User | jaw3000 |
Upload Date | August 15 2024 05:51 PM |
Views | 7 |
AI Information | |
---|---|
Framework | Core ML |
Backend | GPU |
Device | Apple M2 |
System Information | |
---|---|
Operating System | iOS 18.1 |
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% |
3598
669.1 IPS |
|
Image Classification (HP)
|
100% |
3547
659.6 IPS |
|
Image Classification (Q)
|
99% |
3225
601.5 IPS |
|
Image Segmentation (SP)
|
100% |
3899
63.2 IPS |
|
Image Segmentation (HP)
|
100% |
4978
80.7 IPS |
|
Image Segmentation (Q)
|
100% |
4854
78.7 IPS |
|
Pose Estimation (SP)
|
100% |
24371
28.4 IPS |
|
Pose Estimation (HP)
|
100% |
26156
30.5 IPS |
|
Pose Estimation (Q)
|
97% |
23570
27.6 IPS |
|
Object Detection (SP)
|
100% |
3632
288.1 IPS |
|
Object Detection (HP)
|
100% |
3685
292.3 IPS |
|
Object Detection (Q)
|
91% |
2796
223.4 IPS |
|
Face Detection (SP)
|
100% |
10145
120.5 IPS |
|
Face Detection (HP)
|
100% |
11717
139.2 IPS |
|
Face Detection (Q)
|
100% |
8039
95.5 IPS |
|
Depth Estimation (SP)
|
100% |
16498
127.1 IPS |
|
Depth Estimation (HP)
|
99% |
17823
137.3 IPS |
|
Depth Estimation (Q)
|
97% |
2784
21.5 IPS |
|
Style Transfer (SP)
|
100% |
42028
54.0 IPS |
|
Style Transfer (HP)
|
100% |
48414
62.2 IPS |
|
Style Transfer (Q)
|
100% |
48244
62.0 IPS |
|
Image Super-Resolution (SP)
|
100% |
9724
359.1 IPS |
|
Image Super-Resolution (HP)
|
100% |
9980
368.5 IPS |
|
Image Super-Resolution (Q)
|
98% |
7405
274.3 IPS |
|
Text Classification (SP)
|
100% |
2189
2.92 KIPS |
|
Text Classification (HP)
|
100% |
3789
5.06 KIPS |
|
Text Classification (Q)
|
93% |
3672
4.93 KIPS |
|
Machine Translation (SP)
|
100% |
1199
20.7 IPS |
|
Machine Translation (HP)
|
100% |
1276
22.0 IPS |
|
Machine Translation (Q)
|
98% |
1295
22.4 IPS |