User | visualvictor |
Upload Date | November 10 2024 06:08 PM |
Views | 16 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | ARM |
System Information | |
---|---|
Operating System | iOS 18.1 |
Model | iPad16,3 |
Model ID | iPad16,3 |
Motherboard | J717AP |
CPU Information | |
---|---|
Name | ARM |
Topology | 1 Processor, 9 Cores |
Identifier | ARM |
Base Frequency | 4.04 GHz |
Cluster 1 | 3 Cores |
Cluster 2 | 6 Cores |
Memory Information | |
---|---|
Size | 7.29 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1966
365.6 IPS |
|
Image Classification (HP)
|
100% |
18549
3.45 KIPS |
|
Image Classification (Q)
|
97% |
26923
5.02 KIPS |
|
Image Segmentation (SP)
|
100% |
2140
34.7 IPS |
|
Image Segmentation (HP)
|
100% |
22218
360.2 IPS |
|
Image Segmentation (Q)
|
99% |
30633
496.6 IPS |
|
Pose Estimation (SP)
|
100% |
10034
11.7 IPS |
|
Pose Estimation (HP)
|
100% |
123928
144.6 IPS |
|
Pose Estimation (Q)
|
95% |
234180
274.5 IPS |
|
Object Detection (SP)
|
100% |
2216
175.8 IPS |
|
Object Detection (HP)
|
100% |
18549
1.47 KIPS |
|
Object Detection (Q)
|
91% |
26661
2.13 KIPS |
|
Face Detection (SP)
|
100% |
3997
47.5 IPS |
|
Face Detection (HP)
|
100% |
43387
515.5 IPS |
|
Face Detection (Q)
|
100% |
63615
755.9 IPS |
|
Depth Estimation (SP)
|
100% |
8325
64.1 IPS |
|
Depth Estimation (HP)
|
99% |
99118
763.6 IPS |
|
Depth Estimation (Q)
|
85% |
168781
1.32 KIPS |
|
Style Transfer (SP)
|
100% |
25195
32.4 IPS |
|
Style Transfer (HP)
|
100% |
235866
303.2 IPS |
|
Style Transfer (Q)
|
96% |
299789
386.9 IPS |
|
Image Super-Resolution (SP)
|
100% |
5929
218.9 IPS |
|
Image Super-Resolution (HP)
|
100% |
48762
1.80 KIPS |
|
Image Super-Resolution (Q)
|
99% |
84974
3.14 KIPS |
|
Text Classification (SP)
|
100% |
3029
4.04 KIPS |
|
Text Classification (HP)
|
100% |
6398
8.54 KIPS |
|
Text Classification (Q)
|
93% |
6565
8.81 KIPS |
|
Machine Translation (SP)
|
100% |
3960
68.2 IPS |
|
Machine Translation (HP)
|
100% |
17164
295.7 IPS |
|
Machine Translation (Q)
|
98% |
18729
323.7 IPS |