BiT-S R50x3 Feature Vector
BiT-S R50x3 Feature Vector is Google's image to text model. A Big Transfer (BiT-S) vision model with a ResNet-50x3 backbone trained on ILSVRC-2012, producing feature vectors with increased width for richer image representations.
google-bit-s-r50x3-ilsvrc2012 |
| 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 |
|---|---|---|---|---|---|
| BiT-S R50x3 Feature Vector | β | β | β | β | Current |
| BiT-M Classification | β | β | β | β | Available |
| BiT-M Feature Vector | β | β | β | β | Available |
| BiT-M R50x3 | β | β | β | β | Available |
| BiT-M R50x3 ImageNet-21k | β | β | β | β | Available |
| BiT-M R50x3 ImageNet-21k | β | β | β | β | Available |
| BiT-S R101x1 | β | β | β | β | Available |
| BiT-S R101x1 Feature Vector | β | β | β | β | Available |
| BiT-S R101x3 | β | β | β | β | Available |
| BiT-S R101x3 Feature Vector | β | β | β | β | Available |
| BiT-S R152x4 | β | β | β | β | Available |