CenterNet ResNet-v1-50 is Google's image to text model. CenterNet object detection model with a ResNet-v1-50 backbone, offering a lighter-weight keypoint-based detection approach.
google-centernet-resnet50 |
| Image to Text |
| Active |
| Image |
| Text |
Capabilities
Input1/5
·
✓
·
·
·
Output1/5
✓
·
·
·
·
Capabilities0/13
·
·
·
·
·
·
·
·
·
·
·
·
·
Versions
| Version | Released | Context | Input / 1M | Output / 1M | Status |
|---|---|---|---|---|---|
| CenterNet ResNet-v1-50 | — | — | — | — | Current |
| CenterNet Hourglass | — | — | — | — | Available |
| CenterNet Hourglass Keypoints | — | — | — | — | Available |
| CenterNet ResNet-v1-101 | — | — | — | — | Available |
| CenterNet ResNet-v1-50 Keypoints | — | — | — | — | Available |
| CenterNet ResNet-v2-50 | — | — | — | — | Available |
| CenterNet ResNet-v2-50 Keypoints | — | — | — | — | Available |