Upload Date | January 02 2025 11:09 PM |
Views | 5 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A15 Bionic |
System Information | |
---|---|
Operating System | iOS 18.2 |
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% |
1293
240.5 IPS |
|
Image Classification (HP)
|
100% |
7888
1.47 KIPS |
|
Image Classification (Q)
|
96% |
9441
1.76 KIPS |
|
Image Segmentation (SP)
|
100% |
1267
20.5 IPS |
|
Image Segmentation (HP)
|
100% |
11326
183.6 IPS |
|
Image Segmentation (Q)
|
99% |
12361
200.4 IPS |
|
Pose Estimation (SP)
|
100% |
6226
7.26 IPS |
|
Pose Estimation (HP)
|
100% |
75798
88.4 IPS |
|
Pose Estimation (Q)
|
95% |
80407
94.2 IPS |
|
Object Detection (SP)
|
100% |
1425
113.1 IPS |
|
Object Detection (HP)
|
99% |
10373
825.1 IPS |
|
Object Detection (Q)
|
91% |
11675
932.9 IPS |
|
Face Detection (SP)
|
100% |
2650
31.5 IPS |
|
Face Detection (HP)
|
100% |
22806
271.0 IPS |
|
Face Detection (Q)
|
100% |
31304
372.0 IPS |
|
Depth Estimation (SP)
|
100% |
5251
40.5 IPS |
|
Depth Estimation (HP)
|
99% |
52596
405.2 IPS |
|
Depth Estimation (Q)
|
85% |
66027
516.0 IPS |
|
Style Transfer (SP)
|
100% |
17021
21.9 IPS |
|
Style Transfer (HP)
|
100% |
150195
193.1 IPS |
|
Style Transfer (Q)
|
96% |
135458
174.8 IPS |
|
Image Super-Resolution (SP)
|
100% |
3794
140.1 IPS |
|
Image Super-Resolution (HP)
|
100% |
26649
984.0 IPS |
|
Image Super-Resolution (Q)
|
99% |
28414
1.05 KIPS |
|
Text Classification (SP)
|
100% |
2444
3.26 KIPS |
|
Text Classification (HP)
|
100% |
2435
3.25 KIPS |
|
Text Classification (Q)
|
93% |
2417
3.24 KIPS |
|
Machine Translation (SP)
|
100% |
3408
58.7 IPS |
|
Machine Translation (HP)
|
100% |
5983
103.1 IPS |
|
Machine Translation (Q)
|
98% |
6840
118.2 IPS |