| User | toygoon |
| Upload Date | September 27 2024 10:26 AM |
| Views | 8 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | Neural Engine |
| Device | Apple A16 Bionic |
| System Information | |
|---|---|
| Operating System | iOS 17.0 |
| Model | iPhone 14 Pro Max |
| Model ID | iPhone15,3 |
| Motherboard | D74AP |
| CPU Information | |
|---|---|
| Name | Apple A16 Bionic |
| Topology | 1 Processor, 6 Cores |
| Identifier | ARM |
| Base Frequency | 3.46 GHz |
| Cluster 1 | 2 Cores |
| Cluster 2 | 4 Cores |
| Memory Information | |
|---|---|
| Size | 5.49 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
1233
229.4 IPS |
|
|
Image Classification (HP)
|
100% |
5911
1.10 KIPS |
|
|
Image Classification (Q)
|
96% |
6272
1.17 KIPS |
|
|
Image Segmentation (SP)
|
100% |
750
12.2 IPS |
|
|
Image Segmentation (HP)
|
100% |
5124
83.1 IPS |
|
|
Image Segmentation (Q)
|
99% |
9086
147.3 IPS |
|
|
Pose Estimation (SP)
|
100% |
6488
7.57 IPS |
|
|
Pose Estimation (HP)
|
100% |
80457
93.9 IPS |
|
|
Pose Estimation (Q)
|
95% |
83029
97.3 IPS |
|
|
Object Detection (SP)
|
100% |
1335
105.9 IPS |
|
|
Object Detection (HP)
|
100% |
7500
594.9 IPS |
|
|
Object Detection (Q)
|
93% |
8285
661.0 IPS |
|
|
Face Detection (SP)
|
100% |
2196
26.1 IPS |
|
|
Face Detection (HP)
|
100% |
13534
160.8 IPS |
|
|
Face Detection (Q)
|
100% |
697
8.28 IPS |
|
|
Depth Estimation (SP)
|
100% |
4142
31.9 IPS |
|
|
Depth Estimation (HP)
|
99% |
35576
274.1 IPS |
|
|
Depth Estimation (Q)
|
85% |
44405
347.2 IPS |
|
|
Style Transfer (SP)
|
100% |
11643
15.0 IPS |
|
|
Style Transfer (HP)
|
100% |
117662
151.3 IPS |
|
|
Style Transfer (Q)
|
25% |
4896
136.8 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
3161
116.7 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
17347
640.5 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
16674
615.7 IPS |
|
|
Text Classification (SP)
|
100% |
1371
1.83 KIPS |
|
|
Text Classification (HP)
|
100% |
2668
3.56 KIPS |
|
|
Text Classification (Q)
|
93% |
2839
3.81 KIPS |
|
|
Machine Translation (SP)
|
100% |
1456
25.1 IPS |
|
|
Machine Translation (HP)
|
100% |
2460
42.4 IPS |
|
|
Machine Translation (Q)
|
98% |
2464
42.6 IPS |