Upload Date | January 07 2025 04:23 AM |
Views | 1 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A15 Bionic |
System Information | |
---|---|
Operating System | iOS 18.2.1 |
Model | iPad mini (6th generation) |
Model ID | iPad14,1 |
Motherboard | J310AP |
CPU Information | |
---|---|
Name | Apple A15 Bionic |
Topology | 1 Processor, 6 Cores |
Identifier | ARM |
Base Frequency | 2.92 GHz |
Cluster 1 | 2 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 3.77 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1280
238.0 IPS |
|
Image Classification (HP)
|
100% |
7927
1.47 KIPS |
|
Image Classification (Q)
|
96% |
8844
1.65 KIPS |
|
Image Segmentation (SP)
|
100% |
1273
20.6 IPS |
|
Image Segmentation (HP)
|
100% |
11311
183.4 IPS |
|
Image Segmentation (Q)
|
99% |
13101
212.4 IPS |
|
Pose Estimation (SP)
|
100% |
6216
7.25 IPS |
|
Pose Estimation (HP)
|
100% |
75586
88.2 IPS |
|
Pose Estimation (Q)
|
95% |
80288
94.1 IPS |
|
Object Detection (SP)
|
100% |
1428
113.3 IPS |
|
Object Detection (HP)
|
99% |
10345
822.9 IPS |
|
Object Detection (Q)
|
91% |
11239
898.1 IPS |
|
Face Detection (SP)
|
100% |
2660
31.6 IPS |
|
Face Detection (HP)
|
100% |
23855
283.5 IPS |
|
Face Detection (Q)
|
100% |
29093
345.7 IPS |
|
Depth Estimation (SP)
|
100% |
5283
40.7 IPS |
|
Depth Estimation (HP)
|
99% |
52786
406.7 IPS |
|
Depth Estimation (Q)
|
85% |
63129
493.3 IPS |
|
Style Transfer (SP)
|
100% |
16975
21.8 IPS |
|
Style Transfer (HP)
|
100% |
143113
184.0 IPS |
|
Style Transfer (Q)
|
96% |
137167
177.0 IPS |
|
Image Super-Resolution (SP)
|
100% |
3781
139.6 IPS |
|
Image Super-Resolution (HP)
|
100% |
26257
969.6 IPS |
|
Image Super-Resolution (Q)
|
99% |
27449
1.01 KIPS |
|
Text Classification (SP)
|
100% |
2428
3.24 KIPS |
|
Text Classification (HP)
|
100% |
1610
2.15 KIPS |
|
Text Classification (Q)
|
93% |
2391
3.21 KIPS |
|
Machine Translation (SP)
|
100% |
3400
58.6 IPS |
|
Machine Translation (HP)
|
100% |
6021
103.7 IPS |
|
Machine Translation (Q)
|
98% |
6925
119.7 IPS |