Upload Date | November 18 2024 10:25 PM |
Views | 1 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M2 |
System Information | |
---|---|
Operating System | iOS 18.1 |
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% |
1355
252.0 IPS |
|
Image Classification (HP)
|
100% |
14101
2.62 KIPS |
|
Image Classification (Q)
|
96% |
15656
2.92 KIPS |
|
Image Segmentation (SP)
|
100% |
1564
25.4 IPS |
|
Image Segmentation (HP)
|
100% |
19086
309.4 IPS |
|
Image Segmentation (Q)
|
99% |
23830
386.3 IPS |
|
Pose Estimation (SP)
|
100% |
6791
7.92 IPS |
|
Pose Estimation (HP)
|
100% |
106186
123.9 IPS |
|
Pose Estimation (Q)
|
95% |
105388
123.5 IPS |
|
Object Detection (SP)
|
100% |
1531
121.5 IPS |
|
Object Detection (HP)
|
99% |
15152
1.21 KIPS |
|
Object Detection (Q)
|
91% |
17926
1.43 KIPS |
|
Face Detection (SP)
|
100% |
3149
37.4 IPS |
|
Face Detection (HP)
|
100% |
33323
395.9 IPS |
|
Face Detection (Q)
|
100% |
39855
473.6 IPS |
|
Depth Estimation (SP)
|
100% |
5532
42.6 IPS |
|
Depth Estimation (HP)
|
99% |
73733
568.1 IPS |
|
Depth Estimation (Q)
|
85% |
108821
850.4 IPS |
|
Style Transfer (SP)
|
100% |
18907
24.3 IPS |
|
Style Transfer (HP)
|
100% |
198827
255.6 IPS |
|
Style Transfer (Q)
|
96% |
192017
247.8 IPS |
|
Image Super-Resolution (SP)
|
100% |
4126
152.3 IPS |
|
Image Super-Resolution (HP)
|
100% |
39963
1.48 KIPS |
|
Image Super-Resolution (Q)
|
99% |
46131
1.70 KIPS |
|
Text Classification (SP)
|
100% |
2222
2.97 KIPS |
|
Text Classification (HP)
|
100% |
3742
5.00 KIPS |
|
Text Classification (Q)
|
93% |
3764
5.05 KIPS |
|
Machine Translation (SP)
|
100% |
3578
61.6 IPS |
|
Machine Translation (HP)
|
100% |
5677
97.8 IPS |
|
Machine Translation (Q)
|
98% |
6111
105.6 IPS |