User | idanbo |
Upload Date | October 24 2024 09:48 AM |
Views | 12 |
Notes | iPad mini(A17 Pro) |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | ARM |
System Information | |
---|---|
Operating System | iOS 18.0.1 |
Model | iPad16,2 |
Model ID | iPad16,2 |
Motherboard | J411AP |
CPU Information | |
---|---|
Name | ARM |
Topology | 1 Processor, 6 Cores |
Identifier | ARM |
Base Frequency | 3.78 GHz |
Cluster 1 | 2 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 7.73 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1739
323.5 IPS |
|
Image Classification (HP)
|
100% |
11309
2.10 KIPS |
|
Image Classification (Q)
|
97% |
16546
3.09 KIPS |
|
Image Segmentation (SP)
|
100% |
1701
27.6 IPS |
|
Image Segmentation (HP)
|
100% |
13087
212.1 IPS |
|
Image Segmentation (Q)
|
99% |
16020
259.7 IPS |
|
Pose Estimation (SP)
|
100% |
7877
9.19 IPS |
|
Pose Estimation (HP)
|
100% |
107173
125.1 IPS |
|
Pose Estimation (Q)
|
95% |
204488
239.7 IPS |
|
Object Detection (SP)
|
100% |
1838
145.8 IPS |
|
Object Detection (HP)
|
100% |
13525
1.07 KIPS |
|
Object Detection (Q)
|
91% |
19276
1.54 KIPS |
|
Face Detection (SP)
|
100% |
3327
39.5 IPS |
|
Face Detection (HP)
|
100% |
35844
425.9 IPS |
|
Face Detection (Q)
|
100% |
51115
607.4 IPS |
|
Depth Estimation (SP)
|
100% |
7144
55.0 IPS |
|
Depth Estimation (HP)
|
99% |
78543
605.1 IPS |
|
Depth Estimation (Q)
|
85% |
129686
1.01 KIPS |
|
Style Transfer (SP)
|
100% |
21318
27.4 IPS |
|
Style Transfer (HP)
|
100% |
208043
267.4 IPS |
|
Style Transfer (Q)
|
96% |
253543
327.2 IPS |
|
Image Super-Resolution (SP)
|
100% |
5063
186.9 IPS |
|
Image Super-Resolution (HP)
|
100% |
35522
1.31 KIPS |
|
Image Super-Resolution (Q)
|
99% |
58758
2.17 KIPS |
|
Text Classification (SP)
|
100% |
3213
4.29 KIPS |
|
Text Classification (HP)
|
100% |
3852
5.14 KIPS |
|
Text Classification (Q)
|
93% |
3353
4.50 KIPS |
|
Machine Translation (SP)
|
100% |
3344
57.6 IPS |
|
Machine Translation (HP)
|
100% |
6415
110.5 IPS |
|
Machine Translation (Q)
|
98% |
7771
134.3 IPS |