Upload Date | January 21 2024 01:23 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% |
379
70.9 IPS |
|
Image Classification (F16)
|
100% |
360
67.3 IPS |
|
Image Classification (I8)
|
99% |
213
39.9 IPS |
|
Image Segmentation (F32)
|
100% |
276
4.61 IPS |
|
Image Segmentation (F16)
|
100% |
239
4.00 IPS |
|
Image Segmentation (I8)
|
100% |
232
3.87 IPS |
|
Pose Estimation (F32)
|
100% |
1557
1.89 IPS |
|
Pose Estimation (F16)
|
100% |
6325
7.66 IPS |
|
Pose Estimation (I8)
|
100% |
1142
1.38 IPS |
|
Object Detection (F32)
|
100% |
375
28.0 IPS |
|
Object Detection (F16)
|
100% |
443
33.0 IPS |
|
Object Detection (I8)
|
97% |
192
14.3 IPS |
|
Face Detection (F32)
|
100% |
766
9.11 IPS |
|
Face Detection (F16)
|
100% |
1031
12.3 IPS |
|
Face Detection (I8)
|
99% |
427
5.07 IPS |
|
Depth Estimation (F32)
|
100% |
1589
12.3 IPS |
|
Depth Estimation (F16)
|
99% |
681
5.28 IPS |
|
Depth Estimation (I8)
|
99% |
1721
13.3 IPS |
|
Style Transfer (F32)
|
100% |
3652
4.80 IPS |
|
Style Transfer (F16)
|
100% |
2962
3.90 IPS |
|
Style Transfer (I8)
|
100% |
3356
4.42 IPS |
|
Image Super-Resolution (F32)
|
100% |
623
22.3 IPS |
|
Image Super-Resolution (F16)
|
100% |
1160
41.4 IPS |
|
Image Super-Resolution (I8)
|
100% |
1907
68.1 IPS |
|
Text Classification (F32)
|
100% |
266
382.8 IPS |
|
Text Classification (F16)
|
100% |
148
213.0 IPS |
|
Text Classification (I8)
|
96% |
144
207.3 IPS |
|
Machine Translation (F32)
|
100% |
138
2.53 IPS |
|
Machine Translation (F16)
|
99% |
192
3.53 IPS |
|
Machine Translation (I8)
|
99% |
133
2.45 IPS |