Google hatch
Geekbench ML Score
145
TensorFlow Lite CPU Inference Score
Geekbench ML 0.6.0 for Android AArch64
Result Information
| Upload Date | January 26 2024 06:10 AM |
| Views | 1 |
System Information
| System Information | |
|---|---|
| Operating System | Android 13 |
| Model | Google hatch |
| Model ID | Google hatch |
| Motherboard | helios |
| CPU Information | |
|---|---|
| Name | placeholder |
| Topology | 1 Processor, 4 Cores |
| Identifier | ARM implementer 78 architecture 8 variant 2 part 0 revision 1 |
| Base Frequency | 0 MHz |
| Cluster 1 | 4 Cores |
| Memory Information | |
|---|---|
| Size | 6.44 GB |
| Inference Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | CPU |
| Device | Default |
Inference Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (F32)
|
100% |
122
22.9 IPS |
|
|
Image Classification (F16)
|
100% |
114
21.3 IPS |
|
|
Image Classification (I8)
|
97% |
46
8.59 IPS |
|
|
Image Segmentation (F32)
|
100% |
142
2.37 IPS |
|
|
Image Segmentation (F16)
|
100% |
141
2.36 IPS |
|
|
Image Segmentation (I8)
|
98% |
49
0.82 IPS |
|
|
Pose Estimation (F32)
|
100% |
204
0.25 IPS |
|
|
Pose Estimation (F16)
|
100% |
205
0.25 IPS |
|
|
Pose Estimation (I8)
|
100% |
118
0.14 IPS |
|
|
Object Detection (F32)
|
100% |
123
9.15 IPS |
|
|
Object Detection (F16)
|
100% |
121
9.03 IPS |
|
|
Object Detection (I8)
|
61% |
54
4.02 IPS |
|
|
Face Detection (F32)
|
100% |
324
3.85 IPS |
|
|
Face Detection (F16)
|
100% |
323
3.84 IPS |
|
|
Face Detection (I8)
|
86% |
99
1.18 IPS |
|
|
Depth Estimation (F32)
|
100% |
279
2.16 IPS |
|
|
Depth Estimation (F16)
|
100% |
277
2.15 IPS |
|
|
Depth Estimation (I8)
|
95% |
134
1.04 IPS |
|
|
Style Transfer (F32)
|
100% |
507
0.67 IPS |
|
|
Style Transfer (F16)
|
100% |
496
0.65 IPS |
|
|
Style Transfer (I8)
|
98% |
324
0.43 IPS |
|
|
Image Super-Resolution (F32)
|
100% |
139
4.96 IPS |
|
|
Image Super-Resolution (F16)
|
100% |
137
4.89 IPS |
|
|
Image Super-Resolution (I8)
|
98% |
66
2.35 IPS |
|
|
Text Classification (F32)
|
100% |
143
205.4 IPS |
|
|
Text Classification (F16)
|
100% |
148
212.4 IPS |
|
|
Text Classification (I8)
|
92% |
36
52.2 IPS |
|
|
Machine Translation (F32)
|
100% |
241
4.44 IPS |
|
|
Machine Translation (F16)
|
100% |
236
4.35 IPS |
|
|
Machine Translation (I8)
|
64% |
69
1.27 IPS |
