| User | frank_m_h_jaeger |
| Upload Date | August 18 2024 09:02 PM |
| Views | 19 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | GPU |
| Device | Apple A10 Fusion |
| System Information | |
|---|---|
| Operating System | iOS 17.6.1 |
| Model | iPad (6th generation) |
| Model ID | iPad7,5 |
| Motherboard | J71bAP |
| CPU Information | |
|---|---|
| Name | Apple A10 Fusion |
| Topology | 1 Processor, 2 Cores |
| Identifier | ARM |
| Base Frequency | 2.32 GHz |
| Cluster 1 | 2 Cores |
| Memory Information | |
|---|---|
| Size | 1.93 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
196
36.5 IPS |
|
|
Image Classification (HP)
|
100% |
178
33.2 IPS |
|
|
Image Classification (Q)
|
99% |
178
33.2 IPS |
|
|
Image Segmentation (SP)
|
100% |
158
2.56 IPS |
|
|
Image Segmentation (HP)
|
100% |
160
2.60 IPS |
|
|
Image Segmentation (Q)
|
100% |
161
2.61 IPS |
|
|
Pose Estimation (SP)
|
100% |
905
1.06 IPS |
|
|
Pose Estimation (HP)
|
100% |
861
1.00 IPS |
|
|
Pose Estimation (Q)
|
94% |
624
0.73 IPS |
|
|
Object Detection (SP)
|
100% |
174
13.8 IPS |
|
|
Object Detection (HP)
|
100% |
159
12.6 IPS |
|
|
Object Detection (Q)
|
92% |
99
7.93 IPS |
|
|
Face Detection (SP)
|
100% |
364
4.33 IPS |
|
|
Face Detection (HP)
|
100% |
369
4.39 IPS |
|
|
Face Detection (Q)
|
100% |
160
1.90 IPS |
|
|
Depth Estimation (SP)
|
100% |
490
3.78 IPS |
|
|
Depth Estimation (HP)
|
99% |
454
3.50 IPS |
|
|
Depth Estimation (Q)
|
97% |
445
3.44 IPS |
|
|
Style Transfer (SP)
|
100% |
1422
1.83 IPS |
|
|
Style Transfer (HP)
|
100% |
1372
1.76 IPS |
|
|
Style Transfer (Q)
|
100% |
1336
1.72 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
389
14.4 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
388
14.3 IPS |
|
|
Image Super-Resolution (Q)
|
98% |
210
7.79 IPS |
|
|
Text Classification (SP)
|
100% |
145
194.2 IPS |
|
|
Text Classification (HP)
|
100% |
122
162.7 IPS |
|
|
Text Classification (Q)
|
93% |
130
174.7 IPS |
|
|
Machine Translation (SP)
|
100% |
259
4.46 IPS |
|
|
Machine Translation (HP)
|
100% |
220
3.79 IPS |
|
|
Machine Translation (Q)
|
98% |
223
3.85 IPS |