Upload Date | December 27 2024 01:01 PM |
Views | 1 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M2 |
System Information | |
---|---|
Operating System | iOS 18.2 |
Model | iPad Pro (12.9-inch, 6th generation) |
Model ID | iPad14,5 |
Motherboard | J620AP |
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 | 7.35 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1368
254.5 IPS |
|
Image Classification (HP)
|
100% |
14346
2.67 KIPS |
|
Image Classification (Q)
|
96% |
14426
2.69 KIPS |
|
Image Segmentation (SP)
|
100% |
1542
25.0 IPS |
|
Image Segmentation (HP)
|
100% |
18924
306.8 IPS |
|
Image Segmentation (Q)
|
99% |
23783
385.5 IPS |
|
Pose Estimation (SP)
|
100% |
6870
8.02 IPS |
|
Pose Estimation (HP)
|
100% |
102348
119.4 IPS |
|
Pose Estimation (Q)
|
95% |
104504
122.5 IPS |
|
Object Detection (SP)
|
100% |
1559
123.6 IPS |
|
Object Detection (HP)
|
99% |
14905
1.19 KIPS |
|
Object Detection (Q)
|
91% |
17534
1.40 KIPS |
|
Face Detection (SP)
|
100% |
3163
37.6 IPS |
|
Face Detection (HP)
|
100% |
32144
381.9 IPS |
|
Face Detection (Q)
|
100% |
41117
488.6 IPS |
|
Depth Estimation (SP)
|
100% |
5662
43.6 IPS |
|
Depth Estimation (HP)
|
99% |
84865
653.8 IPS |
|
Depth Estimation (Q)
|
85% |
103423
808.2 IPS |
|
Style Transfer (SP)
|
100% |
18862
24.2 IPS |
|
Style Transfer (HP)
|
100% |
200242
257.4 IPS |
|
Style Transfer (Q)
|
96% |
189552
244.6 IPS |
|
Image Super-Resolution (SP)
|
100% |
4041
149.2 IPS |
|
Image Super-Resolution (HP)
|
100% |
37213
1.37 KIPS |
|
Image Super-Resolution (Q)
|
99% |
48887
1.81 KIPS |
|
Text Classification (SP)
|
100% |
2218
2.96 KIPS |
|
Text Classification (HP)
|
100% |
3644
4.86 KIPS |
|
Text Classification (Q)
|
93% |
3639
4.88 KIPS |
|
Machine Translation (SP)
|
100% |
3544
61.0 IPS |
|
Machine Translation (HP)
|
100% |
3917
67.5 IPS |
|
Machine Translation (Q)
|
98% |
4162
71.9 IPS |