{
  "file": "rfdetr-seg-2xlarge.onnx",
  "sha256": "7cc10d4316371946b8441da3512261a8e148b129abcdb0ea6235ed1d1d06d351",
  "format": "onnx",
  "opset": 17,
  "precision": "float32",
  "static_batch_size": 1,
  "input": {
    "name": "input",
    "shape": [1, 3, 1152, 1152],
    "layout": "NCHW",
    "dtype": "float32",
    "resize": "bilinear",
    "scale": 0.00392156862745098,
    "mean": [0.485, 0.456, 0.406],
    "std": [0.229, 0.224, 0.225]
  },
  "outputs": {
    "dets": {
      "shape": [1, 300, 4],
      "dtype": "float32",
      "description": "Normalized boxes in cx, cy, width, height format"
    },
    "labels": {
      "shape": [1, 300, 5],
      "dtype": "float32",
      "description": "Class logits; apply sigmoid to the first four channels and ignore the final no-object channel"
    },
    "masks": {
      "shape": [1, 300, 288, 288],
      "dtype": "float32",
      "description": "Instance mask logits; bilinearly resize to the target image size and threshold at zero"
    }
  },
  "classes": {
    "0": "text",
    "1": "onomatopoeia",
    "2": "bubble",
    "3": "panel"
  },
  "recommended_thresholds": {
    "text": 0.25,
    "onomatopoeia": 0.2,
    "bubble": 0.5,
    "panel": 0.5
  },
  "source": {
    "repo": "mayocream/koharu-layout-rfdetr-seg-2xl-1152",
    "revision": "aed55fdb8ca953c6bec33cf6ed6dd52a9b72bfa2",
    "weights_sha256": "9bf6d2cbd7793c956d8c857bb1672a396eb7f100eb0682f86830d05e31168efb",
    "rfdetr_version": "1.7.0"
  }
}