DETR_FineTuning_2 / config.json
dhruvindankhara's picture
Training in progress, epoch 0
e1020ad
{
"_commit_hash": "d12669b23319c30ecb4c8535ee20527fe11ec286",
"_name_or_path": "dhruvindankhara/DETR_FineTuning",
"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,
"transformers_version": "4.31.0",
"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": "face"
},
"init_std": 0.02,
"init_xavier_std": 1.0,
"is_encoder_decoder": true,
"label2id": {
"LABEL_0": 0
},
"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": null,
"use_pretrained_backbone": null,
"use_timm_backbone": false
}