User | Petenka315 |
Upload Date | August 19 2024 02:48 PM |
Views | 5 |
AI Information | |
---|---|
Framework | Core ML |
Backend | GPU |
Device | Apple M2 |
System Information | |
---|---|
Operating System | iOS 17.5.1 |
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 | 7.33 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
3548
659.7 IPS |
|
Image Classification (HP)
|
100% |
3390
630.4 IPS |
|
Image Classification (Q)
|
99% |
3133
584.4 IPS |
|
Image Segmentation (SP)
|
100% |
3994
64.8 IPS |
|
Image Segmentation (HP)
|
100% |
4898
79.4 IPS |
|
Image Segmentation (Q)
|
100% |
4792
77.7 IPS |
|
Pose Estimation (SP)
|
100% |
24548
28.6 IPS |
|
Pose Estimation (HP)
|
100% |
26170
30.5 IPS |
|
Pose Estimation (Q)
|
96% |
23390
27.4 IPS |
|
Object Detection (SP)
|
100% |
3547
281.3 IPS |
|
Object Detection (HP)
|
100% |
3568
283.0 IPS |
|
Object Detection (Q)
|
92% |
2757
220.1 IPS |
|
Face Detection (SP)
|
100% |
9808
116.5 IPS |
|
Face Detection (HP)
|
100% |
11241
133.6 IPS |
|
Face Detection (Q)
|
100% |
7708
91.6 IPS |
|
Depth Estimation (SP)
|
100% |
16603
127.9 IPS |
|
Depth Estimation (HP)
|
99% |
17739
136.7 IPS |
|
Depth Estimation (Q)
|
97% |
17487
135.2 IPS |
|
Style Transfer (SP)
|
100% |
42215
54.3 IPS |
|
Style Transfer (HP)
|
100% |
48272
62.1 IPS |
|
Style Transfer (Q)
|
100% |
48185
61.9 IPS |
|
Image Super-Resolution (SP)
|
100% |
9490
350.4 IPS |
|
Image Super-Resolution (HP)
|
100% |
10164
375.3 IPS |
|
Image Super-Resolution (Q)
|
98% |
7670
284.2 IPS |
|
Text Classification (SP)
|
100% |
1190
1.59 KIPS |
|
Text Classification (HP)
|
100% |
800
1.07 KIPS |
|
Text Classification (Q)
|
93% |
795
1.07 KIPS |
|
Machine Translation (SP)
|
100% |
953
16.4 IPS |
|
Machine Translation (HP)
|
100% |
993
17.1 IPS |
|
Machine Translation (Q)
|
98% |
1438
24.9 IPS |