| User | ajebulon |
| Upload Date | November 27 2024 02:11 AM |
| Views | 11 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | CPU |
| Device | Apple A15 Bionic |
| System Information | |
|---|---|
| Operating System | iOS 18.1.1 |
| 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% |
1304
242.5 IPS |
|
|
Image Classification (HP)
|
100% |
2248
418.0 IPS |
|
|
Image Classification (Q)
|
96% |
1539
287.3 IPS |
|
|
Image Segmentation (SP)
|
100% |
1286
20.9 IPS |
|
|
Image Segmentation (HP)
|
100% |
1912
31.0 IPS |
|
|
Image Segmentation (Q)
|
99% |
2352
38.1 IPS |
|
|
Pose Estimation (SP)
|
100% |
6156
7.18 IPS |
|
|
Pose Estimation (HP)
|
100% |
13383
15.6 IPS |
|
|
Pose Estimation (Q)
|
95% |
11243
13.2 IPS |
|
|
Object Detection (SP)
|
100% |
1409
111.8 IPS |
|
|
Object Detection (HP)
|
97% |
2621
208.7 IPS |
|
|
Object Detection (Q)
|
94% |
1849
147.4 IPS |
|
|
Face Detection (SP)
|
100% |
2675
31.8 IPS |
|
|
Face Detection (HP)
|
100% |
5515
65.5 IPS |
|
|
Face Detection (Q)
|
100% |
3054
36.3 IPS |
|
|
Depth Estimation (SP)
|
100% |
5298
40.8 IPS |
|
|
Depth Estimation (HP)
|
98% |
10800
83.5 IPS |
|
|
Depth Estimation (Q)
|
85% |
7296
57.0 IPS |
|
|
Style Transfer (SP)
|
100% |
16858
21.7 IPS |
|
|
Style Transfer (HP)
|
100% |
25565
32.9 IPS |
|
|
Style Transfer (Q)
|
96% |
21282
27.5 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
3762
138.9 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
4455
164.5 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
3381
124.9 IPS |
|
|
Text Classification (SP)
|
100% |
2389
3.19 KIPS |
|
|
Text Classification (HP)
|
100% |
4102
5.48 KIPS |
|
|
Text Classification (Q)
|
93% |
4094
5.49 KIPS |
|
|
Machine Translation (SP)
|
100% |
3379
58.2 IPS |
|
|
Machine Translation (HP)
|
98% |
5486
94.8 IPS |
|
|
Machine Translation (Q)
|
98% |
5563
96.1 IPS |