Upload Date | September 17 2024 10:33 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% |
1293
240.4 IPS |
|
Image Classification (HP)
|
100% |
7998
1.49 KIPS |
|
Image Classification (Q)
|
96% |
10475
1.96 KIPS |
|
Image Segmentation (SP)
|
100% |
1166
18.9 IPS |
|
Image Segmentation (HP)
|
100% |
6449
104.5 IPS |
|
Image Segmentation (Q)
|
99% |
6849
111.0 IPS |
|
Pose Estimation (SP)
|
100% |
5385
6.28 IPS |
|
Pose Estimation (HP)
|
100% |
76839
89.7 IPS |
|
Pose Estimation (Q)
|
95% |
70183
82.3 IPS |
|
Object Detection (SP)
|
100% |
1230
97.6 IPS |
|
Object Detection (HP)
|
99% |
10447
831.1 IPS |
|
Object Detection (Q)
|
91% |
11502
919.1 IPS |
|
Face Detection (SP)
|
100% |
2628
31.2 IPS |
|
Face Detection (HP)
|
100% |
21513
255.6 IPS |
|
Face Detection (Q)
|
100% |
29614
351.9 IPS |
|
Depth Estimation (SP)
|
100% |
5265
40.6 IPS |
|
Depth Estimation (HP)
|
99% |
53582
412.8 IPS |
|
Depth Estimation (Q)
|
85% |
69290
541.5 IPS |
|
Style Transfer (SP)
|
100% |
15353
19.7 IPS |
|
Style Transfer (HP)
|
100% |
149767
192.5 IPS |
|
Style Transfer (Q)
|
96% |
138592
178.8 IPS |
|
Image Super-Resolution (SP)
|
100% |
3798
140.2 IPS |
|
Image Super-Resolution (HP)
|
100% |
26712
986.4 IPS |
|
Image Super-Resolution (Q)
|
99% |
29389
1.09 KIPS |
|
Text Classification (SP)
|
100% |
2320
3.10 KIPS |
|
Text Classification (HP)
|
100% |
2276
3.04 KIPS |
|
Text Classification (Q)
|
93% |
2281
3.06 KIPS |
|
Machine Translation (SP)
|
100% |
3322
57.2 IPS |
|
Machine Translation (HP)
|
100% |
2125
36.6 IPS |
|
Machine Translation (Q)
|
98% |
2124
36.7 IPS |