{ "_name_or_path": "nvidia/mit-b5", "architectures": [ "SegformerForSemanticSegmentation" ], "attention_probs_dropout_prob": 0.0, "classifier_dropout_prob": 0.1, "decoder_hidden_size": 768, "depths": [ 3, 6, 40, 3 ], "downsampling_rates": [ 1, 4, 8, 16 ], "drop_path_rate": 0.1, "hidden_act": "gelu", "hidden_dropout_prob": 0.0, "hidden_sizes": [ 64, 128, 320, 512 ], "id2label": { "0": "unlabeled", "1": "paved-area", "2": "dirt", "3": "grass", "4": "gravel", "5": "water", "6": "rocks", "7": "pool", "8": "vegetation", "9": "roof", "10": "wall", "11": "window", "12": "door", "13": "fence", "14": "fence-pole", "15": "person", "16": "dog", "17": "car", "18": "bicycle", "19": "tree", "20": "bald-tree", "21": "ar-marker", "22": "obstacle", "23": "conflicting" }, "image_size": 224, "initializer_range": 0.02, "label2id": { "ar-marker": 21, "bald-tree": 20, "bicycle": 18, "car": 17, "conflicting": 23, "dirt": 2, "dog": 16, "door": 12, "fence": 13, "fence-pole": 14, "grass": 3, "gravel": 4, "obstacle": 22, "paved-area": 1, "person": 15, "pool": 7, "rocks": 6, "roof": 9, "tree": 19, "unlabeled": 0, "vegetation": 8, "wall": 10, "water": 5, "window": 11 }, "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": "4.29.2" }