| User | M91 |
| Upload Date | November 02 2024 08:16 AM |
| Views | 8 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | GPU |
| Device | ARM |
| System Information | |
|---|---|
| Operating System | iOS 18.2 |
| Model | iPhone17,2 |
| Model ID | iPhone17,2 |
| Motherboard | D94AP |
| CPU Information | |
|---|---|
| Name | ARM |
| Topology | 1 Processor, 6 Cores |
| Identifier | ARM |
| Base Frequency | 2.68 GHz |
| Cluster 1 | 2 Cores |
| Cluster 2 | 4 Cores |
| Memory Information | |
|---|---|
| Size | 7.45 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
2165
402.6 IPS |
|
|
Image Classification (HP)
|
100% |
1680
312.5 IPS |
|
|
Image Classification (Q)
|
97% |
1614
301.3 IPS |
|
|
Image Segmentation (SP)
|
100% |
3261
52.9 IPS |
|
|
Image Segmentation (HP)
|
100% |
3840
62.2 IPS |
|
|
Image Segmentation (Q)
|
99% |
4384
71.1 IPS |
|
|
Pose Estimation (SP)
|
100% |
10078
11.8 IPS |
|
|
Pose Estimation (HP)
|
100% |
9870
11.5 IPS |
|
|
Pose Estimation (Q)
|
95% |
12896
15.1 IPS |
|
|
Object Detection (SP)
|
100% |
2521
200.0 IPS |
|
|
Object Detection (HP)
|
100% |
3163
250.9 IPS |
|
|
Object Detection (Q)
|
91% |
2717
217.1 IPS |
|
|
Face Detection (SP)
|
100% |
7552
89.7 IPS |
|
|
Face Detection (HP)
|
100% |
8448
100.4 IPS |
|
|
Face Detection (Q)
|
100% |
7082
84.2 IPS |
|
|
Depth Estimation (SP)
|
100% |
13061
100.6 IPS |
|
|
Depth Estimation (HP)
|
99% |
13910
107.2 IPS |
|
|
Depth Estimation (Q)
|
85% |
11680
91.3 IPS |
|
|
Style Transfer (SP)
|
100% |
27575
35.4 IPS |
|
|
Style Transfer (HP)
|
100% |
24138
31.0 IPS |
|
|
Style Transfer (Q)
|
96% |
29409
38.0 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
5981
220.8 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
6712
247.9 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
6812
251.5 IPS |
|
|
Text Classification (SP)
|
100% |
2127
2.84 KIPS |
|
|
Text Classification (HP)
|
100% |
4303
5.74 KIPS |
|
|
Text Classification (Q)
|
93% |
4526
6.07 KIPS |
|
|
Machine Translation (SP)
|
100% |
808
13.9 IPS |
|
|
Machine Translation (HP)
|
100% |
780
13.4 IPS |
|
|
Machine Translation (Q)
|
98% |
746
12.9 IPS |