User | andaryjos |
Upload Date | October 06 2024 09:16 PM |
Views | 4 |
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% |
1384
257.4 IPS |
|
Image Classification (HP)
|
100% |
14360
2.67 KIPS |
|
Image Classification (Q)
|
96% |
14596
2.73 KIPS |
|
Image Segmentation (SP)
|
100% |
1528
24.8 IPS |
|
Image Segmentation (HP)
|
100% |
18903
306.4 IPS |
|
Image Segmentation (Q)
|
99% |
23604
382.6 IPS |
|
Pose Estimation (SP)
|
100% |
6892
8.04 IPS |
|
Pose Estimation (HP)
|
100% |
102023
119.0 IPS |
|
Pose Estimation (Q)
|
95% |
105132
123.2 IPS |
|
Object Detection (SP)
|
100% |
1567
124.3 IPS |
|
Object Detection (HP)
|
99% |
14982
1.19 KIPS |
|
Object Detection (Q)
|
91% |
16752
1.34 KIPS |
|
Face Detection (SP)
|
100% |
3179
37.8 IPS |
|
Face Detection (HP)
|
100% |
32022
380.5 IPS |
|
Face Detection (Q)
|
100% |
39906
474.2 IPS |
|
Depth Estimation (SP)
|
100% |
5685
43.8 IPS |
|
Depth Estimation (HP)
|
99% |
82821
638.1 IPS |
|
Depth Estimation (Q)
|
85% |
101820
795.7 IPS |
|
Style Transfer (SP)
|
100% |
18866
24.3 IPS |
|
Style Transfer (HP)
|
100% |
201311
258.8 IPS |
|
Style Transfer (Q)
|
96% |
187254
241.6 IPS |
|
Image Super-Resolution (SP)
|
100% |
4065
150.1 IPS |
|
Image Super-Resolution (HP)
|
100% |
36936
1.36 KIPS |
|
Image Super-Resolution (Q)
|
99% |
45558
1.68 KIPS |
|
Text Classification (SP)
|
100% |
2191
2.92 KIPS |
|
Text Classification (HP)
|
100% |
3740
4.99 KIPS |
|
Text Classification (Q)
|
93% |
3628
4.87 KIPS |
|
Machine Translation (SP)
|
100% |
3557
61.3 IPS |
|
Machine Translation (HP)
|
100% |
2362
40.7 IPS |
|
Machine Translation (Q)
|
98% |
2345
40.5 IPS |