User | iPhil |
Upload Date | March 21 2025 08:45 PM |
Views | 3 |
AI Information | |
---|---|
Framework | Core ML |
Backend | GPU |
Device | Apple M2 |
System Information | |
---|---|
Operating System | iOS 18.4 |
Model | iPad Pro (12.9-inch, 6th generation) |
Model ID | iPad14,5 |
Motherboard | J620AP |
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 | 7.35 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
3685
685.4 IPS |
|
Image Classification (HP)
|
100% |
3675
683.5 IPS |
|
Image Classification (Q)
|
96% |
3413
637.3 IPS |
|
Image Segmentation (SP)
|
100% |
5718
92.7 IPS |
|
Image Segmentation (HP)
|
100% |
5875
95.2 IPS |
|
Image Segmentation (Q)
|
99% |
5615
91.0 IPS |
|
Pose Estimation (SP)
|
100% |
24645
28.8 IPS |
|
Pose Estimation (HP)
|
100% |
26301
30.7 IPS |
|
Pose Estimation (Q)
|
96% |
25467
29.8 IPS |
|
Object Detection (SP)
|
100% |
3664
290.6 IPS |
|
Object Detection (HP)
|
100% |
3722
295.2 IPS |
|
Object Detection (Q)
|
92% |
3388
270.5 IPS |
|
Face Detection (SP)
|
100% |
10365
123.2 IPS |
|
Face Detection (HP)
|
100% |
12071
143.4 IPS |
|
Face Detection (Q)
|
100% |
9992
118.7 IPS |
|
Depth Estimation (SP)
|
100% |
16853
129.8 IPS |
|
Depth Estimation (HP)
|
99% |
17949
138.3 IPS |
|
Depth Estimation (Q)
|
85% |
16224
126.9 IPS |
|
Style Transfer (SP)
|
100% |
42734
54.9 IPS |
|
Style Transfer (HP)
|
100% |
48596
62.5 IPS |
|
Style Transfer (Q)
|
96% |
47133
60.8 IPS |
|
Image Super-Resolution (SP)
|
100% |
9820
362.6 IPS |
|
Image Super-Resolution (HP)
|
100% |
10188
376.2 IPS |
|
Image Super-Resolution (Q)
|
99% |
8661
319.8 IPS |
|
Text Classification (SP)
|
100% |
2220
2.96 KIPS |
|
Text Classification (HP)
|
100% |
3949
5.27 KIPS |
|
Text Classification (Q)
|
93% |
3846
5.16 KIPS |
|
Machine Translation (SP)
|
100% |
2130
36.7 IPS |
|
Machine Translation (HP)
|
100% |
1808
31.1 IPS |
|
Machine Translation (Q)
|
98% |
1389
24.0 IPS |