| User | ju83 |
| Upload Date | September 20 2024 05:41 AM |
| Views | 10 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | GPU |
| Device | Apple A12 Bionic |
| System Information | |
|---|---|
| Operating System | iOS 18.0 |
| Model | iPhone XS |
| Model ID | iPhone11,2 |
| Motherboard | D321AP |
| CPU Information | |
|---|---|
| Name | Apple A12 Bionic |
| Topology | 1 Processor, 6 Cores |
| Identifier | ARM |
| Base Frequency | 2.49 GHz |
| Cluster 1 | 2 Cores |
| Cluster 2 | 4 Cores |
| Memory Information | |
|---|---|
| Size | 3.69 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
270
50.3 IPS |
|
|
Image Classification (HP)
|
100% |
306
56.9 IPS |
|
|
Image Classification (Q)
|
96% |
131
24.4 IPS |
|
|
Image Segmentation (SP)
|
100% |
223
3.62 IPS |
|
|
Image Segmentation (HP)
|
100% |
248
4.02 IPS |
|
|
Image Segmentation (Q)
|
99% |
179
2.89 IPS |
|
|
Pose Estimation (SP)
|
100% |
1258
1.47 IPS |
|
|
Pose Estimation (HP)
|
100% |
1257
1.47 IPS |
|
|
Pose Estimation (Q)
|
96% |
686
0.80 IPS |
|
|
Object Detection (SP)
|
100% |
517
41.0 IPS |
|
|
Object Detection (HP)
|
100% |
556
44.1 IPS |
|
|
Object Detection (Q)
|
92% |
122
9.75 IPS |
|
|
Face Detection (SP)
|
100% |
1960
23.3 IPS |
|
|
Face Detection (HP)
|
100% |
2003
23.8 IPS |
|
|
Face Detection (Q)
|
100% |
218
2.59 IPS |
|
|
Depth Estimation (SP)
|
100% |
1670
12.9 IPS |
|
|
Depth Estimation (HP)
|
99% |
1647
12.7 IPS |
|
|
Depth Estimation (Q)
|
86% |
418
3.26 IPS |
|
|
Style Transfer (SP)
|
100% |
4006
5.15 IPS |
|
|
Style Transfer (HP)
|
100% |
3068
3.94 IPS |
|
|
Style Transfer (Q)
|
96% |
1462
1.89 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
774
28.6 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
818
30.2 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
259
9.57 IPS |
|
|
Text Classification (SP)
|
100% |
154
205.9 IPS |
|
|
Text Classification (HP)
|
100% |
203
270.7 IPS |
|
|
Text Classification (Q)
|
93% |
201
270.2 IPS |
|
|
Machine Translation (SP)
|
100% |
165
2.84 IPS |
|
|
Machine Translation (HP)
|
100% |
154
2.65 IPS |
|
|
Machine Translation (Q)
|
98% |
152
2.63 IPS |