Faster R-CNN ResNet50 is Meta's image to text model. A Faster R-CNN object detection model with a ResNet-50 backbone, providing strong detection accuracy for general-purpose object localization.
Specifications
Canonical IDmeta-fasterrcnn-resnet50
TypeImage to Text
StatusActive
CreatorMetaMeta
Input ModalitiesImage
Output ModalitiesText

Capabilities

Input1/5
Text·
Image✓
Audio·
Video·
PDF·
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities0/13
Reasoning·
Adaptive Reasoning·
Function Calling·
Parallel Function Calling·
Structured Outputs·
Native JSON Schema·
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill·

Versions

VersionReleasedContextInput / 1MOutput / 1MStatus
Faster R-CNN MobileNet V3————Available
Faster R-CNN Inception-ResNet 2————Available
Faster R-CNN ResNet50————Current
Faster R-CNN————Available
Faster R-CNN ResNet-101————Available
Faster R-CNN ResNet-152————Available
Faster R-CNN ResNet-50————Available

Model IDs

meta-fasterrcnn-resnet50
pytorch-od1-fasterrcnn-resnet50-fpn