User | funskeen |
Upload Date | December 08 2024 07:43 PM |
Views | 5 |
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% |
1302
242.1 IPS |
|
Image Classification (HP)
|
100% |
8366
1.56 KIPS |
|
Image Classification (Q)
|
96% |
9483
1.77 KIPS |
|
Image Segmentation (SP)
|
100% |
1274
20.6 IPS |
|
Image Segmentation (HP)
|
100% |
6513
105.6 IPS |
|
Image Segmentation (Q)
|
99% |
7865
127.5 IPS |
|
Pose Estimation (SP)
|
100% |
6115
7.14 IPS |
|
Pose Estimation (HP)
|
100% |
74599
87.0 IPS |
|
Pose Estimation (Q)
|
95% |
79831
93.6 IPS |
|
Object Detection (SP)
|
100% |
1413
112.1 IPS |
|
Object Detection (HP)
|
99% |
10363
824.3 IPS |
|
Object Detection (Q)
|
91% |
11561
923.8 IPS |
|
Face Detection (SP)
|
100% |
2697
32.0 IPS |
|
Face Detection (HP)
|
100% |
23514
279.4 IPS |
|
Face Detection (Q)
|
100% |
29154
346.4 IPS |
|
Depth Estimation (SP)
|
100% |
5271
40.6 IPS |
|
Depth Estimation (HP)
|
99% |
54640
421.0 IPS |
|
Depth Estimation (Q)
|
85% |
64942
507.5 IPS |
|
Style Transfer (SP)
|
100% |
16812
21.6 IPS |
|
Style Transfer (HP)
|
100% |
142428
183.1 IPS |
|
Style Transfer (Q)
|
96% |
133674
172.5 IPS |
|
Image Super-Resolution (SP)
|
100% |
3773
139.3 IPS |
|
Image Super-Resolution (HP)
|
100% |
25288
933.8 IPS |
|
Image Super-Resolution (Q)
|
99% |
27469
1.01 KIPS |
|
Text Classification (SP)
|
100% |
2413
3.22 KIPS |
|
Text Classification (HP)
|
100% |
2294
3.06 KIPS |
|
Text Classification (Q)
|
93% |
2342
3.14 KIPS |
|
Machine Translation (SP)
|
100% |
3368
58.0 IPS |
|
Machine Translation (HP)
|
100% |
2121
36.5 IPS |
|
Machine Translation (Q)
|
98% |
2159
37.3 IPS |