| User | EdwinValdezEXD |
| Upload Date | December 04 2024 03:56 PM |
| Views | 15 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | GPU |
| Device | Apple M1 |
| System Information | |
|---|---|
| Operating System | iOS 18.2 |
| Model | iPad Pro (11-inch 3rd generation) |
| Model ID | iPad13,6 |
| Motherboard | J518AP |
| 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% |
2244
417.3 IPS |
|
|
Image Classification (HP)
|
100% |
1985
369.2 IPS |
|
|
Image Classification (Q)
|
97% |
1986
370.5 IPS |
|
|
Image Segmentation (SP)
|
100% |
2694
43.7 IPS |
|
|
Image Segmentation (HP)
|
100% |
3615
58.6 IPS |
|
|
Image Segmentation (Q)
|
99% |
3670
59.5 IPS |
|
|
Pose Estimation (SP)
|
100% |
17283
20.2 IPS |
|
|
Pose Estimation (HP)
|
100% |
18494
21.6 IPS |
|
|
Pose Estimation (Q)
|
95% |
16927
19.8 IPS |
|
|
Object Detection (SP)
|
100% |
2672
211.9 IPS |
|
|
Object Detection (HP)
|
100% |
2699
214.1 IPS |
|
|
Object Detection (Q)
|
91% |
2188
174.8 IPS |
|
|
Face Detection (SP)
|
100% |
6787
80.6 IPS |
|
|
Face Detection (HP)
|
100% |
8448
100.4 IPS |
|
|
Face Detection (Q)
|
100% |
6066
72.1 IPS |
|
|
Depth Estimation (SP)
|
100% |
12102
93.2 IPS |
|
|
Depth Estimation (HP)
|
99% |
13512
104.1 IPS |
|
|
Depth Estimation (Q)
|
85% |
11466
89.6 IPS |
|
|
Style Transfer (SP)
|
100% |
28869
37.1 IPS |
|
|
Style Transfer (HP)
|
100% |
34627
44.5 IPS |
|
|
Style Transfer (Q)
|
96% |
31540
40.7 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
6364
235.0 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
7049
260.3 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
5334
197.0 IPS |
|
|
Text Classification (SP)
|
100% |
2219
2.96 KIPS |
|
|
Text Classification (HP)
|
100% |
3818
5.10 KIPS |
|
|
Text Classification (Q)
|
93% |
3529
4.74 KIPS |
|
|
Machine Translation (SP)
|
100% |
832
14.3 IPS |
|
|
Machine Translation (HP)
|
100% |
837
14.4 IPS |
|
|
Machine Translation (Q)
|
98% |
825
14.3 IPS |