| User | Risto3 |
| Upload Date | September 19 2024 01:18 PM |
| Views | 14 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | GPU |
| Device | Apple M1 |
| System Information | |
|---|---|
| Operating System | iOS 18.1 |
| Model | iPad Pro (12.9-inch 5th generation) |
| Model ID | iPad13,11 |
| Motherboard | J523xAP |
| 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 | 15.35 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
2035
378.5 IPS |
|
|
Image Classification (HP)
|
100% |
1918
356.6 IPS |
|
|
Image Classification (Q)
|
97% |
1864
347.9 IPS |
|
|
Image Segmentation (SP)
|
100% |
2709
43.9 IPS |
|
|
Image Segmentation (HP)
|
100% |
3634
58.9 IPS |
|
|
Image Segmentation (Q)
|
99% |
3648
59.1 IPS |
|
|
Pose Estimation (SP)
|
100% |
17045
19.9 IPS |
|
|
Pose Estimation (HP)
|
100% |
18386
21.5 IPS |
|
|
Pose Estimation (Q)
|
95% |
16994
19.9 IPS |
|
|
Object Detection (SP)
|
100% |
2718
215.6 IPS |
|
|
Object Detection (HP)
|
100% |
2764
219.2 IPS |
|
|
Object Detection (Q)
|
91% |
2166
173.1 IPS |
|
|
Face Detection (SP)
|
100% |
6609
78.5 IPS |
|
|
Face Detection (HP)
|
100% |
8462
100.5 IPS |
|
|
Face Detection (Q)
|
100% |
5831
69.3 IPS |
|
|
Depth Estimation (SP)
|
100% |
12168
93.7 IPS |
|
|
Depth Estimation (HP)
|
99% |
13713
105.7 IPS |
|
|
Depth Estimation (Q)
|
85% |
10806
84.5 IPS |
|
|
Style Transfer (SP)
|
100% |
28748
37.0 IPS |
|
|
Style Transfer (HP)
|
100% |
34338
44.1 IPS |
|
|
Style Transfer (Q)
|
96% |
32724
42.2 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
6358
234.8 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
7205
266.1 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
5384
198.8 IPS |
|
|
Text Classification (SP)
|
100% |
2320
3.10 KIPS |
|
|
Text Classification (HP)
|
100% |
4007
5.35 KIPS |
|
|
Text Classification (Q)
|
93% |
3989
5.35 KIPS |
|
|
Machine Translation (SP)
|
100% |
851
14.7 IPS |
|
|
Machine Translation (HP)
|
100% |
848
14.6 IPS |
|
|
Machine Translation (Q)
|
98% |
945
16.3 IPS |