| User | ju83 |
| Upload Date | November 06 2024 03:44 PM |
| Views | 16 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | GPU |
| Device | Apple A12 Bionic |
| System Information | |
|---|---|
| Operating System | iOS 18.1 |
| 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% |
282
52.5 IPS |
|
|
Image Classification (HP)
|
100% |
258
47.9 IPS |
|
|
Image Classification (Q)
|
96% |
128
23.9 IPS |
|
|
Image Segmentation (SP)
|
100% |
219
3.55 IPS |
|
|
Image Segmentation (HP)
|
100% |
244
3.96 IPS |
|
|
Image Segmentation (Q)
|
99% |
174
2.82 IPS |
|
|
Pose Estimation (SP)
|
100% |
1074
1.25 IPS |
|
|
Pose Estimation (HP)
|
100% |
1361
1.59 IPS |
|
|
Pose Estimation (Q)
|
96% |
677
0.79 IPS |
|
|
Object Detection (SP)
|
100% |
535
42.5 IPS |
|
|
Object Detection (HP)
|
100% |
579
46.0 IPS |
|
|
Object Detection (Q)
|
92% |
157
12.5 IPS |
|
|
Face Detection (SP)
|
100% |
1942
23.1 IPS |
|
|
Face Detection (HP)
|
100% |
2220
26.4 IPS |
|
|
Face Detection (Q)
|
100% |
237
2.82 IPS |
|
|
Depth Estimation (SP)
|
100% |
1646
12.7 IPS |
|
|
Depth Estimation (HP)
|
99% |
1768
13.6 IPS |
|
|
Depth Estimation (Q)
|
86% |
415
3.24 IPS |
|
|
Style Transfer (SP)
|
100% |
4062
5.22 IPS |
|
|
Style Transfer (HP)
|
100% |
3381
4.35 IPS |
|
|
Style Transfer (Q)
|
96% |
1541
1.99 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
771
28.5 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
848
31.3 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
260
9.60 IPS |
|
|
Text Classification (SP)
|
100% |
149
198.9 IPS |
|
|
Text Classification (HP)
|
100% |
196
261.9 IPS |
|
|
Text Classification (Q)
|
93% |
206
276.9 IPS |
|
|
Machine Translation (SP)
|
100% |
173
2.97 IPS |
|
|
Machine Translation (HP)
|
100% |
153
2.64 IPS |
|
|
Machine Translation (Q)
|
98% |
154
2.66 IPS |