| Upload Date | August 15 2024 03:48 AM |
| Views | 15 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | Neural Engine |
| Device | ARM |
| System Information | |
|---|---|
| Operating System | iOS 17.5.1 |
| Model | iPad14,8 |
| Model ID | iPad14,8 |
| Motherboard | J507AP |
| CPU Information | |
|---|---|
| Name | ARM |
| Topology | 1 Processor, 8 Cores |
| Identifier | ARM |
| Base Frequency | 3.48 GHz |
| Cluster 1 | 4 Cores |
| Cluster 2 | 4 Cores |
| Memory Information | |
|---|---|
| Size | 7.47 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
1248
232.2 IPS |
|
|
Image Classification (HP)
|
100% |
7290
1.36 KIPS |
|
|
Image Classification (Q)
|
99% |
7518
1.40 KIPS |
|
|
Image Segmentation (SP)
|
100% |
738
12.0 IPS |
|
|
Image Segmentation (HP)
|
100% |
5036
81.6 IPS |
|
|
Image Segmentation (Q)
|
100% |
5020
81.4 IPS |
|
|
Pose Estimation (SP)
|
100% |
5926
6.91 IPS |
|
|
Pose Estimation (HP)
|
100% |
87267
101.8 IPS |
|
|
Pose Estimation (Q)
|
94% |
87272
102.4 IPS |
|
|
Object Detection (SP)
|
100% |
1328
105.4 IPS |
|
|
Object Detection (HP)
|
99% |
8368
665.6 IPS |
|
|
Object Detection (Q)
|
93% |
8787
701.1 IPS |
|
|
Face Detection (SP)
|
100% |
2423
28.8 IPS |
|
|
Face Detection (HP)
|
100% |
11296
134.2 IPS |
|
|
Face Detection (Q)
|
100% |
13249
157.4 IPS |
|
|
Depth Estimation (SP)
|
100% |
4071
31.4 IPS |
|
|
Depth Estimation (HP)
|
99% |
48205
371.4 IPS |
|
|
Depth Estimation (Q)
|
97% |
52501
405.9 IPS |
|
|
Style Transfer (SP)
|
100% |
10912
14.0 IPS |
|
|
Style Transfer (HP)
|
100% |
138353
177.9 IPS |
|
|
Style Transfer (Q)
|
100% |
138741
178.4 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
3068
113.3 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
19220
709.7 IPS |
|
|
Image Super-Resolution (Q)
|
98% |
24473
906.7 IPS |
|
|
Text Classification (SP)
|
100% |
1198
1.60 KIPS |
|
|
Text Classification (HP)
|
100% |
800
1.07 KIPS |
|
|
Text Classification (Q)
|
93% |
796
1.07 KIPS |
|
|
Machine Translation (SP)
|
100% |
1557
26.8 IPS |
|
|
Machine Translation (HP)
|
100% |
2361
40.7 IPS |
|
|
Machine Translation (Q)
|
98% |
2351
40.6 IPS |