| User | oldnick |
| Upload Date | December 31 2024 01:07 PM |
| Views | 13 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | GPU |
| Device | ARM |
| System Information | |
|---|---|
| Operating System | iOS 18.2 |
| Model | iPad16,2 |
| Model ID | iPad16,2 |
| Motherboard | J411AP |
| CPU Information | |
|---|---|
| Name | ARM |
| Topology | 1 Processor, 6 Cores |
| Identifier | ARM |
| Base Frequency | 3.77 GHz |
| Cluster 1 | 2 Cores |
| Cluster 2 | 4 Cores |
| Memory Information | |
|---|---|
| Size | 7.73 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
1102
204.9 IPS |
|
|
Image Classification (HP)
|
100% |
1436
267.0 IPS |
|
|
Image Classification (Q)
|
97% |
1113
207.7 IPS |
|
|
Image Segmentation (SP)
|
100% |
3126
50.7 IPS |
|
|
Image Segmentation (HP)
|
100% |
3424
55.5 IPS |
|
|
Image Segmentation (Q)
|
99% |
3497
56.7 IPS |
|
|
Pose Estimation (SP)
|
100% |
12277
14.3 IPS |
|
|
Pose Estimation (HP)
|
100% |
12758
14.9 IPS |
|
|
Pose Estimation (Q)
|
95% |
11983
14.0 IPS |
|
|
Object Detection (SP)
|
100% |
1817
144.1 IPS |
|
|
Object Detection (HP)
|
100% |
1749
138.7 IPS |
|
|
Object Detection (Q)
|
91% |
1658
132.5 IPS |
|
|
Face Detection (SP)
|
100% |
5395
64.1 IPS |
|
|
Face Detection (HP)
|
100% |
8156
96.9 IPS |
|
|
Face Detection (Q)
|
100% |
5315
63.1 IPS |
|
|
Depth Estimation (SP)
|
100% |
10031
77.3 IPS |
|
|
Depth Estimation (HP)
|
99% |
10725
82.6 IPS |
|
|
Depth Estimation (Q)
|
85% |
9299
72.7 IPS |
|
|
Style Transfer (SP)
|
100% |
25670
33.0 IPS |
|
|
Style Transfer (HP)
|
100% |
29327
37.7 IPS |
|
|
Style Transfer (Q)
|
96% |
27540
35.5 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
5314
196.2 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
5399
199.4 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
3430
126.7 IPS |
|
|
Text Classification (SP)
|
100% |
3206
4.28 KIPS |
|
|
Text Classification (HP)
|
100% |
5576
7.44 KIPS |
|
|
Text Classification (Q)
|
93% |
5550
7.45 KIPS |
|
|
Machine Translation (SP)
|
100% |
1156
19.9 IPS |
|
|
Machine Translation (HP)
|
100% |
1217
21.0 IPS |
|
|
Machine Translation (Q)
|
98% |
1365
23.6 IPS |