User | AdrienRL |
Upload Date | August 16 2024 03:34 AM |
Views | 4 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
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% |
1370
254.7 IPS |
|
Image Classification (HP)
|
100% |
14483
2.69 KIPS |
|
Image Classification (Q)
|
99% |
15274
2.85 KIPS |
|
Image Segmentation (SP)
|
100% |
1549
25.1 IPS |
|
Image Segmentation (HP)
|
100% |
9217
149.4 IPS |
|
Image Segmentation (Q)
|
100% |
8986
145.7 IPS |
|
Pose Estimation (SP)
|
100% |
6881
8.03 IPS |
|
Pose Estimation (HP)
|
100% |
99798
116.4 IPS |
|
Pose Estimation (Q)
|
94% |
100959
118.4 IPS |
|
Object Detection (SP)
|
100% |
1557
123.5 IPS |
|
Object Detection (HP)
|
99% |
14387
1.14 KIPS |
|
Object Detection (Q)
|
91% |
16982
1.36 KIPS |
|
Face Detection (SP)
|
100% |
3163
37.6 IPS |
|
Face Detection (HP)
|
100% |
21654
257.3 IPS |
|
Face Detection (Q)
|
100% |
33797
401.6 IPS |
|
Depth Estimation (SP)
|
100% |
5687
43.8 IPS |
|
Depth Estimation (HP)
|
99% |
74307
572.5 IPS |
|
Depth Estimation (Q)
|
97% |
81021
626.5 IPS |
|
Style Transfer (SP)
|
100% |
18927
24.3 IPS |
|
Style Transfer (HP)
|
100% |
154310
198.4 IPS |
|
Style Transfer (Q)
|
100% |
155308
199.7 IPS |
|
Image Super-Resolution (SP)
|
100% |
4121
152.2 IPS |
|
Image Super-Resolution (HP)
|
100% |
39199
1.45 KIPS |
|
Image Super-Resolution (Q)
|
98% |
47001
1.74 KIPS |
|
Text Classification (SP)
|
100% |
2244
3.00 KIPS |
|
Text Classification (HP)
|
100% |
3764
5.02 KIPS |
|
Text Classification (Q)
|
93% |
3713
4.98 KIPS |
|
Machine Translation (SP)
|
100% |
3589
61.8 IPS |
|
Machine Translation (HP)
|
100% |
2379
41.0 IPS |
|
Machine Translation (Q)
|
98% |
2378
41.1 IPS |