Upload Date | May 18 2024 08:53 AM |
Views | 6 |
System Information | |
---|---|
Operating System | iOS 17.5 |
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% |
1741
325.8 IPS |
|
Image Classification (F16)
|
100% |
6177
1.16 KIPS |
|
Image Classification (I8)
|
99% |
6372
1.19 KIPS |
|
Image Segmentation (F32)
|
100% |
853
14.2 IPS |
|
Image Segmentation (F16)
|
100% |
3952
66.0 IPS |
|
Image Segmentation (I8)
|
100% |
3941
65.8 IPS |
|
Pose Estimation (F32)
|
100% |
16039
19.4 IPS |
|
Pose Estimation (F16)
|
100% |
63301
76.7 IPS |
|
Pose Estimation (I8)
|
100% |
64576
78.2 IPS |
|
Object Detection (F32)
|
100% |
1595
119.1 IPS |
|
Object Detection (F16)
|
100% |
4144
309.4 IPS |
|
Object Detection (I8)
|
97% |
1545
115.3 IPS |
|
Face Detection (F32)
|
100% |
5822
69.2 IPS |
|
Face Detection (F16)
|
97% |
11661
138.6 IPS |
|
Face Detection (I8)
|
96% |
11597
137.9 IPS |
|
Depth Estimation (F32)
|
100% |
12306
95.4 IPS |
|
Depth Estimation (F16)
|
100% |
41362
320.8 IPS |
|
Depth Estimation (I8)
|
37% |
45753
354.8 IPS |
|
Style Transfer (F32)
|
100% |
26488
34.8 IPS |
|
Style Transfer (F16)
|
100% |
112275
147.7 IPS |
|
Style Transfer (I8)
|
100% |
117668
154.8 IPS |
|
Image Super-Resolution (F32)
|
100% |
5001
178.6 IPS |
|
Image Super-Resolution (F16)
|
100% |
18256
652.0 IPS |
|
Image Super-Resolution (I8)
|
100% |
18192
649.7 IPS |
|
Text Classification (F32)
|
100% |
1183
1.70 KIPS |
|
Text Classification (F16)
|
100% |
2486
3.57 KIPS |
|
Text Classification (I8)
|
96% |
2264
3.25 KIPS |
|
Machine Translation (F32)
|
100% |
582
10.7 IPS |
|
Machine Translation (F16)
|
100% |
1747
32.1 IPS |
|
Machine Translation (I8)
|
99% |
585
10.8 IPS |