Upload Date | January 05 2024 12:14 PM |
Views | 1 |
System Information | |
---|---|
Operating System | iOS 17.2 |
Model | iPad Pro (11-inch, 4th generation) |
Model ID | iPad14,3 |
Motherboard | J617AP |
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 |
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 | 7.34 GB |
Inference Information | |
---|---|
Framework | Core ML |
Backend | CPU |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
1247
233.3 IPS |
|
Image Classification (F16)
|
100% |
1099
205.7 IPS |
|
Image Classification (I8)
|
99% |
1099
205.7 IPS |
|
Image Segmentation (F32)
|
100% |
558
9.32 IPS |
|
Image Segmentation (F16)
|
100% |
503
8.41 IPS |
|
Image Segmentation (I8)
|
100% |
503
8.41 IPS |
|
Pose Estimation (F32)
|
100% |
5772
6.99 IPS |
|
Pose Estimation (F16)
|
100% |
12139
14.7 IPS |
|
Pose Estimation (I8)
|
100% |
12139
14.7 IPS |
|
Object Detection (F32)
|
100% |
1281
95.6 IPS |
|
Object Detection (F16)
|
100% |
1249
93.2 IPS |
|
Object Detection (I8)
|
97% |
1278
95.4 IPS |
|
Face Detection (F32)
|
100% |
2502
29.7 IPS |
|
Face Detection (F16)
|
100% |
2016
24.0 IPS |
|
Face Detection (I8)
|
99% |
2018
24.0 IPS |
|
Depth Estimation (F32)
|
100% |
4132
32.0 IPS |
|
Depth Estimation (F16)
|
99% |
4418
34.3 IPS |
|
Depth Estimation (I8)
|
99% |
4422
34.3 IPS |
|
Style Transfer (F32)
|
100% |
11360
14.9 IPS |
|
Style Transfer (F16)
|
100% |
13551
17.8 IPS |
|
Style Transfer (I8)
|
100% |
13539
17.8 IPS |
|
Image Super-Resolution (F32)
|
100% |
3252
116.1 IPS |
|
Image Super-Resolution (F16)
|
100% |
2901
103.6 IPS |
|
Image Super-Resolution (I8)
|
100% |
2905
103.7 IPS |
|
Text Classification (F32)
|
100% |
1132
1.63 KIPS |
|
Text Classification (F16)
|
100% |
762
1.10 KIPS |
|
Text Classification (I8)
|
96% |
763
1.10 KIPS |
|
Machine Translation (F32)
|
100% |
924
17.0 IPS |
|
Machine Translation (F16)
|
99% |
1055
19.4 IPS |
|
Machine Translation (I8)
|
99% |
921
17.0 IPS |