{
  "return_dict": true,
  "output_hidden_states": false,
  "output_attentions": false,
  "torchscript": false,
  "torch_dtype": "float32",
  "use_bfloat16": false,
  "tf_legacy_loss": false,
  "pruned_heads": {},
  "tie_word_embeddings": true,
  "chunk_size_feed_forward": 0,
  "is_encoder_decoder": false,
  "is_decoder": false,
  "cross_attention_hidden_size": null,
  "add_cross_attention": false,
  "tie_encoder_decoder": false,
  "max_length": 20,
  "min_length": 0,
  "do_sample": false,
  "early_stopping": false,
  "num_beams": 1,
  "num_beam_groups": 1,
  "diversity_penalty": 0.0,
  "temperature": 1.0,
  "top_k": 50,
  "top_p": 1.0,
  "typical_p": 1.0,
  "repetition_penalty": 1.0,
  "length_penalty": 1.0,
  "no_repeat_ngram_size": 0,
  "encoder_no_repeat_ngram_size": 0,
  "bad_words_ids": null,
  "num_return_sequences": 1,
  "output_scores": false,
  "return_dict_in_generate": false,
  "forced_bos_token_id": null,
  "forced_eos_token_id": null,
  "remove_invalid_values": false,
  "exponential_decay_length_penalty": null,
  "suppress_tokens": null,
  "begin_suppress_tokens": null,
  "architectures": [
    "SegformerForSemanticSegmentation"
  ],
  "finetuning_task": null,
  "id2label": {
    "0": "etc",
    "1": "broken",
    "2": "crack",
    "3": "crush",
    "4": "dent",
    "5": "flat_tire",
    "6": "misalignment",
    "7": "missing",
    "8": "scratch",
    "9": "shatter",
    "10": "tear"
  },
  "label2id": {
    "etc": "0",
    "broken": "1",
    "crack": "2",
    "crush": "3",
    "dent": "4",
    "flat_tire": "5",
    "misalignment": "6",
    "missing": "7",
    "scratch": "8",
    "shatter": "9",
    "tear": "10"
  },
  "tokenizer_class": null,
  "prefix": null,
  "bos_token_id": null,
  "pad_token_id": null,
  "eos_token_id": null,
  "sep_token_id": null,
  "decoder_start_token_id": null,
  "task_specific_params": null,
  "problem_type": null,
  "_name_or_path": "mattmdjaga/segformer_b2_clothes",
  "transformers_version": "4.39.3",
  "downsampling_rates": [
    1,
    4,
    8,
    16
  ],
  "image_size": 224,
  "model_type": "segformer",
  "reshape_last_stage": true,
  "num_channels": 3,
  "num_encoder_blocks": 4,
  "depths": [
    3,
    4,
    6,
    3
  ],
  "sr_ratios": [
    8,
    4,
    2,
    1
  ],
  "hidden_sizes": [
    64,
    128,
    320,
    512
  ],
  "patch_sizes": [
    7,
    3,
    3,
    3
  ],
  "strides": [
    4,
    2,
    2,
    2
  ],
  "mlp_ratios": [
    4,
    4,
    4,
    4
  ],
  "num_attention_heads": [
    1,
    2,
    5,
    8
  ],
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.0,
  "attention_probs_dropout_prob": 0.0,
  "classifier_dropout_prob": 0.1,
  "initializer_range": 0.02,
  "drop_path_rate": 0.1,
  "layer_norm_eps": 1e-06,
  "decoder_hidden_size": 768,
  "semantic_loss_ignore_index": 255
}