User | mvodya |
Upload Date | February 03 2025 08:02 AM |
Views | 8 |
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% |
1369
254.7 IPS |
|
Image Classification (HP)
|
100% |
14690
2.73 KIPS |
|
Image Classification (Q)
|
96% |
14949
2.79 KIPS |
|
Image Segmentation (SP)
|
100% |
1536
24.9 IPS |
|
Image Segmentation (HP)
|
100% |
18752
304.0 IPS |
|
Image Segmentation (Q)
|
99% |
23355
378.6 IPS |
|
Pose Estimation (SP)
|
100% |
6886
8.03 IPS |
|
Pose Estimation (HP)
|
100% |
102122
119.2 IPS |
|
Pose Estimation (Q)
|
95% |
104532
122.5 IPS |
|
Object Detection (SP)
|
100% |
1565
124.1 IPS |
|
Object Detection (HP)
|
99% |
14932
1.19 KIPS |
|
Object Detection (Q)
|
91% |
16265
1.30 KIPS |
|
Face Detection (SP)
|
100% |
3165
37.6 IPS |
|
Face Detection (HP)
|
100% |
32272
383.5 IPS |
|
Face Detection (Q)
|
100% |
41538
493.6 IPS |
|
Depth Estimation (SP)
|
100% |
5648
43.5 IPS |
|
Depth Estimation (HP)
|
99% |
84046
647.5 IPS |
|
Depth Estimation (Q)
|
85% |
106478
832.1 IPS |
|
Style Transfer (SP)
|
100% |
18988
24.4 IPS |
|
Style Transfer (HP)
|
100% |
201823
259.4 IPS |
|
Style Transfer (Q)
|
96% |
190007
245.2 IPS |
|
Image Super-Resolution (SP)
|
100% |
4064
150.1 IPS |
|
Image Super-Resolution (HP)
|
100% |
39663
1.46 KIPS |
|
Image Super-Resolution (Q)
|
99% |
45154
1.67 KIPS |
|
Text Classification (SP)
|
100% |
2259
3.02 KIPS |
|
Text Classification (HP)
|
100% |
3656
4.88 KIPS |
|
Text Classification (Q)
|
93% |
3644
4.89 KIPS |
|
Machine Translation (SP)
|
100% |
3531
60.8 IPS |
|
Machine Translation (HP)
|
100% |
3928
67.7 IPS |
|
Machine Translation (Q)
|
98% |
4177
72.2 IPS |