| User | mcx |
| Upload Date | August 15 2024 06:37 PM |
| Views | 9 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | GPU |
| Device | Apple A12X Bionic |
| System Information | |
|---|---|
| Operating System | iOS 17.6.1 |
| Model | iPad Pro (11-inch) |
| Model ID | iPad8,1 |
| Motherboard | J317AP |
| CPU Information | |
|---|---|
| Name | Apple A12X Bionic |
| Topology | 1 Processor, 8 Cores |
| Identifier | ARM |
| Base Frequency | 2.49 GHz |
| Cluster 1 | 4 Cores |
| Cluster 2 | 4 Cores |
| Memory Information | |
|---|---|
| Size | 3.69 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
855
159.0 IPS |
|
|
Image Classification (HP)
|
100% |
1139
211.7 IPS |
|
|
Image Classification (Q)
|
99% |
1133
211.4 IPS |
|
|
Image Segmentation (SP)
|
100% |
365
5.91 IPS |
|
|
Image Segmentation (HP)
|
100% |
386
6.26 IPS |
|
|
Image Segmentation (Q)
|
100% |
382
6.19 IPS |
|
|
Pose Estimation (SP)
|
100% |
2808
3.28 IPS |
|
|
Pose Estimation (HP)
|
100% |
3994
4.66 IPS |
|
|
Pose Estimation (Q)
|
94% |
1577
1.85 IPS |
|
|
Object Detection (SP)
|
100% |
955
75.8 IPS |
|
|
Object Detection (HP)
|
100% |
1252
99.3 IPS |
|
|
Object Detection (Q)
|
92% |
181
14.4 IPS |
|
|
Face Detection (SP)
|
100% |
3430
40.8 IPS |
|
|
Face Detection (HP)
|
100% |
3878
46.1 IPS |
|
|
Face Detection (Q)
|
100% |
297
3.53 IPS |
|
|
Depth Estimation (SP)
|
100% |
2851
22.0 IPS |
|
|
Depth Estimation (HP)
|
99% |
4087
31.5 IPS |
|
|
Depth Estimation (Q)
|
97% |
4108
31.8 IPS |
|
|
Style Transfer (SP)
|
100% |
7834
10.1 IPS |
|
|
Style Transfer (HP)
|
100% |
9460
12.2 IPS |
|
|
Style Transfer (Q)
|
100% |
9524
12.2 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
1384
51.1 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
1853
68.4 IPS |
|
|
Image Super-Resolution (Q)
|
98% |
392
14.5 IPS |
|
|
Text Classification (SP)
|
100% |
212
282.6 IPS |
|
|
Text Classification (HP)
|
100% |
254
338.7 IPS |
|
|
Text Classification (Q)
|
93% |
253
339.3 IPS |
|
|
Machine Translation (SP)
|
100% |
506
8.72 IPS |
|
|
Machine Translation (HP)
|
100% |
434
7.48 IPS |
|
|
Machine Translation (Q)
|
98% |
411
7.10 IPS |