| User | g8mb1t |
| Upload Date | September 23 2024 10:22 PM |
| Views | 12 |
| 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% |
1918
356.7 IPS |
|
|
Image Classification (HP)
|
100% |
3280
610.0 IPS |
|
|
Image Classification (Q)
|
96% |
2216
413.8 IPS |
|
|
Image Segmentation (SP)
|
100% |
1840
29.8 IPS |
|
|
Image Segmentation (HP)
|
100% |
2792
45.3 IPS |
|
|
Image Segmentation (Q)
|
99% |
3169
51.4 IPS |
|
|
Pose Estimation (SP)
|
100% |
7688
8.97 IPS |
|
|
Pose Estimation (HP)
|
100% |
16249
19.0 IPS |
|
|
Pose Estimation (Q)
|
95% |
13749
16.1 IPS |
|
|
Object Detection (SP)
|
100% |
1959
155.4 IPS |
|
|
Object Detection (HP)
|
97% |
3573
284.5 IPS |
|
|
Object Detection (Q)
|
94% |
2500
199.3 IPS |
|
|
Face Detection (SP)
|
100% |
3308
39.3 IPS |
|
|
Face Detection (HP)
|
100% |
6989
83.0 IPS |
|
|
Face Detection (Q)
|
100% |
3898
46.3 IPS |
|
|
Depth Estimation (SP)
|
100% |
7099
54.7 IPS |
|
|
Depth Estimation (HP)
|
97% |
13238
102.3 IPS |
|
|
Depth Estimation (Q)
|
86% |
9110
71.1 IPS |
|
|
Style Transfer (SP)
|
100% |
21732
27.9 IPS |
|
|
Style Transfer (HP)
|
100% |
34387
44.2 IPS |
|
|
Style Transfer (Q)
|
96% |
28483
36.8 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
5014
185.1 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
6448
238.1 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
4572
168.8 IPS |
|
|
Text Classification (SP)
|
100% |
3444
4.60 KIPS |
|
|
Text Classification (HP)
|
100% |
5969
7.97 KIPS |
|
|
Text Classification (Q)
|
93% |
5919
7.94 KIPS |
|
|
Machine Translation (SP)
|
100% |
3652
62.9 IPS |
|
|
Machine Translation (HP)
|
98% |
6798
117.5 IPS |
|
|
Machine Translation (Q)
|
98% |
6876
118.8 IPS |