{ "_commit_hash": null, "add_projection": true, "architectures": [ "DPTForDepthEstimation" ], "attention_probs_dropout_prob": null, "auxiliary_loss_weight": 0.4, "backbone_config": { "_name_or_path": "", "add_cross_attention": false, "apply_layernorm": false, "architectures": [ "Dinov2Model" ], "attention_probs_dropout_prob": 0.0, "bad_words_ids": null, "begin_suppress_tokens": null, "bos_token_id": null, "chunk_size_feed_forward": 0, "cross_attention_hidden_size": null, "decoder_start_token_id": null, "diversity_penalty": 0.0, "do_sample": false, "drop_path_rate": 0.0, "early_stopping": false, "encoder_no_repeat_ngram_size": 0, "eos_token_id": null, "exponential_decay_length_penalty": null, "finetuning_task": null, "forced_bos_token_id": null, "forced_eos_token_id": null, "hidden_act": "gelu", "hidden_dropout_prob": 0.0, "hidden_size": 1536, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "image_size": 518, "initializer_range": 0.02, "is_decoder": false, "is_encoder_decoder": false, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "layer_norm_eps": 1e-06, "layerscale_value": 1.0, "length_penalty": 1.0, "max_length": 20, "min_length": 0, "mlp_ratio": 4, "model_type": "dinov2", "no_repeat_ngram_size": 0, "num_attention_heads": 24, "num_beam_groups": 1, "num_beams": 1, "num_channels": 3, "num_hidden_layers": 40, "num_return_sequences": 1, "out_features": [ "stage10", "stage20", "stage30", "stage40" ], "out_indices": [ 10, 20, 30, 40 ], "output_attentions": false, "output_hidden_states": false, "output_scores": false, "pad_token_id": null, "patch_size": 14, "prefix": null, "problem_type": null, "pruned_heads": {}, "qkv_bias": true, "remove_invalid_values": false, "repetition_penalty": 1.0, "reshape_hidden_states": false, "return_dict": true, "return_dict_in_generate": false, "sep_token_id": null, "stage_names": [ "stem", "stage1", "stage2", "stage3", "stage4", "stage5", "stage6", "stage7", "stage8", "stage9", "stage10", "stage11", "stage12", "stage13", "stage14", "stage15", "stage16", "stage17", "stage18", "stage19", "stage20", "stage21", "stage22", "stage23", "stage24", "stage25", "stage26", "stage27", "stage28", "stage29", "stage30", "stage31", "stage32", "stage33", "stage34", "stage35", "stage36", "stage37", "stage38", "stage39", "stage40" ], "suppress_tokens": null, "task_specific_params": null, "temperature": 1.0, "tf_legacy_loss": false, "tie_encoder_decoder": false, "tie_word_embeddings": true, "tokenizer_class": null, "top_k": 50, "top_p": 1.0, "torch_dtype": "float32", "torchscript": false, "transformers_version": "4.35.0.dev0", "typical_p": 1.0, "use_bfloat16": false, "use_swiglu_ffn": true }, "backbone_featmap_shape": null, "backbone_out_indices": null, "fusion_hidden_size": 256, "head_in_index": -1, "hidden_act": "gelu", "hidden_dropout_prob": null, "hidden_size": 768, "image_size": null, "initializer_range": 0.02, "intermediate_size": null, "is_hybrid": false, "layer_norm_eps": null, "model_type": "dpt", "neck_hidden_sizes": [ 192, 384, 768, 1536 ], "neck_ignore_stages": [], "num_attention_heads": null, "num_channels": null, "num_hidden_layers": null, "patch_size": null, "qkv_bias": null, "readout_type": "project", "reassemble_factors": [ 4, 2, 1, 0.5 ], "semantic_classifier_dropout": 0.1, "semantic_loss_ignore_index": 255, "torch_dtype": "float32", "transformers_version": null, "use_auxiliary_head": true, "use_batch_norm_in_fusion_residual": false, "use_bias_in_fusion_residual": false }