| User | m4n |
| Upload Date | February 01 2025 02:38 PM |
| Views | 13 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | GPU |
| Device | Apple M1 |
| System Information | |
|---|---|
| Operating System | iOS 18.2.1 |
| Model | iPad Pro (11-inch 3rd generation) |
| Model ID | iPad13,4 |
| Motherboard | J517AP |
| CPU Information | |
|---|---|
| Name | Apple M1 |
| Topology | 1 Processor, 8 Cores |
| Identifier | ARM |
| Base Frequency | 3.19 GHz |
| Cluster 1 | 4 Cores |
| Cluster 2 | 4 Cores |
| Memory Information | |
|---|---|
| Size | 7.37 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
1983
368.9 IPS |
|
|
Image Classification (HP)
|
100% |
2293
426.4 IPS |
|
|
Image Classification (Q)
|
97% |
2035
379.9 IPS |
|
|
Image Segmentation (SP)
|
100% |
2661
43.1 IPS |
|
|
Image Segmentation (HP)
|
100% |
3662
59.4 IPS |
|
|
Image Segmentation (Q)
|
99% |
3702
60.0 IPS |
|
|
Pose Estimation (SP)
|
100% |
17356
20.3 IPS |
|
|
Pose Estimation (HP)
|
100% |
18935
22.1 IPS |
|
|
Pose Estimation (Q)
|
95% |
17689
20.7 IPS |
|
|
Object Detection (SP)
|
100% |
2782
220.6 IPS |
|
|
Object Detection (HP)
|
100% |
2777
220.3 IPS |
|
|
Object Detection (Q)
|
91% |
2249
179.7 IPS |
|
|
Face Detection (SP)
|
100% |
6859
81.5 IPS |
|
|
Face Detection (HP)
|
100% |
8543
101.5 IPS |
|
|
Face Detection (Q)
|
100% |
5919
70.3 IPS |
|
|
Depth Estimation (SP)
|
100% |
12488
96.2 IPS |
|
|
Depth Estimation (HP)
|
99% |
13990
107.8 IPS |
|
|
Depth Estimation (Q)
|
85% |
11557
90.3 IPS |
|
|
Style Transfer (SP)
|
100% |
29261
37.6 IPS |
|
|
Style Transfer (HP)
|
100% |
35186
45.2 IPS |
|
|
Style Transfer (Q)
|
96% |
32920
42.5 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
6478
239.2 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
7382
272.6 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
5347
197.4 IPS |
|
|
Text Classification (SP)
|
100% |
2288
3.05 KIPS |
|
|
Text Classification (HP)
|
100% |
3948
5.27 KIPS |
|
|
Text Classification (Q)
|
93% |
3907
5.24 KIPS |
|
|
Machine Translation (SP)
|
100% |
842
14.5 IPS |
|
|
Machine Translation (HP)
|
100% |
851
14.7 IPS |
|
|
Machine Translation (Q)
|
98% |
840
14.5 IPS |