| User | Chris Sack |
| Upload Date | March 29 2025 07:37 PM |
| Views | 16 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | CPU |
| Device | Apple A10X Fusion |
| System Information | |
|---|---|
| Operating System | iOS 17.7.6 |
| Model | iPad Pro (10.5-inch) |
| Model ID | iPad7,3 |
| Motherboard | J207AP |
| CPU Information | |
|---|---|
| Name | Apple A10X Fusion |
| Topology | 1 Processor, 3 Cores |
| Identifier | ARM |
| Base Frequency | 2.34 GHz |
| Cluster 1 | 3 Cores |
| Memory Information | |
|---|---|
| Size | 3.91 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
299
55.7 IPS |
|
|
Image Classification (HP)
|
100% |
14
2.51 IPS |
|
|
Image Classification (Q)
|
96% |
13
2.50 IPS |
|
|
Image Segmentation (SP)
|
100% |
330
5.34 IPS |
|
|
Image Segmentation (HP)
|
100% |
19
0.30 IPS |
|
|
Image Segmentation (Q)
|
99% |
18
0.29 IPS |
|
|
Pose Estimation (SP)
|
100% |
1685
1.97 IPS |
|
|
Pose Estimation (HP)
|
100% |
20
0.02 IPS |
|
|
Pose Estimation (Q)
|
94% |
20
0.02 IPS |
|
|
Object Detection (SP)
|
100% |
331
26.3 IPS |
|
|
Object Detection (HP)
|
99% |
13
1.02 IPS |
|
|
Object Detection (Q)
|
93% |
13
1.00 IPS |
|
|
Face Detection (SP)
|
100% |
688
8.17 IPS |
|
|
Face Detection (HP)
|
100% |
44
0.53 IPS |
|
|
Face Detection (Q)
|
100% |
41
0.48 IPS |
|
|
Depth Estimation (SP)
|
100% |
829
6.39 IPS |
|
|
Depth Estimation (HP)
|
98% |
30
0.23 IPS |
|
|
Depth Estimation (Q)
|
85% |
27
0.21 IPS |
|
|
Style Transfer (SP)
|
100% |
2226
2.86 IPS |
|
|
Style Transfer (HP)
|
100% |
54
0.07 IPS |
|
|
Style Transfer (Q)
|
96% |
48
0.06 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
545
20.1 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
10
0.36 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
10
0.36 IPS |
|
|
Text Classification (SP)
|
100% |
174
232.4 IPS |
|
|
Text Classification (HP)
|
100% |
151
201.8 IPS |
|
|
Text Classification (Q)
|
93% |
154
206.2 IPS |
|
|
Machine Translation (SP)
|
100% |
431
7.42 IPS |
|
|
Machine Translation (HP)
|
96% |
25
0.43 IPS |
|
|
Machine Translation (Q)
|
98% |
26
0.45 IPS |