User | frank_m_h_jaeger |
Upload Date | March 12 2025 07:24 PM |
Views | 7 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | ARM |
System Information | |
---|---|
Operating System | iOS 18.3.2 |
Model | iPad15,7 |
Model ID | iPad15,7 |
Motherboard | J481AP |
CPU Information | |
---|---|
Name | ARM |
Topology | 1 Processor, 5 Cores |
Identifier | ARM |
Base Frequency | 3.43 GHz |
Cluster 1 | 2 Cores |
Cluster 2 | 3 Cores |
Memory Information | |
---|---|
Size | 5.78 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1440
267.8 IPS |
|
Image Classification (HP)
|
100% |
10627
1.98 KIPS |
|
Image Classification (Q)
|
97% |
12353
2.31 KIPS |
|
Image Segmentation (SP)
|
100% |
1464
23.7 IPS |
|
Image Segmentation (HP)
|
100% |
14923
241.9 IPS |
|
Image Segmentation (Q)
|
99% |
18216
295.3 IPS |
|
Pose Estimation (SP)
|
100% |
6858
8.00 IPS |
|
Pose Estimation (HP)
|
100% |
95636
111.6 IPS |
|
Pose Estimation (Q)
|
95% |
103462
121.3 IPS |
|
Object Detection (SP)
|
100% |
1607
127.5 IPS |
|
Object Detection (HP)
|
100% |
12789
1.01 KIPS |
|
Object Detection (Q)
|
91% |
14887
1.19 KIPS |
|
Face Detection (SP)
|
100% |
3256
38.7 IPS |
|
Face Detection (HP)
|
100% |
30418
361.4 IPS |
|
Face Detection (Q)
|
100% |
39830
473.3 IPS |
|
Depth Estimation (SP)
|
100% |
6173
47.6 IPS |
|
Depth Estimation (HP)
|
99% |
76155
586.7 IPS |
|
Depth Estimation (Q)
|
85% |
97175
759.8 IPS |
|
Style Transfer (SP)
|
100% |
18981
24.4 IPS |
|
Style Transfer (HP)
|
100% |
173371
222.9 IPS |
|
Style Transfer (Q)
|
96% |
178792
230.7 IPS |
|
Image Super-Resolution (SP)
|
100% |
4172
154.1 IPS |
|
Image Super-Resolution (HP)
|
100% |
32798
1.21 KIPS |
|
Image Super-Resolution (Q)
|
99% |
36741
1.36 KIPS |
|
Text Classification (SP)
|
100% |
2622
3.50 KIPS |
|
Text Classification (HP)
|
100% |
2003
2.67 KIPS |
|
Text Classification (Q)
|
93% |
1969
2.64 KIPS |
|
Machine Translation (SP)
|
100% |
3415
58.8 IPS |
|
Machine Translation (HP)
|
100% |
7499
129.2 IPS |
|
Machine Translation (Q)
|
98% |
8139
140.7 IPS |