| User | Takayuki1970 |
| Upload Date | January 22 2026 09:27 AM |
| Views | 15 |
| AI Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | GPU |
| Device | placeholder |
| System Information | |
|---|---|
| Operating System | Android 13 |
| Model | Google hatch |
| Model ID | Google hatch |
| Motherboard | helios |
| CPU Information | |
|---|---|
| Name | placeholder |
| Topology | 1 Processor, 8 Cores |
| Identifier | ARM implementer 78 architecture 8 variant 2 part 0 revision 1 |
| Base Frequency | 0 MHz |
| Cluster 1 | 8 Cores |
| Memory Information | |
|---|---|
| Size | 14.66 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
0% |
0
2.26 KIPS |
|
|
Image Classification (HP)
|
0% |
0
2.79 KIPS |
|
|
Image Classification (Q)
|
0% |
0
1.86 KIPS |
|
|
Image Segmentation (SP)
|
73% |
19407
335.4 IPS |
|
|
Image Segmentation (HP)
|
73% |
19878
343.5 IPS |
|
|
Image Segmentation (Q)
|
73% |
2179
37.6 IPS |
|
|
Pose Estimation (SP)
|
0% |
0
1.19 KIPS |
|
|
Pose Estimation (HP)
|
0% |
0
1.19 KIPS |
|
|
Pose Estimation (Q)
|
0% |
0
399.5 IPS |
|
|
Object Detection (SP)
|
0% |
0
1.35 KIPS |
|
|
Object Detection (HP)
|
0% |
0
1.40 KIPS |
|
|
Object Detection (Q)
|
0% |
0
1.30 KIPS |
|
|
Face Detection (SP)
|
0% |
0
460.7 IPS |
|
|
Face Detection (HP)
|
0% |
0
478.0 IPS |
|
|
Face Detection (Q)
|
0% |
0
182.6 IPS |
|
|
Depth Estimation (SP)
|
0% |
0
1.47 KIPS |
|
|
Depth Estimation (HP)
|
0% |
0
1.35 KIPS |
|
|
Depth Estimation (Q)
|
0% |
0
1.46 KIPS |
|
|
Style Transfer (SP)
|
32% |
169636
2.13 KIPS |
|
|
Style Transfer (HP)
|
32% |
167878
2.11 KIPS |
|
|
Style Transfer (Q)
|
32% |
43920
547.8 IPS |
|
|
Image Super-Resolution (SP)
|
1% |
0
2.39 KIPS |
|
|
Image Super-Resolution (HP)
|
1% |
0
2.60 KIPS |
|
|
Image Super-Resolution (Q)
|
1% |
0
831.3 IPS |
|
|
Text Classification (SP)
|
100% |
115
153.8 IPS |
|
|
Text Classification (HP)
|
100% |
125
167.1 IPS |
|
|
Text Classification (Q)
|
91% |
44
59.7 IPS |
|
|
Machine Translation (SP)
|
100% |
178
3.06 IPS |
|
|
Machine Translation (HP)
|
100% |
178
3.06 IPS |
|
|
Machine Translation (Q)
|
57% |
50
1.23 IPS |