User | mvodya |
Upload Date | February 03 2025 07:59 AM |
Views | 6 |
AI Information | |
---|---|
Framework | Core ML |
Backend | GPU |
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% |
3656
679.9 IPS |
|
Image Classification (HP)
|
100% |
3612
671.7 IPS |
|
Image Classification (Q)
|
97% |
3062
571.4 IPS |
|
Image Segmentation (SP)
|
100% |
4046
65.6 IPS |
|
Image Segmentation (HP)
|
100% |
5018
81.3 IPS |
|
Image Segmentation (Q)
|
99% |
5100
82.7 IPS |
|
Pose Estimation (SP)
|
100% |
24706
28.8 IPS |
|
Pose Estimation (HP)
|
100% |
26300
30.7 IPS |
|
Pose Estimation (Q)
|
95% |
24503
28.7 IPS |
|
Object Detection (SP)
|
100% |
3677
291.7 IPS |
|
Object Detection (HP)
|
100% |
3690
292.7 IPS |
|
Object Detection (Q)
|
91% |
3049
243.6 IPS |
|
Face Detection (SP)
|
100% |
10404
123.6 IPS |
|
Face Detection (HP)
|
100% |
11931
141.8 IPS |
|
Face Detection (Q)
|
100% |
8342
99.1 IPS |
|
Depth Estimation (SP)
|
100% |
16735
128.9 IPS |
|
Depth Estimation (HP)
|
99% |
17894
137.9 IPS |
|
Depth Estimation (Q)
|
85% |
14845
116.0 IPS |
|
Style Transfer (SP)
|
100% |
42750
55.0 IPS |
|
Style Transfer (HP)
|
100% |
48546
62.4 IPS |
|
Style Transfer (Q)
|
96% |
45504
58.7 IPS |
|
Image Super-Resolution (SP)
|
100% |
9780
361.1 IPS |
|
Image Super-Resolution (HP)
|
100% |
10019
370.0 IPS |
|
Image Super-Resolution (Q)
|
99% |
7981
294.7 IPS |
|
Text Classification (SP)
|
100% |
2265
3.02 KIPS |
|
Text Classification (HP)
|
100% |
3650
4.87 KIPS |
|
Text Classification (Q)
|
93% |
3660
4.91 KIPS |
|
Machine Translation (SP)
|
100% |
1175
20.2 IPS |
|
Machine Translation (HP)
|
100% |
1247
21.5 IPS |
|
Machine Translation (Q)
|
98% |
1300
22.5 IPS |