Upload Date | September 14 2024 05:42 AM |
Views | 1 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A15 Bionic |
System Information | |
---|---|
Operating System | iOS 18.0 |
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% |
1290
239.9 IPS |
|
Image Classification (HP)
|
100% |
4772
887.5 IPS |
|
Image Classification (Q)
|
96% |
4961
926.4 IPS |
|
Image Segmentation (SP)
|
100% |
1246
20.2 IPS |
|
Image Segmentation (HP)
|
100% |
3924
63.6 IPS |
|
Image Segmentation (Q)
|
99% |
5414
87.8 IPS |
|
Pose Estimation (SP)
|
100% |
6135
7.16 IPS |
|
Pose Estimation (HP)
|
100% |
69778
81.4 IPS |
|
Pose Estimation (Q)
|
95% |
68763
80.6 IPS |
|
Object Detection (SP)
|
100% |
1410
111.8 IPS |
|
Object Detection (HP)
|
99% |
5809
462.1 IPS |
|
Object Detection (Q)
|
93% |
7126
568.6 IPS |
|
Face Detection (SP)
|
100% |
2625
31.2 IPS |
|
Face Detection (HP)
|
100% |
11380
135.2 IPS |
|
Face Detection (Q)
|
100% |
12275
145.9 IPS |
|
Depth Estimation (SP)
|
100% |
5260
40.5 IPS |
|
Depth Estimation (HP)
|
99% |
35928
276.8 IPS |
|
Depth Estimation (Q)
|
85% |
39156
306.0 IPS |
|
Style Transfer (SP)
|
100% |
16919
21.7 IPS |
|
Style Transfer (HP)
|
100% |
99496
127.9 IPS |
|
Style Transfer (Q)
|
96% |
86440
111.5 IPS |
|
Image Super-Resolution (SP)
|
100% |
3878
143.2 IPS |
|
Image Super-Resolution (HP)
|
100% |
15070
556.5 IPS |
|
Image Super-Resolution (Q)
|
99% |
14898
550.1 IPS |
|
Text Classification (SP)
|
100% |
2393
3.19 KIPS |
|
Text Classification (HP)
|
100% |
2438
3.25 KIPS |
|
Text Classification (Q)
|
93% |
2462
3.30 KIPS |
|
Machine Translation (SP)
|
100% |
3354
57.8 IPS |
|
Machine Translation (HP)
|
100% |
2189
37.7 IPS |
|
Machine Translation (Q)
|
98% |
2179
37.7 IPS |