Upload Date | August 21 2024 09:52 AM |
Views | 1 |
System Information | |
---|---|
Operating System | Android 13 |
Model | Punkt MC02 |
Model ID | Punkt MC02 |
Motherboard | k6877v1_64_k419 |
CPU Information | |
---|---|
Name | ARM MT6877V/ZA |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 65 architecture 8 variant 1 part 3393 revision 0 |
Base Frequency | 2.00 GHz |
Cluster 1 | 6 Cores @ 2.00 GHz |
Cluster 2 | 2 Cores @ 2.40 GHz |
Memory Information | |
---|---|
Size | 5.54 GB |
Inference Information | |
---|---|
Framework | TensorFlow Lite |
Backend | GPU |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
158
29.6 IPS |
|
Image Classification (F16)
|
100% |
287
53.8 IPS |
|
Image Classification (I8)
|
97% |
261
48.9 IPS |
|
Image Segmentation (F32)
|
100% |
214
3.57 IPS |
|
Image Segmentation (F16)
|
100% |
342
5.71 IPS |
|
Image Segmentation (I8)
|
98% |
331
5.53 IPS |
|
Pose Estimation (F32)
|
100% |
148
0.18 IPS |
|
Pose Estimation (F16)
|
100% |
173
0.21 IPS |
|
Pose Estimation (I8)
|
100% |
173
0.21 IPS |
|
Object Detection (F32)
|
100% |
123
9.15 IPS |
|
Object Detection (F16)
|
100% |
187
14.0 IPS |
|
Object Detection (I8)
|
62% |
179
13.4 IPS |
|
Face Detection (F32)
|
100% |
517
6.15 IPS |
|
Face Detection (F16)
|
98% |
710
8.45 IPS |
|
Face Detection (I8)
|
86% |
740
8.79 IPS |
|
Depth Estimation (F32)
|
100% |
291
2.26 IPS |
|
Depth Estimation (F16)
|
100% |
376
2.92 IPS |
|
Depth Estimation (I8)
|
95% |
369
2.86 IPS |
|
Style Transfer (F32)
|
100% |
582
0.77 IPS |
|
Style Transfer (F16)
|
100% |
819
1.08 IPS |
|
Style Transfer (I8)
|
98% |
818
1.08 IPS |
|
Image Super-Resolution (F32)
|
100% |
157
5.59 IPS |
|
Image Super-Resolution (F16)
|
100% |
243
8.68 IPS |
|
Image Super-Resolution (I8)
|
98% |
240
8.56 IPS |
|
Text Classification (F32)
|
100% |
145
208.8 IPS |
|
Text Classification (F16)
|
100% |
144
206.6 IPS |
|
Text Classification (I8)
|
92% |
311
446.5 IPS |
|
Machine Translation (F32)
|
100% |
241
4.43 IPS |
|
Machine Translation (F16)
|
100% |
243
4.46 IPS |
|
Machine Translation (I8)
|
64% |
314
5.79 IPS |