Upload Yolov6ForObjectDetection

config.json

@@ -0,0 +1,269 @@
+{
+  "architectures": [
+    "Yolov6ForObjectDetection"
+  ],
+  "backbone_csp_e": 0.0,
+  "backbone_cspsppf": true,
+  "backbone_fuse_P2": true,
+  "backbone_num_repeats": [
+    1,
+    2,
+    4,
+    6,
+    2
+  ],
+  "backbone_out_channels": [
+    16,
+    32,
+    64,
+    128,
+    256
+  ],
+  "backbone_stage_block_type": "Yolov6RepBlock",
+  "block_type": "Yolov6RepVGGBlock",
+  "class_loss_coefficient": 1.0,
+  "dfl_loss_coefficient": 1.0,
+  "head_anchors": 3,
+  "head_anchors_init": [
+    [
+      10,
+      13,
+      19,
+      19,
+      33,
+      23
+    ],
+    [
+      30,
+      61,
+      59,
+      59,
+      59,
+      119
+    ],
+    [
+      116,
+      90,
+      185,
+      185,
+      373,
+      326
+    ]
+  ],
+  "head_atss_warmup_epoch": 0,
+  "head_begin_indices": 24,
+  "head_in_channels": [
+    128,
+    256,
+    512
+  ],
+  "head_num_layers": 3,
+  "head_out_indices": [
+    17,
+    20,
+    23
+  ],
+  "head_strides": [
+    8,
+    16,
+    32
+  ],
+  "hidden_size": 192,
+  "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"
+  },
+  "image_size": [
+    800,
+    1333
+  ],
+  "in_channels": 3,
+  "initializer_range": 0.02,
+  "intermediate_size": 768,
+  "iou_loss_coefficient": 1.0,
+  "iou_type": "siou",
+  "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
+  },
+  "model_type": "yolov6n",
+  "neck_csp_e": 0.0,
+  "neck_num_repeats": [
+    4,
+    4,
+    4,
+    4
+  ],
+  "neck_out_channels": [
+    64,
+    32,
+    32,
+    64,
+    64,
+    128
+  ],
+  "neck_stage_block_type": "Yolov6RepBlock",
+  "num_attention_heads": 3,
+  "num_hidden_layers": 12,
+  "reg_max": 0,
+  "torch_dtype": "float32",
+  "transformers_version": "4.37.0.dev0",
+  "use_dfl": false,
+  "use_mid_position_embeddings": false
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4dad1ac0d4973a00bcddb6cf82c7000fd2d4207e9fd648798f202653fb490bf7
+size 20422840