MobileNet 3
MobileNet 3 is Google's image to text model. A MobileNetV3 image classification model offering improved accuracy-efficiency trade-offs in small and large variants.
google-mobilenet-3 |
| Image to Text |
| Active |
| Google |
| Image |
| Text |
Capabilities
Input1/5
Β·
β
Β·
Β·
Β·
Output1/5
β
Β·
Β·
Β·
Β·
Capabilities0/13
Β·
Β·
Β·
Β·
Β·
Β·
Β·
Β·
Β·
Β·
Β·
Β·
Β·
Versions
| Version | Released | Context | Input / 1M | Output / 1M | Status |
|---|---|---|---|---|---|
| MobileNet 3 | β | β | β | β | Current |
| MobileNet V3 Large | β | β | β | β | Available |
| MobileNet 2 | β | β | β | β | Available |
| MobileNet 2 Classification | β | β | β | β | Available |
| MobileNet 2 Featurevector | β | β | β | β | Available |
| MobileNet V2 0.35 224 Feature Vector | β | β | β | β | Available |
| MobileNet V2 0.75 224 | β | β | β | β | Available |
| MobileNet V2 1.30 224 Feature Vector | β | β | β | β | Available |
| MobileNet V2 1.40 224 Feature Vector | β | β | β | β | Available |
| MobileNet V1 0.25 128 | β | β | β | β | Available |
| MobileNet V1 0.25 128 Feature Vector | β | β | β | β | Available |