sam1120's picture
Training in progress, step 80
dc074c5
{
"_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": "NAT",
"2": "concrete",
"3": "grass",
"4": "speedway bricks",
"5": "steel",
"6": "rough concrete",
"7": "dark bricks",
"8": "road",
"9": "rough red sidewalk",
"10": "tiles",
"11": "red bricks",
"12": "concrete tiles",
"13": "REST"
},
"image_size": 224,
"initializer_range": 0.02,
"label2id": {
"NAT": 1,
"REST": 13,
"concrete": 2,
"concrete tiles": 12,
"dark bricks": 7,
"grass": 3,
"red bricks": 11,
"road": 8,
"rough concrete": 6,
"rough red sidewalk": 9,
"speedway bricks": 4,
"steel": 5,
"tiles": 10,
"unlabeled": 0
},
"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": "4.30.2"
}