segformer_rust / config.json
Ventalik's picture
Training in progress, epoch 1
84fd5e0 verified
{
"_name_or_path": "nvidia/mit-b3",
"architectures": [
"SegformerForSemanticSegmentation"
],
"attention_probs_dropout_prob": 0.0,
"classifier_dropout_prob": 0.1,
"decoder_hidden_size": 768,
"depths": [
3,
4,
18,
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": "\u0424\u043e\u043d",
"1": "\u041a\u043e\u0440\u0440\u043e\u0437\u0438\u044f"
},
"image_size": 224,
"initializer_range": 0.02,
"label2id": {
"\u041a\u043e\u0440\u0440\u043e\u0437\u0438\u044f": 1,
"\u0424\u043e\u043d": 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": "4.33.1"
}