Upload Date | August 15 2024 07:24 PM |
Views | 1 |
System Information | |
---|---|
Operating System | iOS 17.6.1 |
Model | iPad16,3 |
Model ID | iPad16,3 |
Motherboard | J717AP |
CPU Information | |
---|---|
Name | ARM |
Topology | 1 Processor, 9 Cores |
Identifier | ARM |
Base Frequency | 4.41 GHz |
Cluster 1 | 3 Cores |
Cluster 2 | 6 Cores |
L1 Instruction Cache | 128 KB x 1 |
L1 Data Cache | 64.0 KB x 1 |
L2 Cache | 4.00 MB x 1 |
Memory Information | |
---|---|
Size | 7.28 GB |
Inference Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
4041
756.2 IPS |
|
Image Classification (F16)
|
100% |
8270
1.55 KIPS |
|
Image Classification (I8)
|
99% |
8911
1.67 KIPS |
|
Image Segmentation (F32)
|
100% |
1836
30.7 IPS |
|
Image Segmentation (F16)
|
100% |
2192
36.6 IPS |
|
Image Segmentation (I8)
|
100% |
2281
38.1 IPS |
|
Pose Estimation (F32)
|
100% |
26036
31.5 IPS |
|
Pose Estimation (F16)
|
100% |
98983
119.9 IPS |
|
Pose Estimation (I8)
|
100% |
100757
122.0 IPS |
|
Object Detection (F32)
|
100% |
2438
182.0 IPS |
|
Object Detection (F16)
|
100% |
5489
409.8 IPS |
|
Object Detection (I8)
|
97% |
3279
244.8 IPS |
|
Face Detection (F32)
|
100% |
11001
130.8 IPS |
|
Face Detection (F16)
|
97% |
13492
160.4 IPS |
|
Face Detection (I8)
|
96% |
13603
161.7 IPS |
|
Depth Estimation (F32)
|
100% |
16001
124.1 IPS |
|
Depth Estimation (F16)
|
100% |
43414
336.7 IPS |
|
Depth Estimation (I8)
|
37% |
45434
352.3 IPS |
|
Style Transfer (F32)
|
100% |
54173
71.3 IPS |
|
Style Transfer (F16)
|
100% |
154636
203.4 IPS |
|
Style Transfer (I8)
|
100% |
154610
203.4 IPS |
|
Image Super-Resolution (F32)
|
100% |
9644
344.4 IPS |
|
Image Super-Resolution (F16)
|
100% |
19331
690.4 IPS |
|
Image Super-Resolution (I8)
|
100% |
21695
774.8 IPS |
|
Text Classification (F32)
|
100% |
1405
2.02 KIPS |
|
Text Classification (F16)
|
100% |
1283
1.84 KIPS |
|
Text Classification (I8)
|
96% |
1046
1.50 KIPS |
|
Machine Translation (F32)
|
100% |
685
12.6 IPS |
|
Machine Translation (F16)
|
100% |
1790
32.9 IPS |
|
Machine Translation (I8)
|
99% |
773
14.2 IPS |