Upload Date | November 21 2024 04:11 AM |
Views | 1 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M2 |
System Information | |
---|---|
Operating System | iOS 18.1.1 |
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% |
1387
257.9 IPS |
|
Image Classification (HP)
|
100% |
14183
2.64 KIPS |
|
Image Classification (Q)
|
96% |
14702
2.75 KIPS |
|
Image Segmentation (SP)
|
100% |
1514
24.5 IPS |
|
Image Segmentation (HP)
|
100% |
18825
305.2 IPS |
|
Image Segmentation (Q)
|
99% |
23682
383.9 IPS |
|
Pose Estimation (SP)
|
100% |
6876
8.02 IPS |
|
Pose Estimation (HP)
|
100% |
103614
120.9 IPS |
|
Pose Estimation (Q)
|
95% |
104787
122.8 IPS |
|
Object Detection (SP)
|
100% |
1563
123.9 IPS |
|
Object Detection (HP)
|
99% |
15045
1.20 KIPS |
|
Object Detection (Q)
|
91% |
17006
1.36 KIPS |
|
Face Detection (SP)
|
100% |
3128
37.2 IPS |
|
Face Detection (HP)
|
100% |
33157
394.0 IPS |
|
Face Detection (Q)
|
100% |
41483
492.9 IPS |
|
Depth Estimation (SP)
|
100% |
5673
43.7 IPS |
|
Depth Estimation (HP)
|
99% |
84547
651.4 IPS |
|
Depth Estimation (Q)
|
85% |
104596
817.4 IPS |
|
Style Transfer (SP)
|
100% |
18915
24.3 IPS |
|
Style Transfer (HP)
|
100% |
201912
259.6 IPS |
|
Style Transfer (Q)
|
96% |
189742
244.9 IPS |
|
Image Super-Resolution (SP)
|
100% |
4080
150.6 IPS |
|
Image Super-Resolution (HP)
|
100% |
38387
1.42 KIPS |
|
Image Super-Resolution (Q)
|
99% |
46733
1.73 KIPS |
|
Text Classification (SP)
|
100% |
2189
2.92 KIPS |
|
Text Classification (HP)
|
100% |
3588
4.79 KIPS |
|
Text Classification (Q)
|
93% |
3582
4.81 KIPS |
|
Machine Translation (SP)
|
100% |
3561
61.3 IPS |
|
Machine Translation (HP)
|
100% |
6737
116.0 IPS |
|
Machine Translation (Q)
|
98% |
7431
128.4 IPS |