CtrlK
BlogDocsLog inGet started
Tessl Logo

tessl/pypi-rembg

Remove image background using advanced AI models including U-Net, BiRefNet, and SAM with support for multiple input formats and GPU acceleration

84

0.94x
Overview
Eval results
Files

rubric.jsonevals/scenario-2/

{
  "context": "This evaluation assesses the engineer's ability to use the rembg package for background removal, focusing on proper usage of the remove() function, correct file handling, and appropriate error handling patterns.",
  "type": "weighted_checklist",
  "checklist": [
    {
      "name": "Uses remove() function",
      "description": "Implementation correctly imports and uses the rembg.remove() function to perform background removal",
      "max_score": 30
    },
    {
      "name": "File I/O handling",
      "description": "Correctly reads input image file and writes output image file using appropriate methods (e.g., PIL Image.open() and save(), or reading/writing bytes)",
      "max_score": 25
    },
    {
      "name": "Command-line argument parsing",
      "description": "Properly parses command-line arguments to extract input and output file paths (e.g., using sys.argv or argparse)",
      "max_score": 15
    },
    {
      "name": "Error handling",
      "description": "Implements appropriate error handling for missing files or invalid paths, with proper exit codes and error messages",
      "max_score": 15
    },
    {
      "name": "Data format compatibility",
      "description": "Ensures compatibility between file I/O format and remove() function input/output (bytes, PIL Image, or numpy array)",
      "max_score": 15
    }
  ]
}

Install with Tessl CLI

npx tessl i tessl/pypi-rembg

tile.json