| User | aenewton |
| Upload Date | September 22 2024 06:00 AM |
| Views | 17 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | CPU |
| Device | ARM |
| System Information | |
|---|---|
| Operating System | iOS 18.0 |
| Model | iPhone17,2 |
| Model ID | iPhone17,2 |
| Motherboard | D94AP |
| CPU Information | |
|---|---|
| Name | ARM |
| Topology | 1 Processor, 6 Cores |
| Identifier | ARM |
| Base Frequency | 4.04 GHz |
| Cluster 1 | 2 Cores |
| Cluster 2 | 4 Cores |
| Memory Information | |
|---|---|
| Size | 7.47 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
1986
369.3 IPS |
|
|
Image Classification (HP)
|
100% |
3337
620.6 IPS |
|
|
Image Classification (Q)
|
96% |
2272
424.4 IPS |
|
|
Image Segmentation (SP)
|
100% |
1942
31.5 IPS |
|
|
Image Segmentation (HP)
|
100% |
2910
47.2 IPS |
|
|
Image Segmentation (Q)
|
99% |
3329
54.0 IPS |
|
|
Pose Estimation (SP)
|
100% |
8749
10.2 IPS |
|
|
Pose Estimation (HP)
|
100% |
17916
20.9 IPS |
|
|
Pose Estimation (Q)
|
95% |
15247
17.9 IPS |
|
|
Object Detection (SP)
|
100% |
2090
165.8 IPS |
|
|
Object Detection (HP)
|
97% |
3797
302.3 IPS |
|
|
Object Detection (Q)
|
94% |
2642
210.6 IPS |
|
|
Face Detection (SP)
|
100% |
3548
42.2 IPS |
|
|
Face Detection (HP)
|
100% |
7325
87.0 IPS |
|
|
Face Detection (Q)
|
100% |
4160
49.4 IPS |
|
|
Depth Estimation (SP)
|
100% |
7639
58.9 IPS |
|
|
Depth Estimation (HP)
|
97% |
13909
107.5 IPS |
|
|
Depth Estimation (Q)
|
86% |
9687
75.6 IPS |
|
|
Style Transfer (SP)
|
100% |
23687
30.4 IPS |
|
|
Style Transfer (HP)
|
100% |
37570
48.3 IPS |
|
|
Style Transfer (Q)
|
96% |
30675
39.6 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
5615
207.3 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
6901
254.8 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
4911
181.4 IPS |
|
|
Text Classification (SP)
|
100% |
3438
4.59 KIPS |
|
|
Text Classification (HP)
|
100% |
5921
7.90 KIPS |
|
|
Text Classification (Q)
|
93% |
5854
7.86 KIPS |
|
|
Machine Translation (SP)
|
100% |
3730
64.2 IPS |
|
|
Machine Translation (HP)
|
98% |
6942
120.0 IPS |
|
|
Machine Translation (Q)
|
98% |
6948
120.1 IPS |