Upload Date | December 26 2024 12:02 PM |
Views | 1 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M2 |
System Information | |
---|---|
Operating System | iOS 18.2 |
Model | iPad Pro (11-inch, 4th generation) |
Model ID | iPad14,3 |
Motherboard | J617AP |
CPU Information | |
---|---|
Name | Apple M2 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM |
Base Frequency | 3.49 GHz |
Cluster 1 | 4 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 7.37 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1362
253.2 IPS |
|
Image Classification (HP)
|
100% |
14219
2.64 KIPS |
|
Image Classification (Q)
|
96% |
15070
2.81 KIPS |
|
Image Segmentation (SP)
|
100% |
1521
24.7 IPS |
|
Image Segmentation (HP)
|
100% |
19041
308.7 IPS |
|
Image Segmentation (Q)
|
99% |
23812
386.0 IPS |
|
Pose Estimation (SP)
|
100% |
6890
8.04 IPS |
|
Pose Estimation (HP)
|
100% |
105335
122.9 IPS |
|
Pose Estimation (Q)
|
95% |
104864
122.9 IPS |
|
Object Detection (SP)
|
100% |
1565
124.1 IPS |
|
Object Detection (HP)
|
99% |
15079
1.20 KIPS |
|
Object Detection (Q)
|
91% |
16932
1.35 KIPS |
|
Face Detection (SP)
|
100% |
3177
37.8 IPS |
|
Face Detection (HP)
|
100% |
32330
384.2 IPS |
|
Face Detection (Q)
|
100% |
41577
494.0 IPS |
|
Depth Estimation (SP)
|
100% |
5714
44.0 IPS |
|
Depth Estimation (HP)
|
99% |
85626
659.7 IPS |
|
Depth Estimation (Q)
|
85% |
107318
838.6 IPS |
|
Style Transfer (SP)
|
100% |
18910
24.3 IPS |
|
Style Transfer (HP)
|
100% |
201151
258.6 IPS |
|
Style Transfer (Q)
|
96% |
188656
243.5 IPS |
|
Image Super-Resolution (SP)
|
100% |
4036
149.0 IPS |
|
Image Super-Resolution (HP)
|
100% |
38734
1.43 KIPS |
|
Image Super-Resolution (Q)
|
99% |
48588
1.79 KIPS |
|
Text Classification (SP)
|
100% |
2166
2.89 KIPS |
|
Text Classification (HP)
|
100% |
3660
4.89 KIPS |
|
Text Classification (Q)
|
93% |
3604
4.84 KIPS |
|
Machine Translation (SP)
|
100% |
3547
61.1 IPS |
|
Machine Translation (HP)
|
100% |
4001
68.9 IPS |
|
Machine Translation (Q)
|
98% |
4114
71.1 IPS |