10 actions in 10 pieces of software · ranked by words, meaning and measured trust · 598 ms
modelrecord12,947 downloads/month
- object-detection
Task: object-detection
- object-detection
modelrecord12,556 downloads/month
- image-segmentation
Task: image-segmentation
- image-segmentation
modelrecord
- hardikdava/rf-detr
RF-DETR: SOTA Real-Time Object Detection Model
- hardikdava/rf-detr
modelrecord305,885 downloads/month
- image-classification
Task: image-classification
- image-classification
skillnvidia/skillsrecord
- tao-train-deformable-detr
Deformable DETR for 2D object detection. Uses deformable attention for efficient multi-scale feature processing, lighter than DINO with competitive accuracy. Use when training, evaluating, exporting, quantizing, or running inference for a TAO Deformable-DETR model. Trigger phrases include "train def
- tao-train-deformable-detr
modelrecord
- replicate/resnet
Classifies images with ResNet-50
- replicate/resnet
libraryultralytics/ultralyticsrecord4,251,823 downloads/month
- RT-DETR
- huggingface-vision-trainer
Trains and fine-tunes vision models for object detection (D-FINE, RT-DETR v2, DETR, YOLOS), image classification (timm models — MobileNetV3, MobileViT, ResNet, ViT/DINOv3 — plus any Transformers classifier), and SAM/SAM2 segmentation using Hugging Face Transformers on Hugging Face Jobs cloud GPUs. C
- huggingface-vision-trainer
- 9maesa-skillfound in code, not yet checkedno passport yet
MCP serverlancmd/maesa-skill
- run_pytorch_lulc
Run PyTorch LULC inference; native ResNet-50 packages require an explicit patch-grid profile.
- run_pytorch_lulc
- 10excel-mcpfound in code, not yet checkedno passport yet
- excel_remove_conditional_format
Remove conditional formatting
- excel_remove_conditional_format
Labels are the instruments' verdict and are never changed by ranking. Agents and robots get this same answer as JSON at /api/v1/find?q=…&answer=1 and through the MCP server.