| User | ju83 |
| Upload Date | September 09 2024 05:47 AM |
| Views | 15 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | GPU |
| Device | Apple A12 Bionic |
| System Information | |
|---|---|
| Operating System | iOS 17.6.1 |
| 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% |
220
40.8 IPS |
|
|
Image Classification (HP)
|
100% |
268
49.7 IPS |
|
|
Image Classification (Q)
|
96% |
134
25.0 IPS |
|
|
Image Segmentation (SP)
|
100% |
221
3.59 IPS |
|
|
Image Segmentation (HP)
|
100% |
246
3.99 IPS |
|
|
Image Segmentation (Q)
|
99% |
177
2.87 IPS |
|
|
Pose Estimation (SP)
|
100% |
1544
1.80 IPS |
|
|
Pose Estimation (HP)
|
100% |
2172
2.53 IPS |
|
|
Pose Estimation (Q)
|
96% |
694
0.81 IPS |
|
|
Object Detection (SP)
|
100% |
513
40.7 IPS |
|
|
Object Detection (HP)
|
100% |
537
42.6 IPS |
|
|
Object Detection (Q)
|
92% |
148
11.8 IPS |
|
|
Face Detection (SP)
|
100% |
1933
23.0 IPS |
|
|
Face Detection (HP)
|
100% |
2019
24.0 IPS |
|
|
Face Detection (Q)
|
100% |
227
2.70 IPS |
|
|
Depth Estimation (SP)
|
100% |
1661
12.8 IPS |
|
|
Depth Estimation (HP)
|
99% |
1676
12.9 IPS |
|
|
Depth Estimation (Q)
|
86% |
415
3.24 IPS |
|
|
Style Transfer (SP)
|
100% |
4006
5.15 IPS |
|
|
Style Transfer (HP)
|
100% |
3242
4.17 IPS |
|
|
Style Transfer (Q)
|
96% |
1515
1.96 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
766
28.3 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
927
34.2 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
265
9.79 IPS |
|
|
Text Classification (SP)
|
100% |
141
188.7 IPS |
|
|
Text Classification (HP)
|
100% |
199
265.7 IPS |
|
|
Text Classification (Q)
|
93% |
219
294.4 IPS |
|
|
Machine Translation (SP)
|
100% |
196
3.37 IPS |
|
|
Machine Translation (HP)
|
100% |
162
2.80 IPS |
|
|
Machine Translation (Q)
|
98% |
170
2.94 IPS |