Upload Date | January 21 2024 12:45 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 | GPU |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
807
151.1 IPS |
|
Image Classification (F16)
|
100% |
322
60.3 IPS |
|
Image Classification (I8)
|
99% |
679
127.0 IPS |
|
Image Segmentation (F32)
|
100% |
413
6.90 IPS |
|
Image Segmentation (F16)
|
100% |
476
7.96 IPS |
|
Image Segmentation (I8)
|
100% |
333
5.56 IPS |
|
Pose Estimation (F32)
|
100% |
2309
2.80 IPS |
|
Pose Estimation (F16)
|
100% |
3333
4.04 IPS |
|
Pose Estimation (I8)
|
100% |
6272
7.60 IPS |
|
Object Detection (F32)
|
100% |
531
39.6 IPS |
|
Object Detection (F16)
|
100% |
574
42.8 IPS |
|
Object Detection (I8)
|
97% |
622
46.4 IPS |
|
Face Detection (F32)
|
100% |
1614
19.2 IPS |
|
Face Detection (F16)
|
97% |
1160
13.8 IPS |
|
Face Detection (I8)
|
96% |
1332
15.8 IPS |
|
Depth Estimation (F32)
|
100% |
2724
21.1 IPS |
|
Depth Estimation (F16)
|
100% |
3393
26.3 IPS |
|
Depth Estimation (I8)
|
37% |
3122
24.2 IPS |
|
Style Transfer (F32)
|
100% |
7612
10.0 IPS |
|
Style Transfer (F16)
|
100% |
10842
14.3 IPS |
|
Style Transfer (I8)
|
100% |
8695
11.4 IPS |
|
Image Super-Resolution (F32)
|
100% |
1074
38.4 IPS |
|
Image Super-Resolution (F16)
|
100% |
1115
39.8 IPS |
|
Image Super-Resolution (I8)
|
100% |
2200
78.6 IPS |
|
Text Classification (F32)
|
100% |
1170
1.68 KIPS |
|
Text Classification (F16)
|
100% |
759
1.09 KIPS |
|
Text Classification (I8)
|
96% |
759
1.09 KIPS |
|
Machine Translation (F32)
|
100% |
168
3.09 IPS |
|
Machine Translation (F16)
|
100% |
150
2.76 IPS |
|
Machine Translation (I8)
|
99% |
179
3.29 IPS |