{ "_name_or_path": "facebook/detr-resnet-50", "activation_dropout": 0.0, "activation_function": "relu", "architectures": [ "DetrForObjectDetection" ], "attention_dropout": 0.0, "auxiliary_loss": false, "backbone": null, "backbone_config": { "_name_or_path": "", "add_cross_attention": false, "architectures": null, "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, "depths": [ 3, 4, 6, 3 ], "diversity_penalty": 0.0, "do_sample": false, "downsample_in_first_stage": false, "early_stopping": false, "embedding_size": 64, "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": "relu", "hidden_sizes": [ 256, 512, 1024, 2048 ], "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "is_decoder": false, "is_encoder_decoder": false, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "layer_type": "bottleneck", "length_penalty": 1.0, "max_length": 20, "min_length": 0, "model_type": "resnet", "no_repeat_ngram_size": 0, "num_beam_groups": 1, "num_beams": 1, "num_channels": 3, "num_return_sequences": 1, "out_features": [ "stage4" ], "out_indices": [ 4 ], "output_attentions": false, "output_hidden_states": false, "output_scores": false, "pad_token_id": null, "prefix": null, "problem_type": null, "pruned_heads": {}, "remove_invalid_values": false, "repetition_penalty": 1.0, "return_dict": true, "return_dict_in_generate": false, "sep_token_id": null, "stage_names": [ "stem", "stage1", "stage2", "stage3", "stage4" ], "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": null, "torchscript": false, "typical_p": 1.0, "use_bfloat16": false }, "bbox_cost": 5, "bbox_loss_coefficient": 5, "class_cost": 1, "d_model": 256, "decoder_attention_heads": 8, "decoder_ffn_dim": 2048, "decoder_layerdrop": 0.0, "decoder_layers": 6, "dice_loss_coefficient": 1, "dilation": null, "dropout": 0.1, "encoder_attention_heads": 8, "encoder_ffn_dim": 2048, "encoder_layerdrop": 0.0, "encoder_layers": 6, "eos_coefficient": 0.1, "giou_cost": 2, "giou_loss_coefficient": 2, "id2label": { "0": "LABEL_0", "1": "LABEL_1", "2": "LABEL_2", "3": "LABEL_3", "4": "LABEL_4", "5": "LABEL_5", "6": "LABEL_6", "7": "LABEL_7", "8": "LABEL_8", "9": "LABEL_9", "10": "LABEL_10", "11": "LABEL_11", "12": "LABEL_12", "13": "LABEL_13", "14": "LABEL_14", "15": "LABEL_15", "16": "LABEL_16", "17": "LABEL_17", "18": "LABEL_18", "19": "LABEL_19", "20": "LABEL_20", "21": "LABEL_21", "22": "LABEL_22", "23": "LABEL_23", "24": "LABEL_24", "25": "LABEL_25", "26": "LABEL_26", "27": "LABEL_27", "28": "LABEL_28", "29": "LABEL_29" }, "init_std": 0.02, "init_xavier_std": 1.0, "is_encoder_decoder": true, "label2id": { "LABEL_0": 0, "LABEL_1": 1, "LABEL_10": 10, "LABEL_11": 11, "LABEL_12": 12, "LABEL_13": 13, "LABEL_14": 14, "LABEL_15": 15, "LABEL_16": 16, "LABEL_17": 17, "LABEL_18": 18, "LABEL_19": 19, "LABEL_2": 2, "LABEL_20": 20, "LABEL_21": 21, "LABEL_22": 22, "LABEL_23": 23, "LABEL_24": 24, "LABEL_25": 25, "LABEL_26": 26, "LABEL_27": 27, "LABEL_28": 28, "LABEL_29": 29, "LABEL_3": 3, "LABEL_4": 4, "LABEL_5": 5, "LABEL_6": 6, "LABEL_7": 7, "LABEL_8": 8, "LABEL_9": 9 }, "mask_loss_coefficient": 1, "model_type": "detr", "num_channels": 3, "num_hidden_layers": 6, "num_queries": 100, "position_embedding_type": "sine", "scale_embedding": false, "torch_dtype": "float32", "transformers_version": "4.32.1", "use_pretrained_backbone": null, "use_timm_backbone": false }