| Upload Date | April 19 2025 11:56 PM |
| Views | 3 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | CPU |
| Device | Apple M1 |
| System Information | |
|---|---|
| Operating System | iOS 18.4 |
| Model | iPad Pro (12.9-inch 5th generation) |
| Model ID | iPad13,8 |
| Motherboard | J522AP |
| 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 | 7.35 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
1405
261.2 IPS |
|
|
Image Classification (HP)
|
100% |
2203
409.8 IPS |
|
|
Image Classification (Q)
|
96% |
1573
293.7 IPS |
|
|
Image Segmentation (SP)
|
100% |
1365
22.1 IPS |
|
|
Image Segmentation (HP)
|
100% |
2186
35.4 IPS |
|
|
Image Segmentation (Q)
|
99% |
2493
40.4 IPS |
|
|
Pose Estimation (SP)
|
100% |
5959
6.95 IPS |
|
|
Pose Estimation (HP)
|
100% |
14058
16.4 IPS |
|
|
Pose Estimation (Q)
|
95% |
8340
9.78 IPS |
|
|
Object Detection (SP)
|
100% |
1484
117.7 IPS |
|
|
Object Detection (HP)
|
97% |
1836
146.1 IPS |
|
|
Object Detection (Q)
|
94% |
1763
140.6 IPS |
|
|
Face Detection (SP)
|
100% |
2062
24.5 IPS |
|
|
Face Detection (HP)
|
100% |
5375
63.9 IPS |
|
|
Face Detection (Q)
|
100% |
3125
37.1 IPS |
|
|
Depth Estimation (SP)
|
100% |
5448
42.0 IPS |
|
|
Depth Estimation (HP)
|
98% |
7268
56.2 IPS |
|
|
Depth Estimation (Q)
|
85% |
7284
56.9 IPS |
|
|
Style Transfer (SP)
|
100% |
16824
21.6 IPS |
|
|
Style Transfer (HP)
|
100% |
26703
34.3 IPS |
|
|
Style Transfer (Q)
|
96% |
22187
28.6 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
3647
134.7 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
4544
167.8 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
3395
125.4 IPS |
|
|
Text Classification (SP)
|
100% |
1771
2.36 KIPS |
|
|
Text Classification (HP)
|
100% |
3875
5.17 KIPS |
|
|
Text Classification (Q)
|
93% |
3896
5.23 KIPS |
|
|
Machine Translation (SP)
|
100% |
2487
42.8 IPS |
|
|
Machine Translation (HP)
|
98% |
4504
77.8 IPS |
|
|
Machine Translation (Q)
|
98% |
4518
78.1 IPS |