Upload Date | January 21 2024 01:14 PM |
Views | 1 |
System Information | |
---|---|
Operating System | iOS 17.2 |
Model | iPad Air (5th generation) |
Model ID | iPad13,16 |
Motherboard | J407AP |
CPU Information | |
---|---|
Name | Apple M1 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM |
Base Frequency | 3.19 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 | 7.47 GB |
Inference Information | |
---|---|
Framework | Core ML |
Backend | CPU |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
450
84.2 IPS |
|
Image Classification (F16)
|
100% |
541
101.3 IPS |
|
Image Classification (I8)
|
99% |
892
166.9 IPS |
|
Image Segmentation (F32)
|
100% |
317
5.29 IPS |
|
Image Segmentation (F16)
|
100% |
290
4.84 IPS |
|
Image Segmentation (I8)
|
100% |
300
5.02 IPS |
|
Pose Estimation (F32)
|
100% |
2834
3.43 IPS |
|
Pose Estimation (F16)
|
100% |
10528
12.7 IPS |
|
Pose Estimation (I8)
|
100% |
8702
10.5 IPS |
|
Object Detection (F32)
|
100% |
891
66.5 IPS |
|
Object Detection (F16)
|
100% |
456
34.0 IPS |
|
Object Detection (I8)
|
97% |
633
47.2 IPS |
|
Face Detection (F32)
|
100% |
1219
14.5 IPS |
|
Face Detection (F16)
|
100% |
1361
16.2 IPS |
|
Face Detection (I8)
|
99% |
859
10.2 IPS |
|
Depth Estimation (F32)
|
100% |
2269
17.6 IPS |
|
Depth Estimation (F16)
|
99% |
2382
18.5 IPS |
|
Depth Estimation (I8)
|
99% |
3638
28.2 IPS |
|
Style Transfer (F32)
|
100% |
6307
8.30 IPS |
|
Style Transfer (F16)
|
100% |
5916
7.78 IPS |
|
Style Transfer (I8)
|
100% |
7022
9.24 IPS |
|
Image Super-Resolution (F32)
|
100% |
1083
38.7 IPS |
|
Image Super-Resolution (F16)
|
100% |
976
34.8 IPS |
|
Image Super-Resolution (I8)
|
100% |
1191
42.5 IPS |
|
Text Classification (F32)
|
100% |
560
804.2 IPS |
|
Text Classification (F16)
|
100% |
266
383.0 IPS |
|
Text Classification (I8)
|
96% |
710
1.02 KIPS |
|
Machine Translation (F32)
|
100% |
380
6.99 IPS |
|
Machine Translation (F16)
|
99% |
360
6.63 IPS |
|
Machine Translation (I8)
|
99% |
149
2.75 IPS |