Upload Date | May 09 2024 08:45 AM |
Views | 3 |
System Information | |
---|---|
Operating System | Android 12 |
Model | KEYENCE DX-A600 |
Model ID | KEYENCE DX-A600 |
Motherboard | DX-A600_ |
CPU Information | |
---|---|
Name | ARM MT6762 |
Topology | 1 Processor, 4 Cores |
Identifier | ARM implementer 65 architecture 8 variant 0 part 3331 revision 4 |
Base Frequency | 2.00 GHz |
Cluster 1 | 4 Cores @ 2.00 GHz |
Memory Information | |
---|---|
Size | 3.75 GB |
Inference Information | |
---|---|
Framework | TensorFlow Lite |
Backend | NNAPI |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
22
4.14 IPS |
|
Image Classification (F16)
|
100% |
22
4.13 IPS |
|
Image Classification (I8)
|
97% |
36
6.78 IPS |
|
Image Segmentation (F32)
|
100% |
25
0.42 IPS |
|
Image Segmentation (F16)
|
100% |
25
0.42 IPS |
|
Image Segmentation (I8)
|
98% |
41
0.69 IPS |
|
Pose Estimation (F32)
|
100% |
31
0.04 IPS |
|
Pose Estimation (F16)
|
100% |
43
0.05 IPS |
|
Pose Estimation (I8)
|
100% |
73
0.09 IPS |
|
Object Detection (F32)
|
100% |
24
1.79 IPS |
|
Object Detection (F16)
|
100% |
24
1.79 IPS |
|
Object Detection (I8)
|
61% |
39
2.89 IPS |
|
Face Detection (F32)
|
100% |
55
0.65 IPS |
|
Face Detection (F16)
|
100% |
55
0.65 IPS |
|
Face Detection (I8)
|
86% |
95
1.13 IPS |
|
Depth Estimation (F32)
|
100% |
41
0.32 IPS |
|
Depth Estimation (F16)
|
100% |
40
0.31 IPS |
|
Depth Estimation (I8)
|
95% |
85
0.66 IPS |
|
Style Transfer (F32)
|
100% |
71
0.09 IPS |
|
Style Transfer (F16)
|
100% |
72
0.09 IPS |
|
Style Transfer (I8)
|
98% |
161
0.21 IPS |
|
Image Super-Resolution (F32)
|
100% |
24
0.87 IPS |
|
Image Super-Resolution (F16)
|
100% |
25
0.88 IPS |
|
Image Super-Resolution (I8)
|
98% |
49
1.75 IPS |
|
Text Classification (F32)
|
100% |
25
35.7 IPS |
|
Text Classification (F16)
|
100% |
26
37.7 IPS |
|
Text Classification (I8)
|
92% |
40
57.3 IPS |
|
Machine Translation (F32)
|
100% |
47
0.87 IPS |
|
Machine Translation (F16)
|
100% |
47
0.86 IPS |
|
Machine Translation (I8)
|
64% |
54
1.00 IPS |