| User | flipflop |
| Upload Date | June 12 2025 02:07 PM |
| Views | 12 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | GPU |
| Device | Apple A12 Bionic |
| System Information | |
|---|---|
| Operating System | iOS 18.1.1 |
| Model | iPhone XS Max |
| Model ID | iPhone11,6 |
| Motherboard | D331pAP |
| 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 | 3.67 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
228
42.4 IPS |
|
|
Image Classification (HP)
|
100% |
273
50.8 IPS |
|
|
Image Classification (Q)
|
96% |
139
25.9 IPS |
|
|
Image Segmentation (SP)
|
100% |
221
3.58 IPS |
|
|
Image Segmentation (HP)
|
100% |
251
4.06 IPS |
|
|
Image Segmentation (Q)
|
99% |
180
2.92 IPS |
|
|
Pose Estimation (SP)
|
100% |
1317
1.54 IPS |
|
|
Pose Estimation (HP)
|
100% |
1369
1.60 IPS |
|
|
Pose Estimation (Q)
|
96% |
677
0.79 IPS |
|
|
Object Detection (SP)
|
100% |
506
40.2 IPS |
|
|
Object Detection (HP)
|
100% |
549
43.6 IPS |
|
|
Object Detection (Q)
|
92% |
135
10.8 IPS |
|
|
Face Detection (SP)
|
100% |
1830
21.7 IPS |
|
|
Face Detection (HP)
|
100% |
2000
23.8 IPS |
|
|
Face Detection (Q)
|
100% |
240
2.85 IPS |
|
|
Depth Estimation (SP)
|
100% |
1662
12.8 IPS |
|
|
Depth Estimation (HP)
|
99% |
1874
14.4 IPS |
|
|
Depth Estimation (Q)
|
86% |
427
3.34 IPS |
|
|
Style Transfer (SP)
|
100% |
4097
5.27 IPS |
|
|
Style Transfer (HP)
|
100% |
3392
4.36 IPS |
|
|
Style Transfer (Q)
|
96% |
1473
1.90 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
785
29.0 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
911
33.6 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
278
10.3 IPS |
|
|
Text Classification (SP)
|
100% |
152
202.6 IPS |
|
|
Text Classification (HP)
|
100% |
206
274.3 IPS |
|
|
Text Classification (Q)
|
93% |
198
266.1 IPS |
|
|
Machine Translation (SP)
|
100% |
175
3.01 IPS |
|
|
Machine Translation (HP)
|
100% |
160
2.75 IPS |
|
|
Machine Translation (Q)
|
98% |
163
2.82 IPS |