User | springkim |
Upload Date | April 18 2025 04:41 PM |
Views | 2 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A15 Bionic |
System Information | |
---|---|
Operating System | iOS 17.4.1 |
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 | 3.78 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
914
169.9 IPS |
|
Image Classification (HP)
|
100% |
3896
724.5 IPS |
|
Image Classification (Q)
|
96% |
4524
844.9 IPS |
|
Image Segmentation (SP)
|
100% |
601
9.75 IPS |
|
Image Segmentation (HP)
|
100% |
3645
59.1 IPS |
|
Image Segmentation (Q)
|
99% |
5509
89.3 IPS |
|
Pose Estimation (SP)
|
100% |
5380
6.28 IPS |
|
Pose Estimation (HP)
|
100% |
63485
74.1 IPS |
|
Pose Estimation (Q)
|
95% |
66973
78.5 IPS |
|
Object Detection (SP)
|
100% |
951
75.4 IPS |
|
Object Detection (HP)
|
99% |
5321
423.3 IPS |
|
Object Detection (Q)
|
93% |
6014
479.9 IPS |
|
Face Detection (SP)
|
100% |
1615
19.2 IPS |
|
Face Detection (HP)
|
100% |
9738
115.7 IPS |
|
Face Detection (Q)
|
100% |
11369
135.1 IPS |
|
Depth Estimation (SP)
|
100% |
3217
24.8 IPS |
|
Depth Estimation (HP)
|
99% |
34452
265.4 IPS |
|
Depth Estimation (Q)
|
85% |
40892
319.6 IPS |
|
Style Transfer (SP)
|
100% |
9666
12.4 IPS |
|
Style Transfer (HP)
|
100% |
96061
123.5 IPS |
|
Style Transfer (Q)
|
95% |
75912
98.0 IPS |
|
Image Super-Resolution (SP)
|
100% |
2844
105.0 IPS |
|
Image Super-Resolution (HP)
|
100% |
13441
496.3 IPS |
|
Image Super-Resolution (Q)
|
99% |
14815
547.1 IPS |
|
Text Classification (SP)
|
100% |
990
1.32 KIPS |
|
Text Classification (HP)
|
100% |
2467
3.29 KIPS |
|
Text Classification (Q)
|
93% |
2559
3.43 KIPS |
|
Machine Translation (SP)
|
100% |
1342
23.1 IPS |
|
Machine Translation (HP)
|
100% |
2108
36.3 IPS |
|
Machine Translation (Q)
|
98% |
2135
36.9 IPS |