Upload Date | January 12 2024 07:21 AM |
Views | 3 |
System Information | |
---|---|
Operating System | Android 13 |
Model | Google corsola |
Model ID | Google corsola |
Motherboard | rusty |
Governor | schedutil |
CPU Information | |
---|---|
Name | ARM ARMv8 |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 3 part 3339 revision 0 |
Base Frequency | 2.00 GHz |
Cluster 1 | 6 Cores @ 2.00 GHz |
Cluster 2 | 2 Cores @ 2.05 GHz |
Memory Information | |
---|---|
Size | 2.69 GB |
Inference Information | |
---|---|
Framework | TensorFlow Lite |
Backend | GPU |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
59
11.1 IPS |
|
Image Classification (F16)
|
100% |
55
10.4 IPS |
|
Image Classification (I8)
|
97% |
54
10.2 IPS |
|
Image Segmentation (F32)
|
100% |
81
1.36 IPS |
|
Image Segmentation (F16)
|
100% |
77
1.29 IPS |
|
Image Segmentation (I8)
|
98% |
77
1.29 IPS |
|
Pose Estimation (F32)
|
100% |
58
0.07 IPS |
|
Pose Estimation (F16)
|
100% |
42
0.05 IPS |
|
Pose Estimation (I8)
|
100% |
41
0.05 IPS |
|
Object Detection (F32)
|
100% |
51
3.84 IPS |
|
Object Detection (F16)
|
100% |
50
3.70 IPS |
|
Object Detection (I8)
|
56% |
50
3.73 IPS |
|
Face Detection (F32)
|
100% |
170
2.02 IPS |
|
Face Detection (F16)
|
98% |
169
2.01 IPS |
|
Face Detection (I8)
|
86% |
164
1.95 IPS |
|
Depth Estimation (F32)
|
100% |
112
0.87 IPS |
|
Depth Estimation (F16)
|
100% |
94
0.73 IPS |
|
Depth Estimation (I8)
|
94% |
93
0.72 IPS |
|
Style Transfer (F32)
|
100% |
240
0.32 IPS |
|
Style Transfer (F16)
|
100% |
199
0.26 IPS |
|
Style Transfer (I8)
|
98% |
199
0.26 IPS |
|
Image Super-Resolution (F32)
|
100% |
68
2.41 IPS |
|
Image Super-Resolution (F16)
|
100% |
59
2.12 IPS |
|
Image Super-Resolution (I8)
|
98% |
59
2.11 IPS |
|
Text Classification (F32)
|
100% |
84
120.1 IPS |
|
Text Classification (F16)
|
100% |
83
119.6 IPS |
|
Text Classification (I8)
|
92% |
190
273.3 IPS |
|
Machine Translation (F32)
|
100% |
159
2.93 IPS |
|
Machine Translation (F16)
|
100% |
160
2.95 IPS |
|
Machine Translation (I8)
|
64% |
225
4.15 IPS |