Upload Date | July 18 2024 02:44 PM |
Views | 1 |
System Information | |
---|---|
Operating System | iOS 17.5.1 |
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 | Neural Engine |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
1476
276.1 IPS |
|
Image Classification (F16)
|
100% |
6158
1.15 KIPS |
|
Image Classification (I8)
|
99% |
6332
1.18 KIPS |
|
Image Segmentation (F32)
|
100% |
838
14.0 IPS |
|
Image Segmentation (F16)
|
100% |
3981
66.5 IPS |
|
Image Segmentation (I8)
|
100% |
3964
66.2 IPS |
|
Pose Estimation (F32)
|
100% |
16561
20.1 IPS |
|
Pose Estimation (F16)
|
100% |
61983
75.1 IPS |
|
Pose Estimation (I8)
|
100% |
63212
76.5 IPS |
|
Object Detection (F32)
|
100% |
1397
104.3 IPS |
|
Object Detection (F16)
|
100% |
4204
313.8 IPS |
|
Object Detection (I8)
|
97% |
1641
122.5 IPS |
|
Face Detection (F32)
|
100% |
5892
70.1 IPS |
|
Face Detection (F16)
|
97% |
11661
138.7 IPS |
|
Face Detection (I8)
|
96% |
11664
138.7 IPS |
|
Depth Estimation (F32)
|
100% |
12292
95.3 IPS |
|
Depth Estimation (F16)
|
100% |
39941
309.7 IPS |
|
Depth Estimation (I8)
|
37% |
41955
325.4 IPS |
|
Style Transfer (F32)
|
100% |
27049
35.6 IPS |
|
Style Transfer (F16)
|
100% |
112024
147.4 IPS |
|
Style Transfer (I8)
|
100% |
119466
157.1 IPS |
|
Image Super-Resolution (F32)
|
100% |
5020
179.3 IPS |
|
Image Super-Resolution (F16)
|
100% |
18173
649.0 IPS |
|
Image Super-Resolution (I8)
|
100% |
18100
646.4 IPS |
|
Text Classification (F32)
|
100% |
1170
1.68 KIPS |
|
Text Classification (F16)
|
100% |
2323
3.34 KIPS |
|
Text Classification (I8)
|
96% |
2367
3.40 KIPS |
|
Machine Translation (F32)
|
100% |
577
10.6 IPS |
|
Machine Translation (F16)
|
100% |
1757
32.3 IPS |
|
Machine Translation (I8)
|
99% |
582
10.7 IPS |