{ | |
"_name_or_path": "nvidia/segformer-b0-finetuned-ade-512-512", | |
"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": "road", | |
"1": "human", | |
"2": "vehicles", | |
"3": "traffic lights", | |
"4": "background" | |
}, | |
"image_size": 224, | |
"initializer_range": 0.02, | |
"label2id": { | |
"background": 4, | |
"human": 1, | |
"road": 0, | |
"traffic lights": 3, | |
"vehicles": 2 | |
}, | |
"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": "4.28.0" | |
} | |