diff --git a/config.json b/config.json index 546e763..4d021fa 100644 --- a/config.json +++ b/config.json @@ -96,6 +96,97 @@ }, "ce_weight": 1.0, "cross_entropy_weight": 1.0, + "decoder_config": { + "_name_or_path": "", + "activation_dropout": 0.0, + "activation_function": "relu", + "add_cross_attention": false, + "architectures": null, + "attention_dropout": 0.0, + "auxiliary_loss": false, + "backbone": "resnet50", + "bad_words_ids": null, + "bbox_cost": 5, + "bbox_loss_coefficient": 5, + "bos_token_id": null, + "chunk_size_feed_forward": 0, + "class_cost": 1, + "cross_attention_hidden_size": null, + "d_model": 256, + "decoder_attention_heads": 8, + "decoder_ffn_dim": 2048, + "decoder_layerdrop": 0.0, + "decoder_layers": 6, + "decoder_start_token_id": null, + "dice_loss_coefficient": 1, + "dilation": false, + "diversity_penalty": 0.0, + "do_sample": false, + "dropout": 0.1, + "early_stopping": false, + "encoder_attention_heads": 8, + "encoder_ffn_dim": 2048, + "encoder_layerdrop": 0.0, + "encoder_layers": 6, + "encoder_no_repeat_ngram_size": 0, + "eos_coefficient": 0.1, + "eos_token_id": null, + "finetuning_task": null, + "forced_bos_token_id": null, + "forced_eos_token_id": null, + "giou_cost": 2, + "giou_loss_coefficient": 2, + "id2label": { + "0": "LABEL_0", + "1": "LABEL_1" + }, + "init_std": 0.02, + "init_xavier_std": 1.0, + "is_decoder": false, + "is_encoder_decoder": true, + "label2id": { + "LABEL_0": 0, + "LABEL_1": 1 + }, + "length_penalty": 1.0, + "mask_loss_coefficient": 1, + "max_length": 20, + "max_position_embeddings": 1024, + "min_length": 0, + "model_type": "detr", + "no_repeat_ngram_size": 0, + "num_beam_groups": 1, + "num_beams": 1, + "num_hidden_layers": 6, + "num_queries": 100, + "num_return_sequences": 1, + "output_attentions": false, + "output_hidden_states": false, + "output_scores": false, + "pad_token_id": null, + "position_embedding_type": "sine", + "prefix": null, + "problem_type": null, + "pruned_heads": {}, + "remove_invalid_values": false, + "repetition_penalty": 1.0, + "return_dict": true, + "return_dict_in_generate": false, + "scale_embedding": false, + "sep_token_id": null, + "task_specific_params": null, + "temperature": 1.0, + "tie_encoder_decoder": false, + "tie_word_embeddings": true, + "tokenizer_class": null, + "top_k": 50, + "top_p": 1.0, + "torch_dtype": null, + "torchscript": false, + "transformers_version": "4.17.0.dev0", + "typical_p": 1.0, + "use_bfloat16": false + }, "dice_weight": 1.0, "fpn_feature_size": 256, "id2label": { @@ -378,97 +469,6 @@ "num_hidden_layers": 6, "num_queries": 100, "torch_dtype": "float32", - "transformer_decoder_config": { - "_name_or_path": "", - "activation_dropout": 0.0, - "activation_function": "relu", - "add_cross_attention": false, - "architectures": null, - "attention_dropout": 0.0, - "auxiliary_loss": false, - "backbone": "resnet50", - "bad_words_ids": null, - "bbox_cost": 5, - "bbox_loss_coefficient": 5, - "bos_token_id": null, - "chunk_size_feed_forward": 0, - "class_cost": 1, - "cross_attention_hidden_size": null, - "d_model": 256, - "decoder_attention_heads": 8, - "decoder_ffn_dim": 2048, - "decoder_layerdrop": 0.0, - "decoder_layers": 6, - "decoder_start_token_id": null, - "dice_loss_coefficient": 1, - "dilation": false, - "diversity_penalty": 0.0, - "do_sample": false, - "dropout": 0.1, - "early_stopping": false, - "encoder_attention_heads": 8, - "encoder_ffn_dim": 2048, - "encoder_layerdrop": 0.0, - "encoder_layers": 6, - "encoder_no_repeat_ngram_size": 0, - "eos_coefficient": 0.1, - "eos_token_id": null, - "finetuning_task": null, - "forced_bos_token_id": null, - "forced_eos_token_id": null, - "giou_cost": 2, - "giou_loss_coefficient": 2, - "id2label": { - "0": "LABEL_0", - "1": "LABEL_1" - }, - "init_std": 0.02, - "init_xavier_std": 1.0, - "is_decoder": false, - "is_encoder_decoder": true, - "label2id": { - "LABEL_0": 0, - "LABEL_1": 1 - }, - "length_penalty": 1.0, - "mask_loss_coefficient": 1, - "max_length": 20, - "max_position_embeddings": 1024, - "min_length": 0, - "model_type": "detr", - "no_repeat_ngram_size": 0, - "num_beam_groups": 1, - "num_beams": 1, - "num_hidden_layers": 6, - "num_queries": 100, - "num_return_sequences": 1, - "output_attentions": false, - "output_hidden_states": false, - "output_scores": false, - "pad_token_id": null, - "position_embedding_type": "sine", - "prefix": null, - "problem_type": null, - "pruned_heads": {}, - "remove_invalid_values": false, - "repetition_penalty": 1.0, - "return_dict": true, - "return_dict_in_generate": false, - "scale_embedding": false, - "sep_token_id": null, - "task_specific_params": null, - "temperature": 1.0, - "tie_encoder_decoder": false, - "tie_word_embeddings": true, - "tokenizer_class": null, - "top_k": 50, - "top_p": 1.0, - "torch_dtype": null, - "torchscript": false, - "transformers_version": "4.17.0.dev0", - "typical_p": 1.0, - "use_bfloat16": false - }, "transformers_version": null, - "use_auxilary_loss": false + "use_auxiliary_loss": false } diff --git a/pytorch_model.bin b/pytorch_model.bin index 8c38599..6253dc3 100644 --- a/pytorch_model.bin +++ b/pytorch_model.bin @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:a3ab55d7616b1b9100d88e9040531f97cbeb66c1eb65df26b729ace46aaf43ba -size 850574833 +oid sha256:7a660c99ffd28e2dd2b4f77730f0c46cd744962f210eb45ff32a7945f255b12d +size 850571697