Upload Date | January 19 2025 07:31 AM |
Views | 2 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M2 |
System Information | |
---|---|
Operating System | iOS 18.2.1 |
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% |
1315
244.6 IPS |
|
Image Classification (HP)
|
100% |
9814
1.83 KIPS |
|
Image Classification (Q)
|
96% |
15146
2.83 KIPS |
|
Image Segmentation (SP)
|
100% |
1570
25.4 IPS |
|
Image Segmentation (HP)
|
100% |
19146
310.4 IPS |
|
Image Segmentation (Q)
|
99% |
23717
384.5 IPS |
|
Pose Estimation (SP)
|
100% |
6878
8.03 IPS |
|
Pose Estimation (HP)
|
100% |
105560
123.2 IPS |
|
Pose Estimation (Q)
|
95% |
104270
122.2 IPS |
|
Object Detection (SP)
|
100% |
1573
124.8 IPS |
|
Object Detection (HP)
|
99% |
14933
1.19 KIPS |
|
Object Detection (Q)
|
91% |
17112
1.37 KIPS |
|
Face Detection (SP)
|
100% |
3180
37.8 IPS |
|
Face Detection (HP)
|
100% |
31906
379.1 IPS |
|
Face Detection (Q)
|
100% |
41138
488.8 IPS |
|
Depth Estimation (SP)
|
100% |
5710
44.0 IPS |
|
Depth Estimation (HP)
|
99% |
84598
651.8 IPS |
|
Depth Estimation (Q)
|
85% |
104382
815.7 IPS |
|
Style Transfer (SP)
|
100% |
18941
24.3 IPS |
|
Style Transfer (HP)
|
100% |
199371
256.3 IPS |
|
Style Transfer (Q)
|
96% |
190001
245.2 IPS |
|
Image Super-Resolution (SP)
|
100% |
4063
150.0 IPS |
|
Image Super-Resolution (HP)
|
100% |
36780
1.36 KIPS |
|
Image Super-Resolution (Q)
|
99% |
45084
1.66 KIPS |
|
Text Classification (SP)
|
100% |
2226
2.97 KIPS |
|
Text Classification (HP)
|
100% |
3693
4.93 KIPS |
|
Text Classification (Q)
|
93% |
3653
4.90 KIPS |
|
Machine Translation (SP)
|
100% |
3569
61.5 IPS |
|
Machine Translation (HP)
|
100% |
3887
67.0 IPS |
|
Machine Translation (Q)
|
98% |
4085
70.6 IPS |