Upload Date | January 02 2025 11:51 AM |
Views | 2 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A15 Bionic |
System Information | |
---|---|
Operating System | iOS 18.1.1 |
Model | iPad mini (6th generation) |
Model ID | iPad14,2 |
Motherboard | J311AP |
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% |
1305
242.6 IPS |
|
Image Classification (HP)
|
100% |
8575
1.59 KIPS |
|
Image Classification (Q)
|
96% |
9219
1.72 KIPS |
|
Image Segmentation (SP)
|
100% |
1269
20.6 IPS |
|
Image Segmentation (HP)
|
100% |
11899
192.9 IPS |
|
Image Segmentation (Q)
|
99% |
12604
204.3 IPS |
|
Pose Estimation (SP)
|
100% |
6007
7.01 IPS |
|
Pose Estimation (HP)
|
100% |
77203
90.1 IPS |
|
Pose Estimation (Q)
|
95% |
80925
94.8 IPS |
|
Object Detection (SP)
|
100% |
1410
111.8 IPS |
|
Object Detection (HP)
|
99% |
10929
869.4 IPS |
|
Object Detection (Q)
|
91% |
11699
934.8 IPS |
|
Face Detection (SP)
|
100% |
2661
31.6 IPS |
|
Face Detection (HP)
|
100% |
23829
283.1 IPS |
|
Face Detection (Q)
|
100% |
29993
356.4 IPS |
|
Depth Estimation (SP)
|
100% |
5320
41.0 IPS |
|
Depth Estimation (HP)
|
99% |
57204
440.7 IPS |
|
Depth Estimation (Q)
|
85% |
67231
525.4 IPS |
|
Style Transfer (SP)
|
100% |
16855
21.7 IPS |
|
Style Transfer (HP)
|
100% |
150633
193.6 IPS |
|
Style Transfer (Q)
|
96% |
138257
178.4 IPS |
|
Image Super-Resolution (SP)
|
100% |
3869
142.9 IPS |
|
Image Super-Resolution (HP)
|
100% |
26804
989.7 IPS |
|
Image Super-Resolution (Q)
|
99% |
29146
1.08 KIPS |
|
Text Classification (SP)
|
100% |
2406
3.21 KIPS |
|
Text Classification (HP)
|
100% |
2504
3.34 KIPS |
|
Text Classification (Q)
|
93% |
2466
3.31 KIPS |
|
Machine Translation (SP)
|
100% |
3375
58.1 IPS |
|
Machine Translation (HP)
|
100% |
4462
76.9 IPS |
|
Machine Translation (Q)
|
98% |
5434
93.9 IPS |