Upload Date | January 06 2025 01:13 PM |
Views | 1 |
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% |
1294
240.6 IPS |
|
Image Classification (HP)
|
100% |
8342
1.55 KIPS |
|
Image Classification (Q)
|
96% |
9975
1.86 KIPS |
|
Image Segmentation (SP)
|
100% |
1265
20.5 IPS |
|
Image Segmentation (HP)
|
100% |
12089
196.0 IPS |
|
Image Segmentation (Q)
|
99% |
13134
212.9 IPS |
|
Pose Estimation (SP)
|
100% |
6191
7.22 IPS |
|
Pose Estimation (HP)
|
100% |
75354
87.9 IPS |
|
Pose Estimation (Q)
|
95% |
80454
94.3 IPS |
|
Object Detection (SP)
|
100% |
1417
112.4 IPS |
|
Object Detection (HP)
|
99% |
10824
861.1 IPS |
|
Object Detection (Q)
|
91% |
11783
941.5 IPS |
|
Face Detection (SP)
|
100% |
2625
31.2 IPS |
|
Face Detection (HP)
|
100% |
21510
255.6 IPS |
|
Face Detection (Q)
|
100% |
29478
350.3 IPS |
|
Depth Estimation (SP)
|
100% |
5261
40.5 IPS |
|
Depth Estimation (HP)
|
99% |
52543
404.8 IPS |
|
Depth Estimation (Q)
|
85% |
68377
534.3 IPS |
|
Style Transfer (SP)
|
100% |
16913
21.7 IPS |
|
Style Transfer (HP)
|
100% |
145946
187.6 IPS |
|
Style Transfer (Q)
|
96% |
140148
180.9 IPS |
|
Image Super-Resolution (SP)
|
100% |
3789
139.9 IPS |
|
Image Super-Resolution (HP)
|
100% |
26971
995.9 IPS |
|
Image Super-Resolution (Q)
|
99% |
28111
1.04 KIPS |
|
Text Classification (SP)
|
100% |
2406
3.21 KIPS |
|
Text Classification (HP)
|
100% |
2373
3.17 KIPS |
|
Text Classification (Q)
|
93% |
2407
3.23 KIPS |
|
Machine Translation (SP)
|
100% |
3327
57.3 IPS |
|
Machine Translation (HP)
|
100% |
5915
101.9 IPS |
|
Machine Translation (Q)
|
98% |
7017
121.3 IPS |