| User | jpdalamar |
| Upload Date | August 19 2024 05:06 PM |
| Views | 16 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | CPU |
| Device | Apple A16 Bionic |
| System Information | |
|---|---|
| Operating System | iOS 18.0 |
| 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 | 5.51 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
1420
264.1 IPS |
|
|
Image Classification (HP)
|
100% |
2517
468.0 IPS |
|
|
Image Classification (Q)
|
99% |
2519
469.9 IPS |
|
|
Image Segmentation (SP)
|
100% |
1431
23.2 IPS |
|
|
Image Segmentation (HP)
|
100% |
2158
35.0 IPS |
|
|
Image Segmentation (Q)
|
100% |
2157
35.0 IPS |
|
|
Pose Estimation (SP)
|
100% |
6906
8.06 IPS |
|
|
Pose Estimation (HP)
|
100% |
15026
17.5 IPS |
|
|
Pose Estimation (Q)
|
96% |
12905
15.1 IPS |
|
|
Object Detection (SP)
|
100% |
1570
124.5 IPS |
|
|
Object Detection (HP)
|
97% |
2898
230.7 IPS |
|
|
Object Detection (Q)
|
94% |
2046
163.1 IPS |
|
|
Face Detection (SP)
|
100% |
3026
36.0 IPS |
|
|
Face Detection (HP)
|
100% |
6010
71.4 IPS |
|
|
Face Detection (Q)
|
100% |
3464
41.2 IPS |
|
|
Depth Estimation (SP)
|
100% |
6212
47.9 IPS |
|
|
Depth Estimation (HP)
|
98% |
12178
94.1 IPS |
|
|
Depth Estimation (Q)
|
97% |
12125
93.8 IPS |
|
|
Style Transfer (SP)
|
100% |
18989
24.4 IPS |
|
|
Style Transfer (HP)
|
100% |
28088
36.1 IPS |
|
|
Style Transfer (Q)
|
100% |
28036
36.0 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
4176
154.2 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
4964
183.3 IPS |
|
|
Image Super-Resolution (Q)
|
98% |
3613
133.8 IPS |
|
|
Text Classification (SP)
|
100% |
2590
3.46 KIPS |
|
|
Text Classification (HP)
|
100% |
4467
5.96 KIPS |
|
|
Text Classification (Q)
|
93% |
4543
6.10 KIPS |
|
|
Machine Translation (SP)
|
100% |
3414
58.8 IPS |
|
|
Machine Translation (HP)
|
98% |
5769
99.7 IPS |
|
|
Machine Translation (Q)
|
98% |
5759
99.5 IPS |