BiT-M R101x1 ImageNet-21k
BiT-M R101x1 ImageNet-21k is Google's image to text model. A Big Transfer (BiT-M) image classification model using a ResNet-101x1 backbone pretrained on ImageNet-21k for large-scale visual recognition.
google-bit-m-r101x1-imagenet21k-classification |
| Image to Text |
| Active |
| Google |
| Image |
| Text |
Capabilities
Input1/5
·
✓
·
·
·
Output1/5
✓
·
·
·
·
Capabilities0/13
·
·
·
·
·
·
·
·
·
·
·
·
·
Versions
| Version | Released | Context | Input / 1M | Output / 1M | Status |
|---|---|---|---|---|---|
| BiT-M R101x1 ImageNet-21k | — | — | — | — | Current |
| BiT-M R101x3 | — | — | — | — | Available |
| BiT-M R101x3 ImageNet-21k | — | — | — | — | Available |
| BiT-M R101x3 ImageNet-21k Feature Vector | — | — | — | — | Available |
| BiT-M R152x4 | — | — | — | — | Available |
| BiT-M R152x4 ImageNet-21k | — | — | — | — | Available |
| BiT-M R50x1 | — | — | — | — | Available |
| BiT-M R50x1 Feature Vector | — | — | — | — | Available |