User | jankkhvej |
Upload Date | May 12 2025 08:49 PM |
Views | 6 |
AI Information | |
---|---|
Framework | Core ML |
Backend | GPU |
Device | Apple M2 |
System Information | |
---|---|
Operating System | iOS 18.4.1 |
Model | iPad Pro (11-inch, 4th generation) |
Model ID | iPad14,3 |
Motherboard | J617AP |
CPU Information | |
---|---|
Name | Apple M2 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM |
Base Frequency | 3.49 GHz |
Cluster 1 | 4 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 7.37 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
3643
677.5 IPS |
|
Image Classification (HP)
|
100% |
3624
673.9 IPS |
|
Image Classification (Q)
|
96% |
3399
634.7 IPS |
|
Image Segmentation (SP)
|
100% |
5731
92.9 IPS |
|
Image Segmentation (HP)
|
100% |
5875
95.2 IPS |
|
Image Segmentation (Q)
|
99% |
5627
91.2 IPS |
|
Pose Estimation (SP)
|
100% |
24631
28.7 IPS |
|
Pose Estimation (HP)
|
100% |
26304
30.7 IPS |
|
Pose Estimation (Q)
|
96% |
25473
29.8 IPS |
|
Object Detection (SP)
|
100% |
3653
289.8 IPS |
|
Object Detection (HP)
|
100% |
3691
292.8 IPS |
|
Object Detection (Q)
|
92% |
3341
266.7 IPS |
|
Face Detection (SP)
|
100% |
10343
122.9 IPS |
|
Face Detection (HP)
|
100% |
11920
141.6 IPS |
|
Face Detection (Q)
|
100% |
10026
119.1 IPS |
|
Depth Estimation (SP)
|
100% |
16805
129.5 IPS |
|
Depth Estimation (HP)
|
99% |
17944
138.2 IPS |
|
Depth Estimation (Q)
|
85% |
16276
127.3 IPS |
|
Style Transfer (SP)
|
100% |
42677
54.9 IPS |
|
Style Transfer (HP)
|
100% |
48581
62.5 IPS |
|
Style Transfer (Q)
|
96% |
47172
60.9 IPS |
|
Image Super-Resolution (SP)
|
100% |
9789
361.5 IPS |
|
Image Super-Resolution (HP)
|
100% |
10174
375.7 IPS |
|
Image Super-Resolution (Q)
|
99% |
8741
322.7 IPS |
|
Text Classification (SP)
|
100% |
2238
2.99 KIPS |
|
Text Classification (HP)
|
100% |
3850
5.14 KIPS |
|
Text Classification (Q)
|
93% |
3717
4.99 KIPS |
|
Machine Translation (SP)
|
100% |
1727
29.7 IPS |
|
Machine Translation (HP)
|
100% |
1871
32.2 IPS |
|
Machine Translation (Q)
|
98% |
1702
29.4 IPS |