User | AdrienRL |
Upload Date | August 16 2024 03:38 AM |
Views | 3 |
AI Information | |
---|---|
Framework | Core ML |
Backend | GPU |
Device | Apple M2 |
System Information | |
---|---|
Operating System | iOS 18.1 |
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% |
3656
679.9 IPS |
|
Image Classification (HP)
|
100% |
3776
702.3 IPS |
|
Image Classification (Q)
|
99% |
3282
612.2 IPS |
|
Image Segmentation (SP)
|
100% |
4063
65.9 IPS |
|
Image Segmentation (HP)
|
100% |
5047
81.8 IPS |
|
Image Segmentation (Q)
|
100% |
4933
80.0 IPS |
|
Pose Estimation (SP)
|
100% |
24733
28.9 IPS |
|
Pose Estimation (HP)
|
100% |
26282
30.7 IPS |
|
Pose Estimation (Q)
|
97% |
23706
27.8 IPS |
|
Object Detection (SP)
|
100% |
3707
294.0 IPS |
|
Object Detection (HP)
|
100% |
3732
296.0 IPS |
|
Object Detection (Q)
|
91% |
2856
228.2 IPS |
|
Face Detection (SP)
|
100% |
10359
123.1 IPS |
|
Face Detection (HP)
|
100% |
11940
141.9 IPS |
|
Face Detection (Q)
|
100% |
8246
98.0 IPS |
|
Depth Estimation (SP)
|
100% |
16809
129.5 IPS |
|
Depth Estimation (HP)
|
99% |
17968
138.4 IPS |
|
Depth Estimation (Q)
|
97% |
2800
21.7 IPS |
|
Style Transfer (SP)
|
100% |
42533
54.7 IPS |
|
Style Transfer (HP)
|
100% |
48656
62.5 IPS |
|
Style Transfer (Q)
|
100% |
48489
62.3 IPS |
|
Image Super-Resolution (SP)
|
100% |
9886
365.1 IPS |
|
Image Super-Resolution (HP)
|
100% |
10209
377.0 IPS |
|
Image Super-Resolution (Q)
|
98% |
7574
280.6 IPS |
|
Text Classification (SP)
|
100% |
2214
2.95 KIPS |
|
Text Classification (HP)
|
100% |
3719
4.96 KIPS |
|
Text Classification (Q)
|
93% |
3698
4.96 KIPS |
|
Machine Translation (SP)
|
100% |
1593
27.4 IPS |
|
Machine Translation (HP)
|
100% |
1570
27.0 IPS |
|
Machine Translation (Q)
|
98% |
1337
23.1 IPS |