Upload Date | July 27 2024 07:39 AM |
Views | 1 |
System Information | |
---|---|
Operating System | Android 12 |
Model | Xiaomi Redmi 9T |
Model ID | Xiaomi M2010J19SY |
Motherboard | lemon |
Governor | schedutil |
CPU Information | |
---|---|
Name | Qualcomm Qualcomm |
Topology | 1 Processor, 8 Cores |
Identifier | ARM implementer 81 architecture 8 variant 10 part 2048 revision 2 |
Base Frequency | 1.80 GHz |
Cluster 1 | 4 Cores @ 1.80 GHz |
Cluster 2 | 4 Cores @ 2.02 GHz |
Memory Information | |
---|---|
Size | 3.63 GB |
Inference Information | |
---|---|
Framework | TensorFlow Lite |
Backend | CPU |
Device | Default |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
136
25.5 IPS |
|
Image Classification (F16)
|
100% |
136
25.5 IPS |
|
Image Classification (I8)
|
97% |
183
34.2 IPS |
|
Image Segmentation (F32)
|
100% |
169
2.83 IPS |
|
Image Segmentation (F16)
|
100% |
185
3.09 IPS |
|
Image Segmentation (I8)
|
98% |
208
3.47 IPS |
|
Pose Estimation (F32)
|
100% |
223
0.27 IPS |
|
Pose Estimation (F16)
|
100% |
219
0.27 IPS |
|
Pose Estimation (I8)
|
100% |
643
0.78 IPS |
|
Object Detection (F32)
|
100% |
131
9.77 IPS |
|
Object Detection (F16)
|
100% |
128
9.58 IPS |
|
Object Detection (I8)
|
61% |
205
15.3 IPS |
|
Face Detection (F32)
|
100% |
277
3.29 IPS |
|
Face Detection (F16)
|
100% |
276
3.28 IPS |
|
Face Detection (I8)
|
86% |
423
5.03 IPS |
|
Depth Estimation (F32)
|
100% |
246
1.91 IPS |
|
Depth Estimation (F16)
|
100% |
251
1.95 IPS |
|
Depth Estimation (I8)
|
95% |
442
3.42 IPS |
|
Style Transfer (F32)
|
100% |
367
0.48 IPS |
|
Style Transfer (F16)
|
100% |
365
0.48 IPS |
|
Style Transfer (I8)
|
98% |
863
1.14 IPS |
|
Image Super-Resolution (F32)
|
100% |
153
5.47 IPS |
|
Image Super-Resolution (F16)
|
100% |
151
5.40 IPS |
|
Image Super-Resolution (I8)
|
98% |
322
11.5 IPS |
|
Text Classification (F32)
|
100% |
159
228.4 IPS |
|
Text Classification (F16)
|
100% |
161
230.9 IPS |
|
Text Classification (I8)
|
92% |
118
169.9 IPS |
|
Machine Translation (F32)
|
100% |
298
5.49 IPS |
|
Machine Translation (F16)
|
100% |
296
5.45 IPS |
|
Machine Translation (I8)
|
64% |
134
2.46 IPS |