
7.85 KIPS |
|
Text Classification (Q)
|
93% |
7323
9.83 KIPS |
|
Machine Translation (SP)
|
100% |
3867
66.6 IPS |
|
Machine Translation (HP)
|
100% |
16186
278.8 IPS |
|
Machine Translation (Q)
|
98% |
17739
306.6 IPS |