Add/update rt-detr-r50

rt-detr-r50/config.json

@@ -0,0 +1,280 @@
+{
+  "activation_dropout": 0.0,
+  "activation_function": "silu",
+  "anchor_image_size": null,
+  "architectures": [
+    "RTDetrForObjectDetection"
+  ],
+  "attention_dropout": 0.0,
+  "auxiliary_loss": true,
+  "backbone": null,
+  "backbone_config": {
+    "depths": [
+      3,
+      4,
+      6,
+      3
+    ],
+    "downsample_in_bottleneck": false,
+    "downsample_in_first_stage": false,
+    "dtype": "float32",
+    "embedding_size": 64,
+    "hidden_act": "relu",
+    "hidden_sizes": [
+      256,
+      512,
+      1024,
+      2048
+    ],
+    "layer_type": "bottleneck",
+    "model_type": "rt_detr_resnet",
+    "num_channels": 3,
+    "out_features": [
+      "stage2",
+      "stage3",
+      "stage4"
+    ],
+    "out_indices": [
+      2,
+      3,
+      4
+    ],
+    "stage_names": [
+      "stem",
+      "stage1",
+      "stage2",
+      "stage3",
+      "stage4"
+    ]
+  },
+  "backbone_kwargs": null,
+  "batch_norm_eps": 1e-05,
+  "box_noise_scale": 1.0,
+  "d_model": 256,
+  "decoder_activation_function": "relu",
+  "decoder_attention_heads": 8,
+  "decoder_ffn_dim": 1024,
+  "decoder_in_channels": [
+    256,
+    256,
+    256
+  ],
+  "decoder_layers": 6,
+  "decoder_n_points": 4,
+  "disable_custom_kernels": true,
+  "dropout": 0.0,
+  "dtype": "float32",
+  "encode_proj_layers": [
+    2
+  ],
+  "encoder_activation_function": "gelu",
+  "encoder_attention_heads": 8,
+  "encoder_ffn_dim": 1024,
+  "encoder_hidden_dim": 256,
+  "encoder_in_channels": [
+    512,
+    1024,
+    2048
+  ],
+  "encoder_layers": 1,
+  "eos_coefficient": 0.0001,
+  "eval_size": null,
+  "feat_strides": [
+    8,
+    16,
+    32
+  ],
+  "focal_loss_alpha": 0.75,
+  "focal_loss_gamma": 2.0,
+  "freeze_backbone_batch_norms": true,
+  "hidden_expansion": 1.0,
+  "id2label": {
+    "0": "person",
+    "1": "bicycle",
+    "2": "car",
+    "3": "motorbike",
+    "4": "aeroplane",
+    "5": "bus",
+    "6": "train",
+    "7": "truck",
+    "8": "boat",
+    "9": "traffic light",
+    "10": "fire hydrant",
+    "11": "stop sign",
+    "12": "parking meter",
+    "13": "bench",
+    "14": "bird",
+    "15": "cat",
+    "16": "dog",
+    "17": "horse",
+    "18": "sheep",
+    "19": "cow",
+    "20": "elephant",
+    "21": "bear",
+    "22": "zebra",
+    "23": "giraffe",
+    "24": "backpack",
+    "25": "umbrella",
+    "26": "handbag",
+    "27": "tie",
+    "28": "suitcase",
+    "29": "frisbee",
+    "30": "skis",
+    "31": "snowboard",
+    "32": "sports ball",
+    "33": "kite",
+    "34": "baseball bat",
+    "35": "baseball glove",
+    "36": "skateboard",
+    "37": "surfboard",
+    "38": "tennis racket",
+    "39": "bottle",
+    "40": "wine glass",
+    "41": "cup",
+    "42": "fork",
+    "43": "knife",
+    "44": "spoon",
+    "45": "bowl",
+    "46": "banana",
+    "47": "apple",
+    "48": "sandwich",
+    "49": "orange",
+    "50": "broccoli",
+    "51": "carrot",
+    "52": "hot dog",
+    "53": "pizza",
+    "54": "donut",
+    "55": "cake",
+    "56": "chair",
+    "57": "sofa",
+    "58": "pottedplant",
+    "59": "bed",
+    "60": "diningtable",
+    "61": "toilet",
+    "62": "tvmonitor",
+    "63": "laptop",
+    "64": "mouse",
+    "65": "remote",
+    "66": "keyboard",
+    "67": "cell phone",
+    "68": "microwave",
+    "69": "oven",
+    "70": "toaster",
+    "71": "sink",
+    "72": "refrigerator",
+    "73": "book",
+    "74": "clock",
+    "75": "vase",
+    "76": "scissors",
+    "77": "teddy bear",
+    "78": "hair drier",
+    "79": "toothbrush"
+  },
+  "initializer_bias_prior_prob": null,
+  "initializer_range": 0.01,
+  "is_encoder_decoder": true,
+  "label2id": {
+    "aeroplane": 4,
+    "apple": 47,
+    "backpack": 24,
+    "banana": 46,
+    "baseball bat": 34,
+    "baseball glove": 35,
+    "bear": 21,
+    "bed": 59,
+    "bench": 13,
+    "bicycle": 1,
+    "bird": 14,
+    "boat": 8,
+    "book": 73,
+    "bottle": 39,
+    "bowl": 45,
+    "broccoli": 50,
+    "bus": 5,
+    "cake": 55,
+    "car": 2,
+    "carrot": 51,
+    "cat": 15,
+    "cell phone": 67,
+    "chair": 56,
+    "clock": 74,
+    "cow": 19,
+    "cup": 41,
+    "diningtable": 60,
+    "dog": 16,
+    "donut": 54,
+    "elephant": 20,
+    "fire hydrant": 10,
+    "fork": 42,
+    "frisbee": 29,
+    "giraffe": 23,
+    "hair drier": 78,
+    "handbag": 26,
+    "horse": 17,
+    "hot dog": 52,
+    "keyboard": 66,
+    "kite": 33,
+    "knife": 43,
+    "laptop": 63,
+    "microwave": 68,
+    "motorbike": 3,
+    "mouse": 64,
+    "orange": 49,
+    "oven": 69,
+    "parking meter": 12,
+    "person": 0,
+    "pizza": 53,
+    "pottedplant": 58,
+    "refrigerator": 72,
+    "remote": 65,
+    "sandwich": 48,
+    "scissors": 76,
+    "sheep": 18,
+    "sink": 71,
+    "skateboard": 36,
+    "skis": 30,
+    "snowboard": 31,
+    "sofa": 57,
+    "spoon": 44,
+    "sports ball": 32,
+    "stop sign": 11,
+    "suitcase": 28,
+    "surfboard": 37,
+    "teddy bear": 77,
+    "tennis racket": 38,
+    "tie": 27,
+    "toaster": 70,
+    "toilet": 61,
+    "toothbrush": 79,
+    "traffic light": 9,
+    "train": 6,
+    "truck": 7,
+    "tvmonitor": 62,
+    "umbrella": 25,
+    "vase": 75,
+    "wine glass": 40,
+    "zebra": 22
+  },
+  "label_noise_ratio": 0.5,
+  "layer_norm_eps": 1e-05,
+  "learn_initial_query": false,
+  "matcher_alpha": 0.25,
+  "matcher_bbox_cost": 5.0,
+  "matcher_class_cost": 2.0,
+  "matcher_gamma": 2.0,
+  "matcher_giou_cost": 2.0,
+  "model_type": "rt_detr",
+  "normalize_before": false,
+  "num_denoising": 100,
+  "num_feature_levels": 3,
+  "num_queries": 300,
+  "positional_encoding_temperature": 10000,
+  "transformers_version": "4.57.6",
+  "use_focal_loss": true,
+  "use_pretrained_backbone": false,
+  "use_timm_backbone": false,
+  "weight_loss_bbox": 5.0,
+  "weight_loss_giou": 2.0,
+  "weight_loss_vfl": 1.0,
+  "with_box_refine": true
+}

rt-detr-r50/meta.json

@@ -0,0 +1,37 @@
+{
+  "name": "rt-detr-r50",
+  "source": "PekingU/rtdetr_r50vd",
+  "method": "optimum",
+  "note": "falls back to a plain torch.onnx export if this optimum version lacks rt_detr",
+  "revision": "df939e661d8c52e80608d1ec566561aabd25a4e7",
+  "validation": "optimum (atol default)",
+  "opset_requested": 17,
+  "files": {
+    "model.onnx": {
+      "sha256": "49ec318184a40fd361caf5e4f1edd4734245bdba4383d6893090c10e1f490a42",
+      "bytes": 172381578,
+      "inputs": {
+        "pixel_values": [
+          1,
+          3,
+          640,
+          640
+        ]
+      },
+      "outputs": {
+        "logits": [
+          1,
+          "num_queries",
+          80
+        ],
+        "pred_boxes": [
+          1,
+          "num_queries",
+          "Gatherpred_boxes_dim_2"
+        ]
+      },
+      "opset": 17
+    }
+  },
+  "exported_at": "2026-10-19T18:26:53.839889+00:00"
+}

rt-detr-r50/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49ec318184a40fd361caf5e4f1edd4734245bdba4383d6893090c10e1f490a42
+size 172381578

rt-detr-r50/preprocessor_config.json

@@ -0,0 +1,26 @@
+{
+  "do_convert_annotations": true,
+  "do_normalize": false,
+  "do_pad": false,
+  "do_rescale": true,
+  "do_resize": true,
+  "format": "coco_detection",
+  "image_mean": [
+    0.485,
+    0.456,
+    0.406
+  ],
+  "image_processor_type": "RTDetrImageProcessor",
+  "image_std": [
+    0.229,
+    0.224,
+    0.225
+  ],
+  "pad_size": null,
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 640,
+    "width": 640
+  }
+}