| Upload Date | August 15 2024 03:50 AM |
| Views | 18 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | Neural Engine |
| Device | Apple A15 Bionic |
| System Information | |
|---|---|
| Operating System | iOS 17.5.1 |
| 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 | 3.78 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
873
162.4 IPS |
|
|
Image Classification (HP)
|
100% |
4931
917.0 IPS |
|
|
Image Classification (Q)
|
99% |
5323
992.8 IPS |
|
|
Image Segmentation (SP)
|
100% |
589
9.55 IPS |
|
|
Image Segmentation (HP)
|
100% |
3735
60.5 IPS |
|
|
Image Segmentation (Q)
|
100% |
3706
60.1 IPS |
|
|
Pose Estimation (SP)
|
100% |
5253
6.13 IPS |
|
|
Pose Estimation (HP)
|
100% |
65665
76.6 IPS |
|
|
Pose Estimation (Q)
|
94% |
66763
78.3 IPS |
|
|
Object Detection (SP)
|
100% |
929
73.7 IPS |
|
|
Object Detection (HP)
|
99% |
6068
482.7 IPS |
|
|
Object Detection (Q)
|
93% |
7101
566.6 IPS |
|
|
Face Detection (SP)
|
100% |
1536
18.3 IPS |
|
|
Face Detection (HP)
|
100% |
9989
118.7 IPS |
|
|
Face Detection (Q)
|
100% |
11787
140.1 IPS |
|
|
Depth Estimation (SP)
|
100% |
3184
24.5 IPS |
|
|
Depth Estimation (HP)
|
99% |
37388
288.1 IPS |
|
|
Depth Estimation (Q)
|
97% |
42292
327.0 IPS |
|
|
Style Transfer (SP)
|
100% |
9096
11.7 IPS |
|
|
Style Transfer (HP)
|
100% |
105901
136.1 IPS |
|
|
Style Transfer (Q)
|
100% |
109397
140.6 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
2762
102.0 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
14292
527.8 IPS |
|
|
Image Super-Resolution (Q)
|
98% |
14367
532.3 IPS |
|
|
Text Classification (SP)
|
100% |
1003
1.34 KIPS |
|
|
Text Classification (HP)
|
100% |
2330
3.11 KIPS |
|
|
Text Classification (Q)
|
93% |
2423
3.25 KIPS |
|
|
Machine Translation (SP)
|
100% |
1324
22.8 IPS |
|
|
Machine Translation (HP)
|
100% |
2016
34.7 IPS |
|
|
Machine Translation (Q)
|
98% |
2003
34.6 IPS |