{
  "provenance": {
    "scope": "Native later TorchVision ResNet-50-FPN Faster R-CNN inference; not original VGG16 benchmark reproduction",
    "architecture": "FasterRCNN / ResNet-50-FPN / MultiScaleRoIAlign / 91 COCO category slots",
    "weights": "FasterRCNN_ResNet50_FPN_Weights.COCO_V1",
    "checkpoint_url": "https://download.pytorch.org/models/fasterrcnn_resnet50_fpn_coco-258fb6c6.pth",
    "checkpoint_sha256": "258fb6c638b15964ddcdd1ae0748c5eef1be9e732750120cc857feed3faac384",
    "loading": {
      "strict": true,
      "state_keys": 295,
      "missing_keys": [],
      "unexpected_keys": []
    },
    "parameter_count": 41755286,
    "source_revision": "78839c2b06c83c6cfb5c4da692ffb331bbd4c4cc",
    "source_files": [
      {
        "path": "models/detection/faster_rcnn.py",
        "sha256": "54e05318954718c9cf269996cd56fbe35dc935ae0c2df108a7098b25a52b2dc2",
        "url": "https://github.com/pytorch/vision/blob/78839c2b06c83c6cfb5c4da692ffb331bbd4c4cc/torchvision/models/detection/faster_rcnn.py"
      },
      {
        "path": "models/detection/backbone_utils.py",
        "sha256": "23283dc7597676459b29b130177d4e27d43cdf8b35dccd68666ccdfec3f4db9d",
        "url": "https://github.com/pytorch/vision/blob/78839c2b06c83c6cfb5c4da692ffb331bbd4c4cc/torchvision/models/detection/backbone_utils.py"
      },
      {
        "path": "models/detection/rpn.py",
        "sha256": "17eb939224b28c435839b7958c6ab25765f041c151be1cf137507dd0e4d5ddd5",
        "url": "https://github.com/pytorch/vision/blob/78839c2b06c83c6cfb5c4da692ffb331bbd4c4cc/torchvision/models/detection/rpn.py"
      },
      {
        "path": "models/detection/roi_heads.py",
        "sha256": "ddf91a1c89603c86c0e7b30f3ad9f1613adf4623ed1c1688ed03e9af47579ff8",
        "url": "https://github.com/pytorch/vision/blob/78839c2b06c83c6cfb5c4da692ffb331bbd4c4cc/torchvision/models/detection/roi_heads.py"
      },
      {
        "path": "models/detection/transform.py",
        "sha256": "8f53149cd93c3bc291cf081535686282137ae29b2362938e7329f2361325061f",
        "url": "https://github.com/pytorch/vision/blob/78839c2b06c83c6cfb5c4da692ffb331bbd4c4cc/torchvision/models/detection/transform.py"
      },
      {
        "path": "ops/poolers.py",
        "sha256": "6357230e5e36497ae46a30161ebfd65cd2dcfbc38e129cf82ae1909f44bb45e1",
        "url": "https://github.com/pytorch/vision/blob/78839c2b06c83c6cfb5c4da692ffb331bbd4c4cc/torchvision/ops/poolers.py"
      }
    ],
    "program_sha256": "848acdd56404570b0330e89846c054385eb836ba877c936363d225015f129b10",
    "reference_sha256": "8877a165200ce89552df972181f039a9892bb148953e908273e946a8e89d2817",
    "command": "python examples/faster_rcnn_export.py --checkpoint .context/paper-series/weights/fasterrcnn_resnet50_fpn_coco-258fb6c6.pth --photos-dir public/examples/vit-demo --output public/examples/faster-rcnn-demo",
    "executed_argv": [
      "examples/faster_rcnn_export.py",
      "--checkpoint",
      ".context/paper-series/weights/fasterrcnn_resnet50_fpn_coco-258fb6c6.pth",
      "--photos-dir",
      "public/examples/vit-demo",
      "--output",
      "public/examples/faster-rcnn-demo"
    ],
    "generated_at": "2026-10-10T13:01:01.786589+00:00",
    "environment": {
      "python": "3.13.13",
      "torch": "2.12.0+cpu",
      "torchvision": "0.27.0+cpu",
      "pillow": "12.2.0",
      "device": "cpu",
      "dtype": "float32",
      "threads": 2,
      "seed": 8
    }
  },
  "preprocessing": {
    "input": "PIL RGB uint8 -> float32 [C,H,W] /255; no crop",
    "internal_mean": [
      0.485,
      0.456,
      0.406
    ],
    "internal_std": [
      0.229,
      0.224,
      0.225
    ],
    "min_size": [
      800
    ],
    "max_size": 1333,
    "resize": "Tensor bilinear interpolation, align_corners=False, recompute_scale_factor=True; no antialias flag",
    "size_divisible": 32,
    "padding": "zeros after normalization at bottom/right to a multiple of 32",
    "boxes": "continuous xyxy coordinates rescaled to the original uncropped photograph"
  },
  "postprocessing": {
    "score_threshold": 0.05,
    "classwise_nms_iou": 0.5,
    "max_detections": 100,
    "rpn_nms_iou": 0.7,
    "rpn_pre_nms_top_n": 1000,
    "rpn_post_nms_top_n": 1000
  },
  "photos": [
    {
      "id": "cat",
      "title": "Chelsea the cat",
      "image": "/examples/vit-demo/source-cat.png",
      "original_shape": [
        300,
        451
      ],
      "source": {
        "url": "https://raw.githubusercontent.com/scikit-image/scikit-image/v0.25.2/skimage/data/chelsea.png",
        "sha256": "596aa1e7cb875eb79f437e310381d26b338a81c2da23439704a73c4651e8c4bb",
        "author": "Stefan van der Walt",
        "license": "CC0",
        "licenseUrl": "https://github.com/scikit-image/scikit-image/blob/v0.25.2/skimage/data/_fetchers.py"
      },
      "input_tensor_shape": [
        3,
        300,
        451
      ],
      "input_tensor_sha256": "00f315cec922f0b55017da6028feabef6c3e044b0c85b0fd40f512f7a3179b2f",
      "resized_shape": [
        800,
        1202
      ],
      "padded_batch_shape": [
        1,
        3,
        800,
        1216
      ],
      "detections": [
        {
          "box": [
            0.0,
            5.041019439697266,
            398.9359436035156,
            293.379638671875
          ],
          "label_index": 17,
          "label": "cat",
          "score": 0.9861866235733032
        },
        {
          "box": [
            349.7096862792969,
            75.87382507324219,
            414.76531982421875,
            129.28738403320312
          ],
          "label_index": 47,
          "label": "cup",
          "score": 0.305395245552063
        },
        {
          "box": [
            351.6068115234375,
            78.11967468261719,
            413.5489196777344,
            126.07124328613281
          ],
          "label_index": 51,
          "label": "bowl",
          "score": 0.11494896560907364
        },
        {
          "box": [
            184.84413146972656,
            23.881668090820312,
            401.2098693847656,
            288.1811828613281
          ],
          "label_index": 17,
          "label": "cat",
          "score": 0.10500264167785645
        },
        {
          "box": [
            326.2077941894531,
            21.492679595947266,
            451.0,
            288.46124267578125
          ],
          "label_index": 1,
          "label": "person",
          "score": 0.09633852541446686
        },
        {
          "box": [
            245.4605712890625,
            230.4077911376953,
            290.1498107910156,
            263.334228515625
          ],
          "label_index": 57,
          "label": "carrot",
          "score": 0.08080761134624481
        },
        {
          "box": [
            182.49574279785156,
            3.8088340759277344,
            438.37109375,
            293.8271484375
          ],
          "label_index": 1,
          "label": "person",
          "score": 0.07047799974679947
        },
        {
          "box": [
            0.0,
            7.095760345458984,
            427.8191833496094,
            294.20208740234375
          ],
          "label_index": 18,
          "label": "dog",
          "score": 0.06351049244403839
        },
        {
          "box": [
            328.4805908203125,
            59.772377014160156,
            448.5751647949219,
            287.93603515625
          ],
          "label_index": 63,
          "label": "couch",
          "score": 0.059689961373806
        },
        {
          "box": [
            366.6141052246094,
            1.0330123901367188,
            449.2028503417969,
            142.7184600830078
          ],
          "label_index": 1,
          "label": "person",
          "score": 0.05558999627828598
        },
        {
          "box": [
            155.06427001953125,
            95.46916198730469,
            204.79588317871094,
            142.4038848876953
          ],
          "label_index": 52,
          "label": "banana",
          "score": 0.05230044573545456
        },
        {
          "box": [
            325.234619140625,
            92.96175384521484,
            448.4866638183594,
            293.7581481933594
          ],
          "label_index": 65,
          "label": "bed",
          "score": 0.05082390084862709
        }
      ]
    },
    {
      "id": "coffee",
      "title": "Cup of coffee",
      "image": "/examples/vit-demo/source-coffee.png",
      "original_shape": [
        400,
        600
      ],
      "source": {
        "url": "https://raw.githubusercontent.com/scikit-image/scikit-image/v0.25.2/skimage/data/coffee.png",
        "sha256": "cc02f8ca188b167c775a7101b5d767d1e71792cf762c33d6fa15a4599b5a8de7",
        "author": "Rachel Michetti",
        "license": "CC0",
        "licenseUrl": "https://github.com/scikit-image/scikit-image/blob/v0.25.2/skimage/data/_fetchers.py"
      },
      "input_tensor_shape": [
        3,
        400,
        600
      ],
      "input_tensor_sha256": "f7ff09bd78387b85b34182ab89d00452d1bd74397c6ea0e46e26cda8479fd260",
      "resized_shape": [
        800,
        1200
      ],
      "padded_batch_shape": [
        1,
        3,
        800,
        1216
      ],
      "detections": [
        {
          "box": [
            0.0,
            0.0,
            587.223876953125,
            400.0
          ],
          "label_index": 67,
          "label": "dining table",
          "score": 0.9803950190544128
        },
        {
          "box": [
            168.3057403564453,
            19.983612060546875,
            411.25628662109375,
            293.70074462890625
          ],
          "label_index": 47,
          "label": "cup",
          "score": 0.9364811778068542
        },
        {
          "box": [
            326.2474670410156,
            121.1452865600586,
            443.8895568847656,
            321.0793762207031
          ],
          "label_index": 50,
          "label": "spoon",
          "score": 0.8602442145347595
        },
        {
          "box": [
            396.93511962890625,
            66.25924682617188,
            424.58258056640625,
            147.98770141601562
          ],
          "label_index": 50,
          "label": "spoon",
          "score": 0.73204505443573
        },
        {
          "box": [
            175.64791870117188,
            8.21380615234375,
            404.7602233886719,
            283.4040222167969
          ],
          "label_index": 51,
          "label": "bowl",
          "score": 0.523970901966095
        },
        {
          "box": [
            0.3832244873046875,
            13.130111694335938,
            275.05450439453125,
            392.927734375
          ],
          "label_index": 67,
          "label": "dining table",
          "score": 0.37117189168930054
        },
        {
          "box": [
            323.6791076660156,
            212.16424560546875,
            404.5580139160156,
            324.33740234375
          ],
          "label_index": 50,
          "label": "spoon",
          "score": 0.3399369418621063
        },
        {
          "box": [
            362.2526550292969,
            83.6944808959961,
            472.1771545410156,
            332.3655700683594
          ],
          "label_index": 50,
          "label": "spoon",
          "score": 0.33992817997932434
        },
        {
          "box": [
            87.62879943847656,
            30.860107421875,
            424.5147705078125,
            376.573486328125
          ],
          "label_index": 51,
          "label": "bowl",
          "score": 0.24289090931415558
        },
        {
          "box": [
            392.4427185058594,
            67.72382354736328,
            423.1891784667969,
            212.3834228515625
          ],
          "label_index": 50,
          "label": "spoon",
          "score": 0.2212935835123062
        },
        {
          "box": [
            339.61749267578125,
            3.7406158447265625,
            594.76220703125,
            389.6466064453125
          ],
          "label_index": 67,
          "label": "dining table",
          "score": 0.19633905589580536
        },
        {
          "box": [
            389.9554748535156,
            63.83393859863281,
            482.3440856933594,
            336.08648681640625
          ],
          "label_index": 49,
          "label": "knife",
          "score": 0.14725491404533386
        },
        {
          "box": [
            195.71670532226562,
            92.23059844970703,
            420.6004333496094,
            327.71142578125
          ],
          "label_index": 50,
          "label": "spoon",
          "score": 0.1108163520693779
        },
        {
          "box": [
            189.21717834472656,
            110.86369323730469,
            595.9568481445312,
            399.04052734375
          ],
          "label_index": 67,
          "label": "dining table",
          "score": 0.09934037923812866
        },
        {
          "box": [
            367.246826171875,
            73.67672729492188,
            423.56427001953125,
            304.1758728027344
          ],
          "label_index": 50,
          "label": "spoon",
          "score": 0.05737234279513359
        },
        {
          "box": [
            11.119232177734375,
            0.0,
            460.046875,
            114.98106384277344
          ],
          "label_index": 67,
          "label": "dining table",
          "score": 0.053708530962467194
        },
        {
          "box": [
            194.03146362304688,
            229.7338104248047,
            267.40875244140625,
            312.81317138671875
          ],
          "label_index": 74,
          "label": "mouse",
          "score": 0.053427260369062424
        }
      ]
    }
  ]
}