User | antinoos |
Upload Date | June 15 2025 05:46 PM |
Views | 8 |
AI Information | |
---|---|
Framework | Core ML |
Backend | GPU |
Device | Apple M2 |
System Information | |
---|---|
Operating System | iOS 18.5 |
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% |
3630
675.1 IPS |
|
Image Classification (HP)
|
100% |
3639
676.8 IPS |
|
Image Classification (Q)
|
96% |
3403
635.4 IPS |
|
Image Segmentation (SP)
|
100% |
5702
92.4 IPS |
|
Image Segmentation (HP)
|
100% |
5872
95.2 IPS |
|
Image Segmentation (Q)
|
99% |
5605
90.9 IPS |
|
Pose Estimation (SP)
|
100% |
24628
28.7 IPS |
|
Pose Estimation (HP)
|
100% |
26801
31.3 IPS |
|
Pose Estimation (Q)
|
96% |
25981
30.4 IPS |
|
Object Detection (SP)
|
100% |
3657
290.1 IPS |
|
Object Detection (HP)
|
100% |
3701
293.6 IPS |
|
Object Detection (Q)
|
92% |
3329
265.8 IPS |
|
Face Detection (SP)
|
100% |
10324
122.7 IPS |
|
Face Detection (HP)
|
100% |
12094
143.7 IPS |
|
Face Detection (Q)
|
100% |
10010
118.9 IPS |
|
Depth Estimation (SP)
|
100% |
16816
129.6 IPS |
|
Depth Estimation (HP)
|
99% |
18124
139.6 IPS |
|
Depth Estimation (Q)
|
86% |
16505
128.9 IPS |
|
Style Transfer (SP)
|
100% |
42780
55.0 IPS |
|
Style Transfer (HP)
|
100% |
49212
63.3 IPS |
|
Style Transfer (Q)
|
96% |
47787
61.7 IPS |
|
Image Super-Resolution (SP)
|
100% |
9806
362.1 IPS |
|
Image Super-Resolution (HP)
|
100% |
10282
379.7 IPS |
|
Image Super-Resolution (Q)
|
99% |
8787
324.5 IPS |
|
Text Classification (SP)
|
100% |
2297
3.07 KIPS |
|
Text Classification (HP)
|
100% |
3780
5.05 KIPS |
|
Text Classification (Q)
|
93% |
3782
5.08 KIPS |
|
Machine Translation (SP)
|
100% |
1641
28.3 IPS |
|
Machine Translation (HP)
|
100% |
1788
30.8 IPS |
|
Machine Translation (Q)
|
98% |
1474
25.5 IPS |