Upload Date | May 09 2024 10:49 AM |
Views | 1 |
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% |
1617
302.6 IPS |
|
Image Classification (F16)
|
100% |
7067
1.32 KIPS |
|
Image Classification (I8)
|
99% |
6275
1.17 KIPS |
|
Image Segmentation (F32)
|
100% |
831
13.9 IPS |
|
Image Segmentation (F16)
|
100% |
3898
65.1 IPS |
|
Image Segmentation (I8)
|
100% |
3873
64.7 IPS |
|
Pose Estimation (F32)
|
100% |
16066
19.5 IPS |
|
Pose Estimation (F16)
|
100% |
62514
75.7 IPS |
|
Pose Estimation (I8)
|
100% |
63453
76.8 IPS |
|
Object Detection (F32)
|
100% |
1438
107.4 IPS |
|
Object Detection (F16)
|
100% |
4126
308.0 IPS |
|
Object Detection (I8)
|
97% |
1553
116.0 IPS |
|
Face Detection (F32)
|
100% |
6086
72.4 IPS |
|
Face Detection (F16)
|
97% |
11656
138.6 IPS |
|
Face Detection (I8)
|
96% |
11653
138.6 IPS |
|
Depth Estimation (F32)
|
100% |
12191
94.5 IPS |
|
Depth Estimation (F16)
|
100% |
40941
317.5 IPS |
|
Depth Estimation (I8)
|
37% |
42505
329.6 IPS |
|
Style Transfer (F32)
|
100% |
27440
36.1 IPS |
|
Style Transfer (F16)
|
100% |
112302
147.7 IPS |
|
Style Transfer (I8)
|
100% |
118034
155.3 IPS |
|
Image Super-Resolution (F32)
|
100% |
4730
168.9 IPS |
|
Image Super-Resolution (F16)
|
100% |
18173
649.0 IPS |
|
Image Super-Resolution (I8)
|
100% |
18169
648.9 IPS |
|
Text Classification (F32)
|
100% |
1166
1.68 KIPS |
|
Text Classification (F16)
|
100% |
2315
3.33 KIPS |
|
Text Classification (I8)
|
96% |
2332
3.35 KIPS |
|
Machine Translation (F32)
|
100% |
572
10.5 IPS |
|
Machine Translation (F16)
|
100% |
1757
32.3 IPS |
|
Machine Translation (I8)
|
99% |
582
10.7 IPS |