{ "_name_or_path": "nvidia/mit-b0", "architectures": [ "SegformerForSemanticSegmentation" ], "attention_probs_dropout_prob": 0.0, "classifier_dropout_prob": 0.1, "decoder_hidden_size": 256, "depths": [ 2, 2, 2, 2 ], "downsampling_rates": [ 1, 4, 8, 16 ], "drop_path_rate": 0.1, "hidden_act": "gelu", "hidden_dropout_prob": 0.0, "hidden_sizes": [ 32, 64, 160, 256 ], "id2label": { "0": "unlabeled", "1": "flat-road", "2": "flat-sidewalk", "3": "flat-crosswalk", "4": "flat-cyclinglane", "5": "flat-parkingdriveway", "6": "flat-railtrack", "7": "flat-curb", "8": "human-person", "9": "human-rider", "10": "vehicle-car", "11": "vehicle-truck", "12": "vehicle-bus", "13": "vehicle-tramtrain", "14": "vehicle-motorcycle", "15": "vehicle-bicycle", "16": "vehicle-caravan", "17": "vehicle-cartrailer", "18": "construction-building", "19": "construction-door", "20": "construction-wall", "21": "construction-fenceguardrail", "22": "construction-bridge", "23": "construction-tunnel", "24": "construction-stairs", "25": "object-pole", "26": "object-trafficsign", "27": "object-trafficlight", "28": "nature-vegetation", "29": "nature-terrain", "30": "sky", "31": "void-ground", "32": "void-dynamic", "33": "void-static", "34": "void-unclear" }, "image_size": 224, "initializer_range": 0.02, "label2id": { "construction-bridge": 22, "construction-building": 18, "construction-door": 19, "construction-fenceguardrail": 21, "construction-stairs": 24, "construction-tunnel": 23, "construction-wall": 20, "flat-crosswalk": 3, "flat-curb": 7, "flat-cyclinglane": 4, "flat-parkingdriveway": 5, "flat-railtrack": 6, "flat-road": 1, "flat-sidewalk": 2, "human-person": 8, "human-rider": 9, "nature-terrain": 29, "nature-vegetation": 28, "object-pole": 25, "object-trafficlight": 27, "object-trafficsign": 26, "sky": 30, "unlabeled": 0, "vehicle-bicycle": 15, "vehicle-bus": 12, "vehicle-car": 10, "vehicle-caravan": 16, "vehicle-cartrailer": 17, "vehicle-motorcycle": 14, "vehicle-tramtrain": 13, "vehicle-truck": 11, "void-dynamic": 32, "void-ground": 31, "void-static": 33, "void-unclear": 34 }, "layer_norm_eps": 1e-06, "mlp_ratios": [ 4, 4, 4, 4 ], "model_type": "segformer", "num_attention_heads": [ 1, 2, 5, 8 ], "num_channels": 3, "num_encoder_blocks": 4, "patch_sizes": [ 7, 3, 3, 3 ], "reshape_last_stage": true, "semantic_loss_ignore_index": 255, "sr_ratios": [ 8, 4, 2, 1 ], "strides": [ 4, 2, 2, 2 ], "torch_dtype": "float32", "transformers_version": "4.46.2" }