10 actions in 8 pieces of software · ranked by words, meaning and measured trust · 468 ms

1. 1segformer_for_optic_disc_cup_segmentationverified and signedpassport

   modelrecord702 downloads/month

   • image-segmentation

     Task: image-segmentation

2. 2simbrams/segformer-b5-finetuned-ade-640-640verified and signedpassport

   modelrecord

   • simbrams/segformer-b5-finetuned-ade-640-640

     Semantic Segmentation

3. 3tao-train-segformerverified and signedpassport

   skillnvidia/skillsrecord

   • tao-train-segformer

     SegFormer for semantic segmentation. Lightweight transformer-based architecture with hierarchical feature extraction, efficient for real-time segmentation tasks. Use when training, evaluating, exporting, quantizing, or running inference for a TAO SegFormer model. Trigger phrases include "train SegFo

4. 4SegFormer ONNXverified and signedpassport

   MCP serverrecord

   • segformer_tf_transformers_predict

     If a user passes a file as an input, use the upload_file_to_gradio tool, if present, to upload the file to the gradio app and create a Gradio File Input. Then use the returned path as the input to the tool

5. 5bfirsh/segformer-b0-finetuned-ade-512-512demo or tutorialno passport yet

   modelrecord

   • bfirsh/segformer-b0-finetuned-ade-512-512

6. 6eye-mcpfound in code, not yet checkedno passport yet

   MCP serverjimmybai666/eye-mcp

   • optic_disc_cup_seg

     分割眼底图像中的视盘和视杯区域，计算杯盘比(CDR)，返回分割mask、统计数据和可视化叠加图

7. 7tao-train-mask2formerverified and signedpassport

   skillnvidia/skillsrecord

   • tao-train-mask2former

     Mask2Former for universal image segmentation (panoptic, instance, and semantic). Transformer-based with masked attention for high-quality segmentation results. Use when training, evaluating, exporting, quantizing, or running inference for a TAO Mask2Former model. Trigger phrases include "train Mask2

8. 8disc-mcpdemo or tutorialno passport yet

   MCP serveryaoxiaolinglong/disc-mcp

   • start_disc_test

   • calculate_disc_result

   • get_progress

     看看你做了多少题了，还差几题就能看到你的DISC风格报告。