| User | Stephen_L |
| Upload Date | August 26 2024 10:38 AM |
| Views | 2 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | GPU |
| Device | Apple A13 Bionic |
| System Information | |
|---|---|
| Operating System | iOS 17.6.1 |
| Model | iPhone 11 |
| Model ID | iPhone12,1 |
| Motherboard | N104AP |
| CPU Information | |
|---|---|
| Name | Apple A13 Bionic |
| Topology | 1 Processor, 6 Cores |
| Identifier | ARM |
| Base Frequency | 2.66 GHz |
| Cluster 1 | 2 Cores |
| Cluster 2 | 4 Cores |
| Memory Information | |
|---|---|
| Size | 3.76 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
301
56.0 IPS |
|
|
Image Classification (HP)
|
100% |
358
66.5 IPS |
|
|
Image Classification (Q)
|
99% |
369
68.9 IPS |
|
|
Image Segmentation (SP)
|
100% |
311
5.05 IPS |
|
|
Image Segmentation (HP)
|
100% |
345
5.59 IPS |
|
|
Image Segmentation (Q)
|
100% |
351
5.69 IPS |
|
|
Pose Estimation (SP)
|
100% |
1898
2.21 IPS |
|
|
Pose Estimation (HP)
|
100% |
2416
2.82 IPS |
|
|
Pose Estimation (Q)
|
96% |
1240
1.45 IPS |
|
|
Object Detection (SP)
|
100% |
631
50.0 IPS |
|
|
Object Detection (HP)
|
100% |
625
49.6 IPS |
|
|
Object Detection (Q)
|
94% |
160
12.7 IPS |
|
|
Face Detection (SP)
|
100% |
2504
29.8 IPS |
|
|
Face Detection (HP)
|
100% |
2752
32.7 IPS |
|
|
Face Detection (Q)
|
100% |
185
2.20 IPS |
|
|
Depth Estimation (SP)
|
100% |
2236
17.2 IPS |
|
|
Depth Estimation (HP)
|
99% |
2320
17.9 IPS |
|
|
Depth Estimation (Q)
|
97% |
2166
16.8 IPS |
|
|
Style Transfer (SP)
|
100% |
3703
4.76 IPS |
|
|
Style Transfer (HP)
|
100% |
4494
5.78 IPS |
|
|
Style Transfer (Q)
|
100% |
4274
5.49 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
659
24.3 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
911
33.6 IPS |
|
|
Image Super-Resolution (Q)
|
98% |
309
11.4 IPS |
|
|
Text Classification (SP)
|
100% |
197
262.5 IPS |
|
|
Text Classification (HP)
|
100% |
183
244.9 IPS |
|
|
Text Classification (Q)
|
93% |
263
353.4 IPS |
|
|
Machine Translation (SP)
|
100% |
285
4.92 IPS |
|
|
Machine Translation (HP)
|
100% |
248
4.27 IPS |
|
|
Machine Translation (Q)
|
98% |
243
4.21 IPS |