Upload Date | November 11 2024 01:34 AM |
Views | 1 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A15 Bionic |
System Information | |
---|---|
Operating System | iOS 18.1 |
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
239.8 IPS |
|
Image Classification (HP)
|
100% |
8662
1.61 KIPS |
|
Image Classification (Q)
|
96% |
9759
1.82 KIPS |
|
Image Segmentation (SP)
|
100% |
1276
20.7 IPS |
|
Image Segmentation (HP)
|
100% |
12072
195.7 IPS |
|
Image Segmentation (Q)
|
99% |
13526
219.3 IPS |
|
Pose Estimation (SP)
|
100% |
6007
7.01 IPS |
|
Pose Estimation (HP)
|
100% |
77209
90.1 IPS |
|
Pose Estimation (Q)
|
95% |
80741
94.6 IPS |
|
Object Detection (SP)
|
100% |
1397
110.8 IPS |
|
Object Detection (HP)
|
99% |
11013
876.1 IPS |
|
Object Detection (Q)
|
91% |
11960
955.6 IPS |
|
Face Detection (SP)
|
100% |
2644
31.4 IPS |
|
Face Detection (HP)
|
100% |
22364
265.7 IPS |
|
Face Detection (Q)
|
100% |
32000
380.2 IPS |
|
Depth Estimation (SP)
|
100% |
5225
40.3 IPS |
|
Depth Estimation (HP)
|
99% |
53972
415.8 IPS |
|
Depth Estimation (Q)
|
85% |
67766
529.6 IPS |
|
Style Transfer (SP)
|
100% |
16885
21.7 IPS |
|
Style Transfer (HP)
|
100% |
154421
198.5 IPS |
|
Style Transfer (Q)
|
96% |
137781
177.8 IPS |
|
Image Super-Resolution (SP)
|
100% |
3783
139.7 IPS |
|
Image Super-Resolution (HP)
|
100% |
26549
980.3 IPS |
|
Image Super-Resolution (Q)
|
99% |
28209
1.04 KIPS |
|
Text Classification (SP)
|
100% |
2368
3.16 KIPS |
|
Text Classification (HP)
|
100% |
2363
3.15 KIPS |
|
Text Classification (Q)
|
93% |
2368
3.18 KIPS |
|
Machine Translation (SP)
|
100% |
3343
57.6 IPS |
|
Machine Translation (HP)
|
100% |
4436
76.4 IPS |
|
Machine Translation (Q)
|
98% |
5259
90.9 IPS |