| User | K4ZT13L |
| Upload Date | November 02 2024 02:51 PM |
| Views | 12 |
| 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 | iPad13,10 |
| Motherboard | J523AP |
| 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% |
1904
354.1 IPS |
|
|
Image Classification (HP)
|
100% |
2039
379.2 IPS |
|
|
Image Classification (Q)
|
97% |
1866
348.2 IPS |
|
|
Image Segmentation (SP)
|
100% |
2676
43.4 IPS |
|
|
Image Segmentation (HP)
|
100% |
3604
58.4 IPS |
|
|
Image Segmentation (Q)
|
99% |
3624
58.8 IPS |
|
|
Pose Estimation (SP)
|
100% |
16840
19.6 IPS |
|
|
Pose Estimation (HP)
|
100% |
18226
21.3 IPS |
|
|
Pose Estimation (Q)
|
95% |
16764
19.6 IPS |
|
|
Object Detection (SP)
|
100% |
2668
211.6 IPS |
|
|
Object Detection (HP)
|
100% |
2694
213.7 IPS |
|
|
Object Detection (Q)
|
91% |
2102
168.0 IPS |
|
|
Face Detection (SP)
|
100% |
6733
80.0 IPS |
|
|
Face Detection (HP)
|
100% |
8497
101.0 IPS |
|
|
Face Detection (Q)
|
100% |
5837
69.4 IPS |
|
|
Depth Estimation (SP)
|
100% |
12117
93.4 IPS |
|
|
Depth Estimation (HP)
|
99% |
13539
104.3 IPS |
|
|
Depth Estimation (Q)
|
85% |
10688
83.5 IPS |
|
|
Style Transfer (SP)
|
100% |
28182
36.2 IPS |
|
|
Style Transfer (HP)
|
100% |
33813
43.5 IPS |
|
|
Style Transfer (Q)
|
96% |
32141
41.5 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
6294
232.4 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
7024
259.4 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
5374
198.4 IPS |
|
|
Text Classification (SP)
|
100% |
2229
2.97 KIPS |
|
|
Text Classification (HP)
|
100% |
3598
4.80 KIPS |
|
|
Text Classification (Q)
|
93% |
3574
4.80 KIPS |
|
|
Machine Translation (SP)
|
100% |
849
14.6 IPS |
|
|
Machine Translation (HP)
|
100% |
846
14.6 IPS |
|
|
Machine Translation (Q)
|
98% |
868
15.0 IPS |