diff --git "a/debug/info.txt" "b/debug/info.txt" new file mode 100644--- /dev/null +++ "b/debug/info.txt" @@ -0,0 +1,1604 @@ +INFO  2024-03-29 17:46:26,830 | git: + sha: N/A, status: clean, branch: N/A + +INFO  2024-03-29 17:46:26,830 | Command: main.py --output_dir ./debug -c config/cfg_fsc147_vit_b.py --datasets config/datasets_fsc147.json --pretrain_model_path checkpoints/groundingdino_swinb_cogcoor.pth --options text_encoder_type=checkpoints/bert-base-uncased +INFO  2024-03-29 17:46:26,831 | Full config saved to ./debug/config_args_all.json +INFO  2024-03-29 17:46:26,831 | world size: 1 +INFO  2024-03-29 17:46:26,831 | rank: 0 +INFO  2024-03-29 17:46:26,831 | local_rank: 0 +INFO  2024-03-29 17:46:26,831 | args: Namespace(config_file='config/cfg_fsc147_vit_b.py', options={'text_encoder_type': 'checkpoints/bert-base-uncased'}, datasets='config/datasets_fsc147.json', remove_difficult=False, fix_size=False, output_dir='./debug', note='', device='cuda', seed=42, resume='', pretrain_model_path='checkpoints/groundingdino_swinb_cogcoor.pth', finetune_ignore=None, start_epoch=0, eval=False, num_workers=8, test=False, debug=False, find_unused_params=False, save_results=False, save_log=False, world_size=1, dist_url='env://', rank=0, local_rank=0, amp=False, distributed=False, data_aug_scales=[480, 512, 544, 576, 608, 640, 672, 704, 736, 768, 800], data_aug_max_size=1333, data_aug_scales2_resize=[400, 500, 600], data_aug_scales2_crop=[384, 600], data_aug_scale_overlap=None, batch_size=4, modelname='groundingdino', backbone='swin_B_384_22k', position_embedding='sine', pe_temperatureH=20, pe_temperatureW=20, return_interm_indices=[1, 2, 3], enc_layers=6, dec_layers=6, pre_norm=False, dim_feedforward=2048, hidden_dim=256, dropout=0.0, nheads=8, num_queries=900, query_dim=4, num_patterns=0, num_feature_levels=4, enc_n_points=4, dec_n_points=4, two_stage_type='standard', two_stage_bbox_embed_share=False, two_stage_class_embed_share=False, transformer_activation='relu', dec_pred_bbox_embed_share=True, dn_box_noise_scale=1.0, dn_label_noise_ratio=0.5, dn_label_coef=1.0, dn_bbox_coef=1.0, embed_init_tgt=True, dn_labelbook_size=91, max_text_len=256, text_encoder_type='checkpoints/bert-base-uncased', use_text_enhancer=True, use_fusion_layer=True, use_checkpoint=True, use_transformer_ckpt=True, use_text_cross_attention=True, text_dropout=0.0, fusion_dropout=0.0, fusion_droppath=0.1, sub_sentence_present=True, max_labels=90, lr=0.0001, backbone_freeze_keywords=None, freeze_keywords=['backbone.0', 'bert'], lr_backbone=1e-05, lr_backbone_names=['backbone.0', 'bert'], lr_linear_proj_mult=1e-05, lr_linear_proj_names=['ref_point_head', 'sampling_offsets'], weight_decay=0.0001, param_dict_type='ddetr_in_mmdet', ddetr_lr_param=False, epochs=30, lr_drop=10, save_checkpoint_interval=10, clip_max_norm=0.1, onecyclelr=False, multi_step_lr=False, lr_drop_list=[10, 20], frozen_weights=None, dilation=False, pdetr3_bbox_embed_diff_each_layer=False, pdetr3_refHW=-1, random_refpoints_xy=False, fix_refpoints_hw=-1, dabdetr_yolo_like_anchor_update=False, dabdetr_deformable_encoder=False, dabdetr_deformable_decoder=False, use_deformable_box_attn=False, box_attn_type='roi_align', dec_layer_number=None, decoder_layer_noise=False, dln_xy_noise=0.2, dln_hw_noise=0.2, add_channel_attention=False, add_pos_value=False, two_stage_pat_embed=0, two_stage_add_query_num=0, two_stage_learn_wh=False, two_stage_default_hw=0.05, two_stage_keep_all_tokens=False, num_select=900, batch_norm_type='FrozenBatchNorm2d', masks=False, aux_loss=True, set_cost_class=5.0, set_cost_bbox=1.0, set_cost_giou=0.0, cls_loss_coef=5.0, bbox_loss_coef=1.0, giou_loss_coef=0.0, enc_loss_coef=1.0, interm_loss_coef=1.0, no_interm_box_loss=False, mask_loss_coef=1.0, dice_loss_coef=1.0, focal_alpha=0.25, focal_gamma=2.0, decoder_sa_type='sa', matcher_type='HungarianMatcher', decoder_module_seq=['sa', 'ca', 'ffn'], nms_iou_threshold=-1, dec_pred_class_embed_share=True, match_unstable_error=True, use_detached_boxes_dec_out=False, dn_scalar=100, box_threshold=0.23, text_threshold=0, use_coco_eval=False, label_list=['alcohol bottle', 'baguette roll', 'ball', 'banana', 'bead', 'bee', 'birthday candle', 'biscuit', 'boat', 'bottle', 'bowl', 'box', 'bread roll', 'brick', 'buffalo', 'bun', 'calamari ring', 'can', 'candle', 'cap', 'car', 'cartridge', 'cassette', 'cement bag', 'cereal', 'chewing gum piece', 'chopstick', 'clam', 'coffee bean', 'coin', 'cotton ball', 'cow', 'crane', 'crayon', 'croissant', 'crow', 'cup', 'cupcake', 'cupcake holder', 'fish', 'gemstone', 'go game piece', 'goat', 'goldfish snack', 'goose', 'ice cream', 'ice cream cone', 'instant noodle', 'jade stone', 'jeans', 'kidney bean', 'kitchen towel', 'lighter', 'lipstick', 'm&m piece', 'macaron', 'match', 'meat skewer', 'mini blind', 'mosaic tile', 'naan bread', 'nail', 'nut', 'onion ring', 'orange', 'pearl', 'pen', 'pencil', 'penguin', 'pepper', 'person', 'pigeon', 'plate', 'polka dot tile', 'potato', 'rice bag', 'roof tile', 'screw', 'shoe', 'spoon', 'spring roll', 'stair', 'stapler pin', 'straw', 'supermarket shelf', 'swan', 'tomato', 'watermelon', 'window', 'zebra'], val_label_list=['ant', 'bird', 'book', 'bottle cap', 'bullet', 'camel', 'chair', 'chicken wing', 'donut', 'donut holder', 'flamingo', 'flower', 'flower pot', 'grape', 'horse', 'kiwi', 'milk carton', 'oyster', 'oyster shell', 'package of fresh cut fruit', 'peach', 'pill', 'polka dot', 'prawn cracker', 'sausage', 'seagull', 'shallot', 'shirt', 'skateboard', 'toilet paper roll']) + +DEBUG  2024-03-29 17:46:26,832 | build model ... ... +DEBUG  2024-03-29 17:46:28,620 | build model, done. +INFO  2024-03-29 17:46:28,622 | number of params:236717952 +INFO  2024-03-29 17:46:28,625 | params before freezing: +{ + "transformer.level_embed": 1024, + "transformer.encoder.layers.0.self_attn.sampling_offsets.weight": 65536, + "transformer.encoder.layers.0.self_attn.sampling_offsets.bias": 256, + "transformer.encoder.layers.0.self_attn.attention_weights.weight": 32768, + "transformer.encoder.layers.0.self_attn.attention_weights.bias": 128, + "transformer.encoder.layers.0.self_attn.value_proj.weight": 65536, + "transformer.encoder.layers.0.self_attn.value_proj.bias": 256, + "transformer.encoder.layers.0.self_attn.output_proj.weight": 65536, + "transformer.encoder.layers.0.self_attn.output_proj.bias": 256, + "transformer.encoder.layers.0.norm1.weight": 256, + "transformer.encoder.layers.0.norm1.bias": 256, + "transformer.encoder.layers.0.linear1.weight": 524288, + "transformer.encoder.layers.0.linear1.bias": 2048, + "transformer.encoder.layers.0.linear2.weight": 524288, + "transformer.encoder.layers.0.linear2.bias": 256, + "transformer.encoder.layers.0.norm2.weight": 256, + "transformer.encoder.layers.0.norm2.bias": 256, + "transformer.encoder.layers.1.self_attn.sampling_offsets.weight": 65536, + "transformer.encoder.layers.1.self_attn.sampling_offsets.bias": 256, + "transformer.encoder.layers.1.self_attn.attention_weights.weight": 32768, + "transformer.encoder.layers.1.self_attn.attention_weights.bias": 128, + "transformer.encoder.layers.1.self_attn.value_proj.weight": 65536, + "transformer.encoder.layers.1.self_attn.value_proj.bias": 256, + "transformer.encoder.layers.1.self_attn.output_proj.weight": 65536, + "transformer.encoder.layers.1.self_attn.output_proj.bias": 256, + "transformer.encoder.layers.1.norm1.weight": 256, + "transformer.encoder.layers.1.norm1.bias": 256, + "transformer.encoder.layers.1.linear1.weight": 524288, + "transformer.encoder.layers.1.linear1.bias": 2048, + "transformer.encoder.layers.1.linear2.weight": 524288, + "transformer.encoder.layers.1.linear2.bias": 256, + "transformer.encoder.layers.1.norm2.weight": 256, + "transformer.encoder.layers.1.norm2.bias": 256, + "transformer.encoder.layers.2.self_attn.sampling_offsets.weight": 65536, + "transformer.encoder.layers.2.self_attn.sampling_offsets.bias": 256, + "transformer.encoder.layers.2.self_attn.attention_weights.weight": 32768, + "transformer.encoder.layers.2.self_attn.attention_weights.bias": 128, + "transformer.encoder.layers.2.self_attn.value_proj.weight": 65536, + "transformer.encoder.layers.2.self_attn.value_proj.bias": 256, + "transformer.encoder.layers.2.self_attn.output_proj.weight": 65536, + "transformer.encoder.layers.2.self_attn.output_proj.bias": 256, + "transformer.encoder.layers.2.norm1.weight": 256, + "transformer.encoder.layers.2.norm1.bias": 256, + "transformer.encoder.layers.2.linear1.weight": 524288, + "transformer.encoder.layers.2.linear1.bias": 2048, + "transformer.encoder.layers.2.linear2.weight": 524288, + "transformer.encoder.layers.2.linear2.bias": 256, + "transformer.encoder.layers.2.norm2.weight": 256, + "transformer.encoder.layers.2.norm2.bias": 256, + "transformer.encoder.layers.3.self_attn.sampling_offsets.weight": 65536, + "transformer.encoder.layers.3.self_attn.sampling_offsets.bias": 256, + "transformer.encoder.layers.3.self_attn.attention_weights.weight": 32768, + "transformer.encoder.layers.3.self_attn.attention_weights.bias": 128, + "transformer.encoder.layers.3.self_attn.value_proj.weight": 65536, + "transformer.encoder.layers.3.self_attn.value_proj.bias": 256, + "transformer.encoder.layers.3.self_attn.output_proj.weight": 65536, + "transformer.encoder.layers.3.self_attn.output_proj.bias": 256, + "transformer.encoder.layers.3.norm1.weight": 256, + "transformer.encoder.layers.3.norm1.bias": 256, + "transformer.encoder.layers.3.linear1.weight": 524288, + "transformer.encoder.layers.3.linear1.bias": 2048, + "transformer.encoder.layers.3.linear2.weight": 524288, + "transformer.encoder.layers.3.linear2.bias": 256, + "transformer.encoder.layers.3.norm2.weight": 256, + "transformer.encoder.layers.3.norm2.bias": 256, + "transformer.encoder.layers.4.self_attn.sampling_offsets.weight": 65536, + "transformer.encoder.layers.4.self_attn.sampling_offsets.bias": 256, + "transformer.encoder.layers.4.self_attn.attention_weights.weight": 32768, + "transformer.encoder.layers.4.self_attn.attention_weights.bias": 128, + "transformer.encoder.layers.4.self_attn.value_proj.weight": 65536, + "transformer.encoder.layers.4.self_attn.value_proj.bias": 256, + "transformer.encoder.layers.4.self_attn.output_proj.weight": 65536, + "transformer.encoder.layers.4.self_attn.output_proj.bias": 256, + "transformer.encoder.layers.4.norm1.weight": 256, + "transformer.encoder.layers.4.norm1.bias": 256, + "transformer.encoder.layers.4.linear1.weight": 524288, + "transformer.encoder.layers.4.linear1.bias": 2048, + "transformer.encoder.layers.4.linear2.weight": 524288, + "transformer.encoder.layers.4.linear2.bias": 256, + "transformer.encoder.layers.4.norm2.weight": 256, + "transformer.encoder.layers.4.norm2.bias": 256, + "transformer.encoder.layers.5.self_attn.sampling_offsets.weight": 65536, + "transformer.encoder.layers.5.self_attn.sampling_offsets.bias": 256, + "transformer.encoder.layers.5.self_attn.attention_weights.weight": 32768, + "transformer.encoder.layers.5.self_attn.attention_weights.bias": 128, + "transformer.encoder.layers.5.self_attn.value_proj.weight": 65536, + "transformer.encoder.layers.5.self_attn.value_proj.bias": 256, + "transformer.encoder.layers.5.self_attn.output_proj.weight": 65536, + "transformer.encoder.layers.5.self_attn.output_proj.bias": 256, + "transformer.encoder.layers.5.norm1.weight": 256, + "transformer.encoder.layers.5.norm1.bias": 256, + "transformer.encoder.layers.5.linear1.weight": 524288, + "transformer.encoder.layers.5.linear1.bias": 2048, + "transformer.encoder.layers.5.linear2.weight": 524288, + "transformer.encoder.layers.5.linear2.bias": 256, + "transformer.encoder.layers.5.norm2.weight": 256, + "transformer.encoder.layers.5.norm2.bias": 256, + "transformer.encoder.text_layers.0.self_attn.in_proj_weight": 196608, + "transformer.encoder.text_layers.0.self_attn.in_proj_bias": 768, + "transformer.encoder.text_layers.0.self_attn.out_proj.weight": 65536, + "transformer.encoder.text_layers.0.self_attn.out_proj.bias": 256, + "transformer.encoder.text_layers.0.linear1.weight": 262144, + "transformer.encoder.text_layers.0.linear1.bias": 1024, + "transformer.encoder.text_layers.0.linear2.weight": 262144, + "transformer.encoder.text_layers.0.linear2.bias": 256, + "transformer.encoder.text_layers.0.norm1.weight": 256, + "transformer.encoder.text_layers.0.norm1.bias": 256, + "transformer.encoder.text_layers.0.norm2.weight": 256, + "transformer.encoder.text_layers.0.norm2.bias": 256, + "transformer.encoder.text_layers.1.self_attn.in_proj_weight": 196608, + "transformer.encoder.text_layers.1.self_attn.in_proj_bias": 768, + "transformer.encoder.text_layers.1.self_attn.out_proj.weight": 65536, + "transformer.encoder.text_layers.1.self_attn.out_proj.bias": 256, + "transformer.encoder.text_layers.1.linear1.weight": 262144, + "transformer.encoder.text_layers.1.linear1.bias": 1024, + "transformer.encoder.text_layers.1.linear2.weight": 262144, + "transformer.encoder.text_layers.1.linear2.bias": 256, + "transformer.encoder.text_layers.1.norm1.weight": 256, + "transformer.encoder.text_layers.1.norm1.bias": 256, + "transformer.encoder.text_layers.1.norm2.weight": 256, + "transformer.encoder.text_layers.1.norm2.bias": 256, + "transformer.encoder.text_layers.2.self_attn.in_proj_weight": 196608, + "transformer.encoder.text_layers.2.self_attn.in_proj_bias": 768, + "transformer.encoder.text_layers.2.self_attn.out_proj.weight": 65536, + "transformer.encoder.text_layers.2.self_attn.out_proj.bias": 256, + "transformer.encoder.text_layers.2.linear1.weight": 262144, + "transformer.encoder.text_layers.2.linear1.bias": 1024, + "transformer.encoder.text_layers.2.linear2.weight": 262144, + "transformer.encoder.text_layers.2.linear2.bias": 256, + "transformer.encoder.text_layers.2.norm1.weight": 256, + "transformer.encoder.text_layers.2.norm1.bias": 256, + "transformer.encoder.text_layers.2.norm2.weight": 256, + "transformer.encoder.text_layers.2.norm2.bias": 256, + "transformer.encoder.text_layers.3.self_attn.in_proj_weight": 196608, + "transformer.encoder.text_layers.3.self_attn.in_proj_bias": 768, + "transformer.encoder.text_layers.3.self_attn.out_proj.weight": 65536, + "transformer.encoder.text_layers.3.self_attn.out_proj.bias": 256, + "transformer.encoder.text_layers.3.linear1.weight": 262144, + "transformer.encoder.text_layers.3.linear1.bias": 1024, + "transformer.encoder.text_layers.3.linear2.weight": 262144, + "transformer.encoder.text_layers.3.linear2.bias": 256, + "transformer.encoder.text_layers.3.norm1.weight": 256, + "transformer.encoder.text_layers.3.norm1.bias": 256, + "transformer.encoder.text_layers.3.norm2.weight": 256, + "transformer.encoder.text_layers.3.norm2.bias": 256, + "transformer.encoder.text_layers.4.self_attn.in_proj_weight": 196608, + "transformer.encoder.text_layers.4.self_attn.in_proj_bias": 768, + "transformer.encoder.text_layers.4.self_attn.out_proj.weight": 65536, + "transformer.encoder.text_layers.4.self_attn.out_proj.bias": 256, + "transformer.encoder.text_layers.4.linear1.weight": 262144, + "transformer.encoder.text_layers.4.linear1.bias": 1024, + "transformer.encoder.text_layers.4.linear2.weight": 262144, + "transformer.encoder.text_layers.4.linear2.bias": 256, + "transformer.encoder.text_layers.4.norm1.weight": 256, + "transformer.encoder.text_layers.4.norm1.bias": 256, + "transformer.encoder.text_layers.4.norm2.weight": 256, + "transformer.encoder.text_layers.4.norm2.bias": 256, + "transformer.encoder.text_layers.5.self_attn.in_proj_weight": 196608, + "transformer.encoder.text_layers.5.self_attn.in_proj_bias": 768, + "transformer.encoder.text_layers.5.self_attn.out_proj.weight": 65536, + "transformer.encoder.text_layers.5.self_attn.out_proj.bias": 256, + "transformer.encoder.text_layers.5.linear1.weight": 262144, + "transformer.encoder.text_layers.5.linear1.bias": 1024, + "transformer.encoder.text_layers.5.linear2.weight": 262144, + "transformer.encoder.text_layers.5.linear2.bias": 256, + "transformer.encoder.text_layers.5.norm1.weight": 256, + "transformer.encoder.text_layers.5.norm1.bias": 256, + "transformer.encoder.text_layers.5.norm2.weight": 256, + "transformer.encoder.text_layers.5.norm2.bias": 256, + "transformer.encoder.fusion_layers.0.gamma_v": 256, + "transformer.encoder.fusion_layers.0.gamma_l": 256, + "transformer.encoder.fusion_layers.0.layer_norm_v.weight": 256, + "transformer.encoder.fusion_layers.0.layer_norm_v.bias": 256, + "transformer.encoder.fusion_layers.0.layer_norm_l.weight": 256, + "transformer.encoder.fusion_layers.0.layer_norm_l.bias": 256, + "transformer.encoder.fusion_layers.0.attn.v_proj.weight": 262144, + "transformer.encoder.fusion_layers.0.attn.v_proj.bias": 1024, + "transformer.encoder.fusion_layers.0.attn.l_proj.weight": 262144, + "transformer.encoder.fusion_layers.0.attn.l_proj.bias": 1024, + "transformer.encoder.fusion_layers.0.attn.values_v_proj.weight": 262144, + "transformer.encoder.fusion_layers.0.attn.values_v_proj.bias": 1024, + "transformer.encoder.fusion_layers.0.attn.values_l_proj.weight": 262144, + "transformer.encoder.fusion_layers.0.attn.values_l_proj.bias": 1024, + "transformer.encoder.fusion_layers.0.attn.out_v_proj.weight": 262144, + "transformer.encoder.fusion_layers.0.attn.out_v_proj.bias": 256, + "transformer.encoder.fusion_layers.0.attn.out_l_proj.weight": 262144, + "transformer.encoder.fusion_layers.0.attn.out_l_proj.bias": 256, + "transformer.encoder.fusion_layers.1.gamma_v": 256, + "transformer.encoder.fusion_layers.1.gamma_l": 256, + "transformer.encoder.fusion_layers.1.layer_norm_v.weight": 256, + "transformer.encoder.fusion_layers.1.layer_norm_v.bias": 256, + "transformer.encoder.fusion_layers.1.layer_norm_l.weight": 256, + "transformer.encoder.fusion_layers.1.layer_norm_l.bias": 256, + "transformer.encoder.fusion_layers.1.attn.v_proj.weight": 262144, + "transformer.encoder.fusion_layers.1.attn.v_proj.bias": 1024, + "transformer.encoder.fusion_layers.1.attn.l_proj.weight": 262144, + "transformer.encoder.fusion_layers.1.attn.l_proj.bias": 1024, + "transformer.encoder.fusion_layers.1.attn.values_v_proj.weight": 262144, + "transformer.encoder.fusion_layers.1.attn.values_v_proj.bias": 1024, + "transformer.encoder.fusion_layers.1.attn.values_l_proj.weight": 262144, + "transformer.encoder.fusion_layers.1.attn.values_l_proj.bias": 1024, + "transformer.encoder.fusion_layers.1.attn.out_v_proj.weight": 262144, + "transformer.encoder.fusion_layers.1.attn.out_v_proj.bias": 256, + "transformer.encoder.fusion_layers.1.attn.out_l_proj.weight": 262144, + "transformer.encoder.fusion_layers.1.attn.out_l_proj.bias": 256, + "transformer.encoder.fusion_layers.2.gamma_v": 256, + "transformer.encoder.fusion_layers.2.gamma_l": 256, + "transformer.encoder.fusion_layers.2.layer_norm_v.weight": 256, + "transformer.encoder.fusion_layers.2.layer_norm_v.bias": 256, + "transformer.encoder.fusion_layers.2.layer_norm_l.weight": 256, + "transformer.encoder.fusion_layers.2.layer_norm_l.bias": 256, + "transformer.encoder.fusion_layers.2.attn.v_proj.weight": 262144, + "transformer.encoder.fusion_layers.2.attn.v_proj.bias": 1024, + "transformer.encoder.fusion_layers.2.attn.l_proj.weight": 262144, + "transformer.encoder.fusion_layers.2.attn.l_proj.bias": 1024, + "transformer.encoder.fusion_layers.2.attn.values_v_proj.weight": 262144, + "transformer.encoder.fusion_layers.2.attn.values_v_proj.bias": 1024, + "transformer.encoder.fusion_layers.2.attn.values_l_proj.weight": 262144, + "transformer.encoder.fusion_layers.2.attn.values_l_proj.bias": 1024, + "transformer.encoder.fusion_layers.2.attn.out_v_proj.weight": 262144, + "transformer.encoder.fusion_layers.2.attn.out_v_proj.bias": 256, + "transformer.encoder.fusion_layers.2.attn.out_l_proj.weight": 262144, + "transformer.encoder.fusion_layers.2.attn.out_l_proj.bias": 256, + "transformer.encoder.fusion_layers.3.gamma_v": 256, + "transformer.encoder.fusion_layers.3.gamma_l": 256, + "transformer.encoder.fusion_layers.3.layer_norm_v.weight": 256, + "transformer.encoder.fusion_layers.3.layer_norm_v.bias": 256, + "transformer.encoder.fusion_layers.3.layer_norm_l.weight": 256, + "transformer.encoder.fusion_layers.3.layer_norm_l.bias": 256, + "transformer.encoder.fusion_layers.3.attn.v_proj.weight": 262144, + "transformer.encoder.fusion_layers.3.attn.v_proj.bias": 1024, + "transformer.encoder.fusion_layers.3.attn.l_proj.weight": 262144, + "transformer.encoder.fusion_layers.3.attn.l_proj.bias": 1024, + "transformer.encoder.fusion_layers.3.attn.values_v_proj.weight": 262144, + "transformer.encoder.fusion_layers.3.attn.values_v_proj.bias": 1024, + "transformer.encoder.fusion_layers.3.attn.values_l_proj.weight": 262144, + "transformer.encoder.fusion_layers.3.attn.values_l_proj.bias": 1024, + "transformer.encoder.fusion_layers.3.attn.out_v_proj.weight": 262144, + "transformer.encoder.fusion_layers.3.attn.out_v_proj.bias": 256, + "transformer.encoder.fusion_layers.3.attn.out_l_proj.weight": 262144, + "transformer.encoder.fusion_layers.3.attn.out_l_proj.bias": 256, + "transformer.encoder.fusion_layers.4.gamma_v": 256, + "transformer.encoder.fusion_layers.4.gamma_l": 256, + "transformer.encoder.fusion_layers.4.layer_norm_v.weight": 256, + "transformer.encoder.fusion_layers.4.layer_norm_v.bias": 256, + "transformer.encoder.fusion_layers.4.layer_norm_l.weight": 256, + "transformer.encoder.fusion_layers.4.layer_norm_l.bias": 256, + "transformer.encoder.fusion_layers.4.attn.v_proj.weight": 262144, + "transformer.encoder.fusion_layers.4.attn.v_proj.bias": 1024, + "transformer.encoder.fusion_layers.4.attn.l_proj.weight": 262144, + "transformer.encoder.fusion_layers.4.attn.l_proj.bias": 1024, + "transformer.encoder.fusion_layers.4.attn.values_v_proj.weight": 262144, + "transformer.encoder.fusion_layers.4.attn.values_v_proj.bias": 1024, + "transformer.encoder.fusion_layers.4.attn.values_l_proj.weight": 262144, + "transformer.encoder.fusion_layers.4.attn.values_l_proj.bias": 1024, + "transformer.encoder.fusion_layers.4.attn.out_v_proj.weight": 262144, + "transformer.encoder.fusion_layers.4.attn.out_v_proj.bias": 256, + "transformer.encoder.fusion_layers.4.attn.out_l_proj.weight": 262144, + "transformer.encoder.fusion_layers.4.attn.out_l_proj.bias": 256, + "transformer.encoder.fusion_layers.5.gamma_v": 256, + "transformer.encoder.fusion_layers.5.gamma_l": 256, + "transformer.encoder.fusion_layers.5.layer_norm_v.weight": 256, + "transformer.encoder.fusion_layers.5.layer_norm_v.bias": 256, + "transformer.encoder.fusion_layers.5.layer_norm_l.weight": 256, + "transformer.encoder.fusion_layers.5.layer_norm_l.bias": 256, + "transformer.encoder.fusion_layers.5.attn.v_proj.weight": 262144, + "transformer.encoder.fusion_layers.5.attn.v_proj.bias": 1024, + "transformer.encoder.fusion_layers.5.attn.l_proj.weight": 262144, + "transformer.encoder.fusion_layers.5.attn.l_proj.bias": 1024, + "transformer.encoder.fusion_layers.5.attn.values_v_proj.weight": 262144, + "transformer.encoder.fusion_layers.5.attn.values_v_proj.bias": 1024, + "transformer.encoder.fusion_layers.5.attn.values_l_proj.weight": 262144, + "transformer.encoder.fusion_layers.5.attn.values_l_proj.bias": 1024, + "transformer.encoder.fusion_layers.5.attn.out_v_proj.weight": 262144, + "transformer.encoder.fusion_layers.5.attn.out_v_proj.bias": 256, + "transformer.encoder.fusion_layers.5.attn.out_l_proj.weight": 262144, + "transformer.encoder.fusion_layers.5.attn.out_l_proj.bias": 256, + "transformer.decoder.layers.0.cross_attn.sampling_offsets.weight": 65536, + "transformer.decoder.layers.0.cross_attn.sampling_offsets.bias": 256, + "transformer.decoder.layers.0.cross_attn.attention_weights.weight": 32768, + "transformer.decoder.layers.0.cross_attn.attention_weights.bias": 128, + "transformer.decoder.layers.0.cross_attn.value_proj.weight": 65536, + "transformer.decoder.layers.0.cross_attn.value_proj.bias": 256, + "transformer.decoder.layers.0.cross_attn.output_proj.weight": 65536, + "transformer.decoder.layers.0.cross_attn.output_proj.bias": 256, + "transformer.decoder.layers.0.norm1.weight": 256, + "transformer.decoder.layers.0.norm1.bias": 256, + "transformer.decoder.layers.0.ca_text.in_proj_weight": 196608, + "transformer.decoder.layers.0.ca_text.in_proj_bias": 768, + "transformer.decoder.layers.0.ca_text.out_proj.weight": 65536, + "transformer.decoder.layers.0.ca_text.out_proj.bias": 256, + "transformer.decoder.layers.0.catext_norm.weight": 256, + "transformer.decoder.layers.0.catext_norm.bias": 256, + "transformer.decoder.layers.0.self_attn.in_proj_weight": 196608, + "transformer.decoder.layers.0.self_attn.in_proj_bias": 768, + "transformer.decoder.layers.0.self_attn.out_proj.weight": 65536, + "transformer.decoder.layers.0.self_attn.out_proj.bias": 256, + "transformer.decoder.layers.0.norm2.weight": 256, + "transformer.decoder.layers.0.norm2.bias": 256, + "transformer.decoder.layers.0.linear1.weight": 524288, + "transformer.decoder.layers.0.linear1.bias": 2048, + "transformer.decoder.layers.0.linear2.weight": 524288, + "transformer.decoder.layers.0.linear2.bias": 256, + "transformer.decoder.layers.0.norm3.weight": 256, + "transformer.decoder.layers.0.norm3.bias": 256, + "transformer.decoder.layers.1.cross_attn.sampling_offsets.weight": 65536, + "transformer.decoder.layers.1.cross_attn.sampling_offsets.bias": 256, + "transformer.decoder.layers.1.cross_attn.attention_weights.weight": 32768, + "transformer.decoder.layers.1.cross_attn.attention_weights.bias": 128, + "transformer.decoder.layers.1.cross_attn.value_proj.weight": 65536, + "transformer.decoder.layers.1.cross_attn.value_proj.bias": 256, + "transformer.decoder.layers.1.cross_attn.output_proj.weight": 65536, + "transformer.decoder.layers.1.cross_attn.output_proj.bias": 256, + "transformer.decoder.layers.1.norm1.weight": 256, + "transformer.decoder.layers.1.norm1.bias": 256, + "transformer.decoder.layers.1.ca_text.in_proj_weight": 196608, + "transformer.decoder.layers.1.ca_text.in_proj_bias": 768, + "transformer.decoder.layers.1.ca_text.out_proj.weight": 65536, + "transformer.decoder.layers.1.ca_text.out_proj.bias": 256, + "transformer.decoder.layers.1.catext_norm.weight": 256, + "transformer.decoder.layers.1.catext_norm.bias": 256, + "transformer.decoder.layers.1.self_attn.in_proj_weight": 196608, + "transformer.decoder.layers.1.self_attn.in_proj_bias": 768, + "transformer.decoder.layers.1.self_attn.out_proj.weight": 65536, + "transformer.decoder.layers.1.self_attn.out_proj.bias": 256, + "transformer.decoder.layers.1.norm2.weight": 256, + "transformer.decoder.layers.1.norm2.bias": 256, + "transformer.decoder.layers.1.linear1.weight": 524288, + "transformer.decoder.layers.1.linear1.bias": 2048, + "transformer.decoder.layers.1.linear2.weight": 524288, + "transformer.decoder.layers.1.linear2.bias": 256, + "transformer.decoder.layers.1.norm3.weight": 256, + "transformer.decoder.layers.1.norm3.bias": 256, + "transformer.decoder.layers.2.cross_attn.sampling_offsets.weight": 65536, + "transformer.decoder.layers.2.cross_attn.sampling_offsets.bias": 256, + "transformer.decoder.layers.2.cross_attn.attention_weights.weight": 32768, + "transformer.decoder.layers.2.cross_attn.attention_weights.bias": 128, + "transformer.decoder.layers.2.cross_attn.value_proj.weight": 65536, + "transformer.decoder.layers.2.cross_attn.value_proj.bias": 256, + "transformer.decoder.layers.2.cross_attn.output_proj.weight": 65536, + "transformer.decoder.layers.2.cross_attn.output_proj.bias": 256, + "transformer.decoder.layers.2.norm1.weight": 256, + "transformer.decoder.layers.2.norm1.bias": 256, + "transformer.decoder.layers.2.ca_text.in_proj_weight": 196608, + "transformer.decoder.layers.2.ca_text.in_proj_bias": 768, + "transformer.decoder.layers.2.ca_text.out_proj.weight": 65536, + "transformer.decoder.layers.2.ca_text.out_proj.bias": 256, + "transformer.decoder.layers.2.catext_norm.weight": 256, + "transformer.decoder.layers.2.catext_norm.bias": 256, + "transformer.decoder.layers.2.self_attn.in_proj_weight": 196608, + "transformer.decoder.layers.2.self_attn.in_proj_bias": 768, + "transformer.decoder.layers.2.self_attn.out_proj.weight": 65536, + "transformer.decoder.layers.2.self_attn.out_proj.bias": 256, + "transformer.decoder.layers.2.norm2.weight": 256, + "transformer.decoder.layers.2.norm2.bias": 256, + "transformer.decoder.layers.2.linear1.weight": 524288, + "transformer.decoder.layers.2.linear1.bias": 2048, + "transformer.decoder.layers.2.linear2.weight": 524288, + "transformer.decoder.layers.2.linear2.bias": 256, + "transformer.decoder.layers.2.norm3.weight": 256, + "transformer.decoder.layers.2.norm3.bias": 256, + "transformer.decoder.layers.3.cross_attn.sampling_offsets.weight": 65536, + "transformer.decoder.layers.3.cross_attn.sampling_offsets.bias": 256, + "transformer.decoder.layers.3.cross_attn.attention_weights.weight": 32768, + "transformer.decoder.layers.3.cross_attn.attention_weights.bias": 128, + "transformer.decoder.layers.3.cross_attn.value_proj.weight": 65536, + "transformer.decoder.layers.3.cross_attn.value_proj.bias": 256, + "transformer.decoder.layers.3.cross_attn.output_proj.weight": 65536, + "transformer.decoder.layers.3.cross_attn.output_proj.bias": 256, + "transformer.decoder.layers.3.norm1.weight": 256, + "transformer.decoder.layers.3.norm1.bias": 256, + "transformer.decoder.layers.3.ca_text.in_proj_weight": 196608, + "transformer.decoder.layers.3.ca_text.in_proj_bias": 768, + "transformer.decoder.layers.3.ca_text.out_proj.weight": 65536, + "transformer.decoder.layers.3.ca_text.out_proj.bias": 256, + "transformer.decoder.layers.3.catext_norm.weight": 256, + "transformer.decoder.layers.3.catext_norm.bias": 256, + "transformer.decoder.layers.3.self_attn.in_proj_weight": 196608, + "transformer.decoder.layers.3.self_attn.in_proj_bias": 768, + "transformer.decoder.layers.3.self_attn.out_proj.weight": 65536, + "transformer.decoder.layers.3.self_attn.out_proj.bias": 256, + "transformer.decoder.layers.3.norm2.weight": 256, + "transformer.decoder.layers.3.norm2.bias": 256, + "transformer.decoder.layers.3.linear1.weight": 524288, + "transformer.decoder.layers.3.linear1.bias": 2048, + "transformer.decoder.layers.3.linear2.weight": 524288, + "transformer.decoder.layers.3.linear2.bias": 256, + "transformer.decoder.layers.3.norm3.weight": 256, + "transformer.decoder.layers.3.norm3.bias": 256, + "transformer.decoder.layers.4.cross_attn.sampling_offsets.weight": 65536, + "transformer.decoder.layers.4.cross_attn.sampling_offsets.bias": 256, + "transformer.decoder.layers.4.cross_attn.attention_weights.weight": 32768, + "transformer.decoder.layers.4.cross_attn.attention_weights.bias": 128, + "transformer.decoder.layers.4.cross_attn.value_proj.weight": 65536, + "transformer.decoder.layers.4.cross_attn.value_proj.bias": 256, + "transformer.decoder.layers.4.cross_attn.output_proj.weight": 65536, + "transformer.decoder.layers.4.cross_attn.output_proj.bias": 256, + "transformer.decoder.layers.4.norm1.weight": 256, + "transformer.decoder.layers.4.norm1.bias": 256, + "transformer.decoder.layers.4.ca_text.in_proj_weight": 196608, + "transformer.decoder.layers.4.ca_text.in_proj_bias": 768, + "transformer.decoder.layers.4.ca_text.out_proj.weight": 65536, + "transformer.decoder.layers.4.ca_text.out_proj.bias": 256, + "transformer.decoder.layers.4.catext_norm.weight": 256, + "transformer.decoder.layers.4.catext_norm.bias": 256, + "transformer.decoder.layers.4.self_attn.in_proj_weight": 196608, + "transformer.decoder.layers.4.self_attn.in_proj_bias": 768, + "transformer.decoder.layers.4.self_attn.out_proj.weight": 65536, + "transformer.decoder.layers.4.self_attn.out_proj.bias": 256, + "transformer.decoder.layers.4.norm2.weight": 256, + "transformer.decoder.layers.4.norm2.bias": 256, + "transformer.decoder.layers.4.linear1.weight": 524288, + "transformer.decoder.layers.4.linear1.bias": 2048, + "transformer.decoder.layers.4.linear2.weight": 524288, + "transformer.decoder.layers.4.linear2.bias": 256, + "transformer.decoder.layers.4.norm3.weight": 256, + "transformer.decoder.layers.4.norm3.bias": 256, + "transformer.decoder.layers.5.cross_attn.sampling_offsets.weight": 65536, + "transformer.decoder.layers.5.cross_attn.sampling_offsets.bias": 256, + "transformer.decoder.layers.5.cross_attn.attention_weights.weight": 32768, + "transformer.decoder.layers.5.cross_attn.attention_weights.bias": 128, + "transformer.decoder.layers.5.cross_attn.value_proj.weight": 65536, + "transformer.decoder.layers.5.cross_attn.value_proj.bias": 256, + "transformer.decoder.layers.5.cross_attn.output_proj.weight": 65536, + "transformer.decoder.layers.5.cross_attn.output_proj.bias": 256, + "transformer.decoder.layers.5.norm1.weight": 256, + "transformer.decoder.layers.5.norm1.bias": 256, + "transformer.decoder.layers.5.ca_text.in_proj_weight": 196608, + "transformer.decoder.layers.5.ca_text.in_proj_bias": 768, + "transformer.decoder.layers.5.ca_text.out_proj.weight": 65536, + "transformer.decoder.layers.5.ca_text.out_proj.bias": 256, + "transformer.decoder.layers.5.catext_norm.weight": 256, + "transformer.decoder.layers.5.catext_norm.bias": 256, + "transformer.decoder.layers.5.self_attn.in_proj_weight": 196608, + "transformer.decoder.layers.5.self_attn.in_proj_bias": 768, + "transformer.decoder.layers.5.self_attn.out_proj.weight": 65536, + "transformer.decoder.layers.5.self_attn.out_proj.bias": 256, + "transformer.decoder.layers.5.norm2.weight": 256, + "transformer.decoder.layers.5.norm2.bias": 256, + "transformer.decoder.layers.5.linear1.weight": 524288, + "transformer.decoder.layers.5.linear1.bias": 2048, + "transformer.decoder.layers.5.linear2.weight": 524288, + "transformer.decoder.layers.5.linear2.bias": 256, + "transformer.decoder.layers.5.norm3.weight": 256, + "transformer.decoder.layers.5.norm3.bias": 256, + "transformer.decoder.norm.weight": 256, + "transformer.decoder.norm.bias": 256, + "transformer.decoder.ref_point_head.layers.0.weight": 131072, + "transformer.decoder.ref_point_head.layers.0.bias": 256, + "transformer.decoder.ref_point_head.layers.1.weight": 65536, + "transformer.decoder.ref_point_head.layers.1.bias": 256, + "transformer.decoder.bbox_embed.0.layers.0.weight": 65536, + "transformer.decoder.bbox_embed.0.layers.0.bias": 256, + "transformer.decoder.bbox_embed.0.layers.1.weight": 65536, + "transformer.decoder.bbox_embed.0.layers.1.bias": 256, + "transformer.decoder.bbox_embed.0.layers.2.weight": 1024, + "transformer.decoder.bbox_embed.0.layers.2.bias": 4, + "transformer.tgt_embed.weight": 230400, + "transformer.enc_output.weight": 65536, + "transformer.enc_output.bias": 256, + "transformer.enc_output_norm.weight": 256, + "transformer.enc_output_norm.bias": 256, + "transformer.enc_out_bbox_embed.layers.0.weight": 65536, + "transformer.enc_out_bbox_embed.layers.0.bias": 256, + "transformer.enc_out_bbox_embed.layers.1.weight": 65536, + "transformer.enc_out_bbox_embed.layers.1.bias": 256, + "transformer.enc_out_bbox_embed.layers.2.weight": 1024, + "transformer.enc_out_bbox_embed.layers.2.bias": 4, + "feature_map_proj.weight": 458752, + "feature_map_proj.bias": 256, + "feature_map_encoder.layers.0.norm1.weight": 256, + "feature_map_encoder.layers.0.norm1.bias": 256, + "feature_map_encoder.layers.0.norm2.weight": 256, + "feature_map_encoder.layers.0.norm2.bias": 256, + "feature_map_encoder.layers.0.self_attn.in_proj_weight": 196608, + "feature_map_encoder.layers.0.self_attn.in_proj_bias": 768, + "feature_map_encoder.layers.0.self_attn.out_proj.weight": 65536, + "feature_map_encoder.layers.0.self_attn.out_proj.bias": 256, + "feature_map_encoder.layers.0.mlp.linear1.weight": 524288, + "feature_map_encoder.layers.0.mlp.linear1.bias": 2048, + "feature_map_encoder.layers.0.mlp.linear2.weight": 524288, + "feature_map_encoder.layers.0.mlp.linear2.bias": 256, + "feature_map_encoder.layers.1.norm1.weight": 256, + "feature_map_encoder.layers.1.norm1.bias": 256, + "feature_map_encoder.layers.1.norm2.weight": 256, + "feature_map_encoder.layers.1.norm2.bias": 256, + "feature_map_encoder.layers.1.self_attn.in_proj_weight": 196608, + "feature_map_encoder.layers.1.self_attn.in_proj_bias": 768, + "feature_map_encoder.layers.1.self_attn.out_proj.weight": 65536, + "feature_map_encoder.layers.1.self_attn.out_proj.bias": 256, + "feature_map_encoder.layers.1.mlp.linear1.weight": 524288, + "feature_map_encoder.layers.1.mlp.linear1.bias": 2048, + "feature_map_encoder.layers.1.mlp.linear2.weight": 524288, + "feature_map_encoder.layers.1.mlp.linear2.bias": 256, + "feature_map_encoder.layers.2.norm1.weight": 256, + "feature_map_encoder.layers.2.norm1.bias": 256, + "feature_map_encoder.layers.2.norm2.weight": 256, + "feature_map_encoder.layers.2.norm2.bias": 256, + "feature_map_encoder.layers.2.self_attn.in_proj_weight": 196608, + "feature_map_encoder.layers.2.self_attn.in_proj_bias": 768, + "feature_map_encoder.layers.2.self_attn.out_proj.weight": 65536, + "feature_map_encoder.layers.2.self_attn.out_proj.bias": 256, + "feature_map_encoder.layers.2.mlp.linear1.weight": 524288, + "feature_map_encoder.layers.2.mlp.linear1.bias": 2048, + "feature_map_encoder.layers.2.mlp.linear2.weight": 524288, + "feature_map_encoder.layers.2.mlp.linear2.bias": 256, + "feature_map_encoder.norm.weight": 256, + "feature_map_encoder.norm.bias": 256, + "bert.embeddings.word_embeddings.weight": 23440896, + "bert.embeddings.position_embeddings.weight": 393216, + "bert.embeddings.token_type_embeddings.weight": 1536, + "bert.embeddings.LayerNorm.weight": 768, + "bert.embeddings.LayerNorm.bias": 768, + "bert.encoder.layer.0.attention.self.query.weight": 589824, + "bert.encoder.layer.0.attention.self.query.bias": 768, + "bert.encoder.layer.0.attention.self.key.weight": 589824, + "bert.encoder.layer.0.attention.self.key.bias": 768, + "bert.encoder.layer.0.attention.self.value.weight": 589824, + "bert.encoder.layer.0.attention.self.value.bias": 768, + "bert.encoder.layer.0.attention.output.dense.weight": 589824, + "bert.encoder.layer.0.attention.output.dense.bias": 768, + "bert.encoder.layer.0.attention.output.LayerNorm.weight": 768, + "bert.encoder.layer.0.attention.output.LayerNorm.bias": 768, + "bert.encoder.layer.0.intermediate.dense.weight": 2359296, + "bert.encoder.layer.0.intermediate.dense.bias": 3072, + "bert.encoder.layer.0.output.dense.weight": 2359296, + "bert.encoder.layer.0.output.dense.bias": 768, + "bert.encoder.layer.0.output.LayerNorm.weight": 768, + "bert.encoder.layer.0.output.LayerNorm.bias": 768, + "bert.encoder.layer.1.attention.self.query.weight": 589824, + "bert.encoder.layer.1.attention.self.query.bias": 768, + "bert.encoder.layer.1.attention.self.key.weight": 589824, + "bert.encoder.layer.1.attention.self.key.bias": 768, + "bert.encoder.layer.1.attention.self.value.weight": 589824, + "bert.encoder.layer.1.attention.self.value.bias": 768, + "bert.encoder.layer.1.attention.output.dense.weight": 589824, + "bert.encoder.layer.1.attention.output.dense.bias": 768, + "bert.encoder.layer.1.attention.output.LayerNorm.weight": 768, + "bert.encoder.layer.1.attention.output.LayerNorm.bias": 768, + "bert.encoder.layer.1.intermediate.dense.weight": 2359296, + "bert.encoder.layer.1.intermediate.dense.bias": 3072, + "bert.encoder.layer.1.output.dense.weight": 2359296, + "bert.encoder.layer.1.output.dense.bias": 768, + "bert.encoder.layer.1.output.LayerNorm.weight": 768, + "bert.encoder.layer.1.output.LayerNorm.bias": 768, + "bert.encoder.layer.2.attention.self.query.weight": 589824, + "bert.encoder.layer.2.attention.self.query.bias": 768, + "bert.encoder.layer.2.attention.self.key.weight": 589824, + "bert.encoder.layer.2.attention.self.key.bias": 768, + "bert.encoder.layer.2.attention.self.value.weight": 589824, + "bert.encoder.layer.2.attention.self.value.bias": 768, + "bert.encoder.layer.2.attention.output.dense.weight": 589824, + "bert.encoder.layer.2.attention.output.dense.bias": 768, + "bert.encoder.layer.2.attention.output.LayerNorm.weight": 768, + "bert.encoder.layer.2.attention.output.LayerNorm.bias": 768, + "bert.encoder.layer.2.intermediate.dense.weight": 2359296, + "bert.encoder.layer.2.intermediate.dense.bias": 3072, + "bert.encoder.layer.2.output.dense.weight": 2359296, + "bert.encoder.layer.2.output.dense.bias": 768, + "bert.encoder.layer.2.output.LayerNorm.weight": 768, + "bert.encoder.layer.2.output.LayerNorm.bias": 768, + "bert.encoder.layer.3.attention.self.query.weight": 589824, + "bert.encoder.layer.3.attention.self.query.bias": 768, + "bert.encoder.layer.3.attention.self.key.weight": 589824, + "bert.encoder.layer.3.attention.self.key.bias": 768, + "bert.encoder.layer.3.attention.self.value.weight": 589824, + "bert.encoder.layer.3.attention.self.value.bias": 768, + "bert.encoder.layer.3.attention.output.dense.weight": 589824, + "bert.encoder.layer.3.attention.output.dense.bias": 768, + "bert.encoder.layer.3.attention.output.LayerNorm.weight": 768, + "bert.encoder.layer.3.attention.output.LayerNorm.bias": 768, + "bert.encoder.layer.3.intermediate.dense.weight": 2359296, + "bert.encoder.layer.3.intermediate.dense.bias": 3072, + "bert.encoder.layer.3.output.dense.weight": 2359296, + "bert.encoder.layer.3.output.dense.bias": 768, + "bert.encoder.layer.3.output.LayerNorm.weight": 768, + "bert.encoder.layer.3.output.LayerNorm.bias": 768, + "bert.encoder.layer.4.attention.self.query.weight": 589824, + "bert.encoder.layer.4.attention.self.query.bias": 768, + "bert.encoder.layer.4.attention.self.key.weight": 589824, + "bert.encoder.layer.4.attention.self.key.bias": 768, + "bert.encoder.layer.4.attention.self.value.weight": 589824, + "bert.encoder.layer.4.attention.self.value.bias": 768, + "bert.encoder.layer.4.attention.output.dense.weight": 589824, + "bert.encoder.layer.4.attention.output.dense.bias": 768, + "bert.encoder.layer.4.attention.output.LayerNorm.weight": 768, + "bert.encoder.layer.4.attention.output.LayerNorm.bias": 768, + "bert.encoder.layer.4.intermediate.dense.weight": 2359296, + "bert.encoder.layer.4.intermediate.dense.bias": 3072, + "bert.encoder.layer.4.output.dense.weight": 2359296, + "bert.encoder.layer.4.output.dense.bias": 768, + "bert.encoder.layer.4.output.LayerNorm.weight": 768, + "bert.encoder.layer.4.output.LayerNorm.bias": 768, + "bert.encoder.layer.5.attention.self.query.weight": 589824, + "bert.encoder.layer.5.attention.self.query.bias": 768, + "bert.encoder.layer.5.attention.self.key.weight": 589824, + "bert.encoder.layer.5.attention.self.key.bias": 768, + "bert.encoder.layer.5.attention.self.value.weight": 589824, + "bert.encoder.layer.5.attention.self.value.bias": 768, + "bert.encoder.layer.5.attention.output.dense.weight": 589824, + "bert.encoder.layer.5.attention.output.dense.bias": 768, + "bert.encoder.layer.5.attention.output.LayerNorm.weight": 768, + "bert.encoder.layer.5.attention.output.LayerNorm.bias": 768, + "bert.encoder.layer.5.intermediate.dense.weight": 2359296, + "bert.encoder.layer.5.intermediate.dense.bias": 3072, + "bert.encoder.layer.5.output.dense.weight": 2359296, + "bert.encoder.layer.5.output.dense.bias": 768, + "bert.encoder.layer.5.output.LayerNorm.weight": 768, + "bert.encoder.layer.5.output.LayerNorm.bias": 768, + "bert.encoder.layer.6.attention.self.query.weight": 589824, + "bert.encoder.layer.6.attention.self.query.bias": 768, + "bert.encoder.layer.6.attention.self.key.weight": 589824, + "bert.encoder.layer.6.attention.self.key.bias": 768, + "bert.encoder.layer.6.attention.self.value.weight": 589824, + "bert.encoder.layer.6.attention.self.value.bias": 768, + "bert.encoder.layer.6.attention.output.dense.weight": 589824, + "bert.encoder.layer.6.attention.output.dense.bias": 768, + "bert.encoder.layer.6.attention.output.LayerNorm.weight": 768, + "bert.encoder.layer.6.attention.output.LayerNorm.bias": 768, + "bert.encoder.layer.6.intermediate.dense.weight": 2359296, + "bert.encoder.layer.6.intermediate.dense.bias": 3072, + "bert.encoder.layer.6.output.dense.weight": 2359296, + "bert.encoder.layer.6.output.dense.bias": 768, + "bert.encoder.layer.6.output.LayerNorm.weight": 768, + "bert.encoder.layer.6.output.LayerNorm.bias": 768, + "bert.encoder.layer.7.attention.self.query.weight": 589824, + "bert.encoder.layer.7.attention.self.query.bias": 768, + "bert.encoder.layer.7.attention.self.key.weight": 589824, + "bert.encoder.layer.7.attention.self.key.bias": 768, + "bert.encoder.layer.7.attention.self.value.weight": 589824, + "bert.encoder.layer.7.attention.self.value.bias": 768, + "bert.encoder.layer.7.attention.output.dense.weight": 589824, + "bert.encoder.layer.7.attention.output.dense.bias": 768, + "bert.encoder.layer.7.attention.output.LayerNorm.weight": 768, + "bert.encoder.layer.7.attention.output.LayerNorm.bias": 768, + "bert.encoder.layer.7.intermediate.dense.weight": 2359296, + "bert.encoder.layer.7.intermediate.dense.bias": 3072, + "bert.encoder.layer.7.output.dense.weight": 2359296, + "bert.encoder.layer.7.output.dense.bias": 768, + "bert.encoder.layer.7.output.LayerNorm.weight": 768, + "bert.encoder.layer.7.output.LayerNorm.bias": 768, + "bert.encoder.layer.8.attention.self.query.weight": 589824, + "bert.encoder.layer.8.attention.self.query.bias": 768, + "bert.encoder.layer.8.attention.self.key.weight": 589824, + "bert.encoder.layer.8.attention.self.key.bias": 768, + "bert.encoder.layer.8.attention.self.value.weight": 589824, + "bert.encoder.layer.8.attention.self.value.bias": 768, + "bert.encoder.layer.8.attention.output.dense.weight": 589824, + "bert.encoder.layer.8.attention.output.dense.bias": 768, + "bert.encoder.layer.8.attention.output.LayerNorm.weight": 768, + "bert.encoder.layer.8.attention.output.LayerNorm.bias": 768, + "bert.encoder.layer.8.intermediate.dense.weight": 2359296, + "bert.encoder.layer.8.intermediate.dense.bias": 3072, + "bert.encoder.layer.8.output.dense.weight": 2359296, + "bert.encoder.layer.8.output.dense.bias": 768, + "bert.encoder.layer.8.output.LayerNorm.weight": 768, + "bert.encoder.layer.8.output.LayerNorm.bias": 768, + "bert.encoder.layer.9.attention.self.query.weight": 589824, + "bert.encoder.layer.9.attention.self.query.bias": 768, + "bert.encoder.layer.9.attention.self.key.weight": 589824, + "bert.encoder.layer.9.attention.self.key.bias": 768, + "bert.encoder.layer.9.attention.self.value.weight": 589824, + "bert.encoder.layer.9.attention.self.value.bias": 768, + "bert.encoder.layer.9.attention.output.dense.weight": 589824, + "bert.encoder.layer.9.attention.output.dense.bias": 768, + "bert.encoder.layer.9.attention.output.LayerNorm.weight": 768, + "bert.encoder.layer.9.attention.output.LayerNorm.bias": 768, + "bert.encoder.layer.9.intermediate.dense.weight": 2359296, + "bert.encoder.layer.9.intermediate.dense.bias": 3072, + "bert.encoder.layer.9.output.dense.weight": 2359296, + "bert.encoder.layer.9.output.dense.bias": 768, + "bert.encoder.layer.9.output.LayerNorm.weight": 768, + "bert.encoder.layer.9.output.LayerNorm.bias": 768, + "bert.encoder.layer.10.attention.self.query.weight": 589824, + "bert.encoder.layer.10.attention.self.query.bias": 768, + "bert.encoder.layer.10.attention.self.key.weight": 589824, + "bert.encoder.layer.10.attention.self.key.bias": 768, + "bert.encoder.layer.10.attention.self.value.weight": 589824, + "bert.encoder.layer.10.attention.self.value.bias": 768, + "bert.encoder.layer.10.attention.output.dense.weight": 589824, + "bert.encoder.layer.10.attention.output.dense.bias": 768, + "bert.encoder.layer.10.attention.output.LayerNorm.weight": 768, + "bert.encoder.layer.10.attention.output.LayerNorm.bias": 768, + "bert.encoder.layer.10.intermediate.dense.weight": 2359296, + "bert.encoder.layer.10.intermediate.dense.bias": 3072, + "bert.encoder.layer.10.output.dense.weight": 2359296, + "bert.encoder.layer.10.output.dense.bias": 768, + "bert.encoder.layer.10.output.LayerNorm.weight": 768, + "bert.encoder.layer.10.output.LayerNorm.bias": 768, + "bert.encoder.layer.11.attention.self.query.weight": 589824, + "bert.encoder.layer.11.attention.self.query.bias": 768, + "bert.encoder.layer.11.attention.self.key.weight": 589824, + "bert.encoder.layer.11.attention.self.key.bias": 768, + "bert.encoder.layer.11.attention.self.value.weight": 589824, + "bert.encoder.layer.11.attention.self.value.bias": 768, + "bert.encoder.layer.11.attention.output.dense.weight": 589824, + "bert.encoder.layer.11.attention.output.dense.bias": 768, + "bert.encoder.layer.11.attention.output.LayerNorm.weight": 768, + "bert.encoder.layer.11.attention.output.LayerNorm.bias": 768, + "bert.encoder.layer.11.intermediate.dense.weight": 2359296, + "bert.encoder.layer.11.intermediate.dense.bias": 3072, + "bert.encoder.layer.11.output.dense.weight": 2359296, + "bert.encoder.layer.11.output.dense.bias": 768, + "bert.encoder.layer.11.output.LayerNorm.weight": 768, + "bert.encoder.layer.11.output.LayerNorm.bias": 768, + "feat_map.weight": 196608, + "feat_map.bias": 256, + "input_proj.0.0.weight": 65536, + "input_proj.0.0.bias": 256, + "input_proj.0.1.weight": 256, + "input_proj.0.1.bias": 256, + "input_proj.1.0.weight": 131072, + "input_proj.1.0.bias": 256, + "input_proj.1.1.weight": 256, + "input_proj.1.1.bias": 256, + "input_proj.2.0.weight": 262144, + "input_proj.2.0.bias": 256, + "input_proj.2.1.weight": 256, + "input_proj.2.1.bias": 256, + "input_proj.3.0.weight": 2359296, + "input_proj.3.0.bias": 256, + "input_proj.3.1.weight": 256, + "input_proj.3.1.bias": 256, + "backbone.0.patch_embed.proj.weight": 6144, + "backbone.0.patch_embed.proj.bias": 128, + "backbone.0.patch_embed.norm.weight": 128, + "backbone.0.patch_embed.norm.bias": 128, + "backbone.0.layers.0.blocks.0.norm1.weight": 128, + "backbone.0.layers.0.blocks.0.norm1.bias": 128, + "backbone.0.layers.0.blocks.0.attn.relative_position_bias_table": 2116, + "backbone.0.layers.0.blocks.0.attn.qkv.weight": 49152, + "backbone.0.layers.0.blocks.0.attn.qkv.bias": 384, + "backbone.0.layers.0.blocks.0.attn.proj.weight": 16384, + "backbone.0.layers.0.blocks.0.attn.proj.bias": 128, + "backbone.0.layers.0.blocks.0.norm2.weight": 128, + "backbone.0.layers.0.blocks.0.norm2.bias": 128, + "backbone.0.layers.0.blocks.0.mlp.fc1.weight": 65536, + "backbone.0.layers.0.blocks.0.mlp.fc1.bias": 512, + "backbone.0.layers.0.blocks.0.mlp.fc2.weight": 65536, + "backbone.0.layers.0.blocks.0.mlp.fc2.bias": 128, + "backbone.0.layers.0.blocks.1.norm1.weight": 128, + "backbone.0.layers.0.blocks.1.norm1.bias": 128, + "backbone.0.layers.0.blocks.1.attn.relative_position_bias_table": 2116, + "backbone.0.layers.0.blocks.1.attn.qkv.weight": 49152, + "backbone.0.layers.0.blocks.1.attn.qkv.bias": 384, + "backbone.0.layers.0.blocks.1.attn.proj.weight": 16384, + "backbone.0.layers.0.blocks.1.attn.proj.bias": 128, + "backbone.0.layers.0.blocks.1.norm2.weight": 128, + "backbone.0.layers.0.blocks.1.norm2.bias": 128, + "backbone.0.layers.0.blocks.1.mlp.fc1.weight": 65536, + "backbone.0.layers.0.blocks.1.mlp.fc1.bias": 512, + "backbone.0.layers.0.blocks.1.mlp.fc2.weight": 65536, + "backbone.0.layers.0.blocks.1.mlp.fc2.bias": 128, + "backbone.0.layers.0.downsample.reduction.weight": 131072, + "backbone.0.layers.0.downsample.norm.weight": 512, + "backbone.0.layers.0.downsample.norm.bias": 512, + "backbone.0.layers.1.blocks.0.norm1.weight": 256, + "backbone.0.layers.1.blocks.0.norm1.bias": 256, + "backbone.0.layers.1.blocks.0.attn.relative_position_bias_table": 4232, + "backbone.0.layers.1.blocks.0.attn.qkv.weight": 196608, + "backbone.0.layers.1.blocks.0.attn.qkv.bias": 768, + "backbone.0.layers.1.blocks.0.attn.proj.weight": 65536, + "backbone.0.layers.1.blocks.0.attn.proj.bias": 256, + "backbone.0.layers.1.blocks.0.norm2.weight": 256, + "backbone.0.layers.1.blocks.0.norm2.bias": 256, + "backbone.0.layers.1.blocks.0.mlp.fc1.weight": 262144, + "backbone.0.layers.1.blocks.0.mlp.fc1.bias": 1024, + "backbone.0.layers.1.blocks.0.mlp.fc2.weight": 262144, + "backbone.0.layers.1.blocks.0.mlp.fc2.bias": 256, + "backbone.0.layers.1.blocks.1.norm1.weight": 256, + "backbone.0.layers.1.blocks.1.norm1.bias": 256, + "backbone.0.layers.1.blocks.1.attn.relative_position_bias_table": 4232, + "backbone.0.layers.1.blocks.1.attn.qkv.weight": 196608, + "backbone.0.layers.1.blocks.1.attn.qkv.bias": 768, + "backbone.0.layers.1.blocks.1.attn.proj.weight": 65536, + "backbone.0.layers.1.blocks.1.attn.proj.bias": 256, + "backbone.0.layers.1.blocks.1.norm2.weight": 256, + "backbone.0.layers.1.blocks.1.norm2.bias": 256, + "backbone.0.layers.1.blocks.1.mlp.fc1.weight": 262144, + "backbone.0.layers.1.blocks.1.mlp.fc1.bias": 1024, + "backbone.0.layers.1.blocks.1.mlp.fc2.weight": 262144, + "backbone.0.layers.1.blocks.1.mlp.fc2.bias": 256, + "backbone.0.layers.1.downsample.reduction.weight": 524288, + "backbone.0.layers.1.downsample.norm.weight": 1024, + "backbone.0.layers.1.downsample.norm.bias": 1024, + "backbone.0.layers.2.blocks.0.norm1.weight": 512, + "backbone.0.layers.2.blocks.0.norm1.bias": 512, + "backbone.0.layers.2.blocks.0.attn.relative_position_bias_table": 8464, + "backbone.0.layers.2.blocks.0.attn.qkv.weight": 786432, + "backbone.0.layers.2.blocks.0.attn.qkv.bias": 1536, + "backbone.0.layers.2.blocks.0.attn.proj.weight": 262144, + "backbone.0.layers.2.blocks.0.attn.proj.bias": 512, + "backbone.0.layers.2.blocks.0.norm2.weight": 512, + "backbone.0.layers.2.blocks.0.norm2.bias": 512, + "backbone.0.layers.2.blocks.0.mlp.fc1.weight": 1048576, + "backbone.0.layers.2.blocks.0.mlp.fc1.bias": 2048, + "backbone.0.layers.2.blocks.0.mlp.fc2.weight": 1048576, + "backbone.0.layers.2.blocks.0.mlp.fc2.bias": 512, + "backbone.0.layers.2.blocks.1.norm1.weight": 512, + "backbone.0.layers.2.blocks.1.norm1.bias": 512, + "backbone.0.layers.2.blocks.1.attn.relative_position_bias_table": 8464, + "backbone.0.layers.2.blocks.1.attn.qkv.weight": 786432, + "backbone.0.layers.2.blocks.1.attn.qkv.bias": 1536, + "backbone.0.layers.2.blocks.1.attn.proj.weight": 262144, + "backbone.0.layers.2.blocks.1.attn.proj.bias": 512, + "backbone.0.layers.2.blocks.1.norm2.weight": 512, + "backbone.0.layers.2.blocks.1.norm2.bias": 512, + "backbone.0.layers.2.blocks.1.mlp.fc1.weight": 1048576, + "backbone.0.layers.2.blocks.1.mlp.fc1.bias": 2048, + "backbone.0.layers.2.blocks.1.mlp.fc2.weight": 1048576, + "backbone.0.layers.2.blocks.1.mlp.fc2.bias": 512, + "backbone.0.layers.2.blocks.2.norm1.weight": 512, + "backbone.0.layers.2.blocks.2.norm1.bias": 512, + "backbone.0.layers.2.blocks.2.attn.relative_position_bias_table": 8464, + "backbone.0.layers.2.blocks.2.attn.qkv.weight": 786432, + "backbone.0.layers.2.blocks.2.attn.qkv.bias": 1536, + "backbone.0.layers.2.blocks.2.attn.proj.weight": 262144, + "backbone.0.layers.2.blocks.2.attn.proj.bias": 512, + "backbone.0.layers.2.blocks.2.norm2.weight": 512, + "backbone.0.layers.2.blocks.2.norm2.bias": 512, + "backbone.0.layers.2.blocks.2.mlp.fc1.weight": 1048576, + "backbone.0.layers.2.blocks.2.mlp.fc1.bias": 2048, + "backbone.0.layers.2.blocks.2.mlp.fc2.weight": 1048576, + "backbone.0.layers.2.blocks.2.mlp.fc2.bias": 512, + "backbone.0.layers.2.blocks.3.norm1.weight": 512, + "backbone.0.layers.2.blocks.3.norm1.bias": 512, + "backbone.0.layers.2.blocks.3.attn.relative_position_bias_table": 8464, + "backbone.0.layers.2.blocks.3.attn.qkv.weight": 786432, + "backbone.0.layers.2.blocks.3.attn.qkv.bias": 1536, + "backbone.0.layers.2.blocks.3.attn.proj.weight": 262144, + "backbone.0.layers.2.blocks.3.attn.proj.bias": 512, + "backbone.0.layers.2.blocks.3.norm2.weight": 512, + "backbone.0.layers.2.blocks.3.norm2.bias": 512, + "backbone.0.layers.2.blocks.3.mlp.fc1.weight": 1048576, + "backbone.0.layers.2.blocks.3.mlp.fc1.bias": 2048, + "backbone.0.layers.2.blocks.3.mlp.fc2.weight": 1048576, + "backbone.0.layers.2.blocks.3.mlp.fc2.bias": 512, + "backbone.0.layers.2.blocks.4.norm1.weight": 512, + "backbone.0.layers.2.blocks.4.norm1.bias": 512, + "backbone.0.layers.2.blocks.4.attn.relative_position_bias_table": 8464, + "backbone.0.layers.2.blocks.4.attn.qkv.weight": 786432, + "backbone.0.layers.2.blocks.4.attn.qkv.bias": 1536, + "backbone.0.layers.2.blocks.4.attn.proj.weight": 262144, + "backbone.0.layers.2.blocks.4.attn.proj.bias": 512, + "backbone.0.layers.2.blocks.4.norm2.weight": 512, + "backbone.0.layers.2.blocks.4.norm2.bias": 512, + "backbone.0.layers.2.blocks.4.mlp.fc1.weight": 1048576, + "backbone.0.layers.2.blocks.4.mlp.fc1.bias": 2048, + "backbone.0.layers.2.blocks.4.mlp.fc2.weight": 1048576, + "backbone.0.layers.2.blocks.4.mlp.fc2.bias": 512, + "backbone.0.layers.2.blocks.5.norm1.weight": 512, + "backbone.0.layers.2.blocks.5.norm1.bias": 512, + "backbone.0.layers.2.blocks.5.attn.relative_position_bias_table": 8464, + "backbone.0.layers.2.blocks.5.attn.qkv.weight": 786432, + "backbone.0.layers.2.blocks.5.attn.qkv.bias": 1536, + "backbone.0.layers.2.blocks.5.attn.proj.weight": 262144, + "backbone.0.layers.2.blocks.5.attn.proj.bias": 512, + "backbone.0.layers.2.blocks.5.norm2.weight": 512, + "backbone.0.layers.2.blocks.5.norm2.bias": 512, + "backbone.0.layers.2.blocks.5.mlp.fc1.weight": 1048576, + "backbone.0.layers.2.blocks.5.mlp.fc1.bias": 2048, + "backbone.0.layers.2.blocks.5.mlp.fc2.weight": 1048576, + "backbone.0.layers.2.blocks.5.mlp.fc2.bias": 512, + "backbone.0.layers.2.blocks.6.norm1.weight": 512, + "backbone.0.layers.2.blocks.6.norm1.bias": 512, + "backbone.0.layers.2.blocks.6.attn.relative_position_bias_table": 8464, + "backbone.0.layers.2.blocks.6.attn.qkv.weight": 786432, + "backbone.0.layers.2.blocks.6.attn.qkv.bias": 1536, + "backbone.0.layers.2.blocks.6.attn.proj.weight": 262144, + "backbone.0.layers.2.blocks.6.attn.proj.bias": 512, + "backbone.0.layers.2.blocks.6.norm2.weight": 512, + "backbone.0.layers.2.blocks.6.norm2.bias": 512, + "backbone.0.layers.2.blocks.6.mlp.fc1.weight": 1048576, + "backbone.0.layers.2.blocks.6.mlp.fc1.bias": 2048, + "backbone.0.layers.2.blocks.6.mlp.fc2.weight": 1048576, + "backbone.0.layers.2.blocks.6.mlp.fc2.bias": 512, + "backbone.0.layers.2.blocks.7.norm1.weight": 512, + "backbone.0.layers.2.blocks.7.norm1.bias": 512, + "backbone.0.layers.2.blocks.7.attn.relative_position_bias_table": 8464, + "backbone.0.layers.2.blocks.7.attn.qkv.weight": 786432, + "backbone.0.layers.2.blocks.7.attn.qkv.bias": 1536, + "backbone.0.layers.2.blocks.7.attn.proj.weight": 262144, + "backbone.0.layers.2.blocks.7.attn.proj.bias": 512, + "backbone.0.layers.2.blocks.7.norm2.weight": 512, + "backbone.0.layers.2.blocks.7.norm2.bias": 512, + "backbone.0.layers.2.blocks.7.mlp.fc1.weight": 1048576, + "backbone.0.layers.2.blocks.7.mlp.fc1.bias": 2048, + "backbone.0.layers.2.blocks.7.mlp.fc2.weight": 1048576, + "backbone.0.layers.2.blocks.7.mlp.fc2.bias": 512, + "backbone.0.layers.2.blocks.8.norm1.weight": 512, + "backbone.0.layers.2.blocks.8.norm1.bias": 512, + "backbone.0.layers.2.blocks.8.attn.relative_position_bias_table": 8464, + "backbone.0.layers.2.blocks.8.attn.qkv.weight": 786432, + "backbone.0.layers.2.blocks.8.attn.qkv.bias": 1536, + "backbone.0.layers.2.blocks.8.attn.proj.weight": 262144, + "backbone.0.layers.2.blocks.8.attn.proj.bias": 512, + "backbone.0.layers.2.blocks.8.norm2.weight": 512, + "backbone.0.layers.2.blocks.8.norm2.bias": 512, + "backbone.0.layers.2.blocks.8.mlp.fc1.weight": 1048576, + "backbone.0.layers.2.blocks.8.mlp.fc1.bias": 2048, + "backbone.0.layers.2.blocks.8.mlp.fc2.weight": 1048576, + "backbone.0.layers.2.blocks.8.mlp.fc2.bias": 512, + "backbone.0.layers.2.blocks.9.norm1.weight": 512, + "backbone.0.layers.2.blocks.9.norm1.bias": 512, + "backbone.0.layers.2.blocks.9.attn.relative_position_bias_table": 8464, + "backbone.0.layers.2.blocks.9.attn.qkv.weight": 786432, + "backbone.0.layers.2.blocks.9.attn.qkv.bias": 1536, + "backbone.0.layers.2.blocks.9.attn.proj.weight": 262144, + "backbone.0.layers.2.blocks.9.attn.proj.bias": 512, + "backbone.0.layers.2.blocks.9.norm2.weight": 512, + "backbone.0.layers.2.blocks.9.norm2.bias": 512, + "backbone.0.layers.2.blocks.9.mlp.fc1.weight": 1048576, + "backbone.0.layers.2.blocks.9.mlp.fc1.bias": 2048, + "backbone.0.layers.2.blocks.9.mlp.fc2.weight": 1048576, + "backbone.0.layers.2.blocks.9.mlp.fc2.bias": 512, + "backbone.0.layers.2.blocks.10.norm1.weight": 512, + "backbone.0.layers.2.blocks.10.norm1.bias": 512, + "backbone.0.layers.2.blocks.10.attn.relative_position_bias_table": 8464, + "backbone.0.layers.2.blocks.10.attn.qkv.weight": 786432, + "backbone.0.layers.2.blocks.10.attn.qkv.bias": 1536, + "backbone.0.layers.2.blocks.10.attn.proj.weight": 262144, + "backbone.0.layers.2.blocks.10.attn.proj.bias": 512, + "backbone.0.layers.2.blocks.10.norm2.weight": 512, + "backbone.0.layers.2.blocks.10.norm2.bias": 512, + "backbone.0.layers.2.blocks.10.mlp.fc1.weight": 1048576, + "backbone.0.layers.2.blocks.10.mlp.fc1.bias": 2048, + "backbone.0.layers.2.blocks.10.mlp.fc2.weight": 1048576, + "backbone.0.layers.2.blocks.10.mlp.fc2.bias": 512, + "backbone.0.layers.2.blocks.11.norm1.weight": 512, + "backbone.0.layers.2.blocks.11.norm1.bias": 512, + "backbone.0.layers.2.blocks.11.attn.relative_position_bias_table": 8464, + "backbone.0.layers.2.blocks.11.attn.qkv.weight": 786432, + "backbone.0.layers.2.blocks.11.attn.qkv.bias": 1536, + "backbone.0.layers.2.blocks.11.attn.proj.weight": 262144, + "backbone.0.layers.2.blocks.11.attn.proj.bias": 512, + "backbone.0.layers.2.blocks.11.norm2.weight": 512, + "backbone.0.layers.2.blocks.11.norm2.bias": 512, + "backbone.0.layers.2.blocks.11.mlp.fc1.weight": 1048576, + "backbone.0.layers.2.blocks.11.mlp.fc1.bias": 2048, + "backbone.0.layers.2.blocks.11.mlp.fc2.weight": 1048576, + "backbone.0.layers.2.blocks.11.mlp.fc2.bias": 512, + "backbone.0.layers.2.blocks.12.norm1.weight": 512, + "backbone.0.layers.2.blocks.12.norm1.bias": 512, + "backbone.0.layers.2.blocks.12.attn.relative_position_bias_table": 8464, + "backbone.0.layers.2.blocks.12.attn.qkv.weight": 786432, + "backbone.0.layers.2.blocks.12.attn.qkv.bias": 1536, + "backbone.0.layers.2.blocks.12.attn.proj.weight": 262144, + "backbone.0.layers.2.blocks.12.attn.proj.bias": 512, + "backbone.0.layers.2.blocks.12.norm2.weight": 512, + "backbone.0.layers.2.blocks.12.norm2.bias": 512, + "backbone.0.layers.2.blocks.12.mlp.fc1.weight": 1048576, + "backbone.0.layers.2.blocks.12.mlp.fc1.bias": 2048, + "backbone.0.layers.2.blocks.12.mlp.fc2.weight": 1048576, + "backbone.0.layers.2.blocks.12.mlp.fc2.bias": 512, + "backbone.0.layers.2.blocks.13.norm1.weight": 512, + "backbone.0.layers.2.blocks.13.norm1.bias": 512, + "backbone.0.layers.2.blocks.13.attn.relative_position_bias_table": 8464, + "backbone.0.layers.2.blocks.13.attn.qkv.weight": 786432, + "backbone.0.layers.2.blocks.13.attn.qkv.bias": 1536, + "backbone.0.layers.2.blocks.13.attn.proj.weight": 262144, + "backbone.0.layers.2.blocks.13.attn.proj.bias": 512, + "backbone.0.layers.2.blocks.13.norm2.weight": 512, + "backbone.0.layers.2.blocks.13.norm2.bias": 512, + "backbone.0.layers.2.blocks.13.mlp.fc1.weight": 1048576, + "backbone.0.layers.2.blocks.13.mlp.fc1.bias": 2048, + "backbone.0.layers.2.blocks.13.mlp.fc2.weight": 1048576, + "backbone.0.layers.2.blocks.13.mlp.fc2.bias": 512, + "backbone.0.layers.2.blocks.14.norm1.weight": 512, + "backbone.0.layers.2.blocks.14.norm1.bias": 512, + "backbone.0.layers.2.blocks.14.attn.relative_position_bias_table": 8464, + "backbone.0.layers.2.blocks.14.attn.qkv.weight": 786432, + "backbone.0.layers.2.blocks.14.attn.qkv.bias": 1536, + "backbone.0.layers.2.blocks.14.attn.proj.weight": 262144, + "backbone.0.layers.2.blocks.14.attn.proj.bias": 512, + "backbone.0.layers.2.blocks.14.norm2.weight": 512, + "backbone.0.layers.2.blocks.14.norm2.bias": 512, + "backbone.0.layers.2.blocks.14.mlp.fc1.weight": 1048576, + "backbone.0.layers.2.blocks.14.mlp.fc1.bias": 2048, + "backbone.0.layers.2.blocks.14.mlp.fc2.weight": 1048576, + "backbone.0.layers.2.blocks.14.mlp.fc2.bias": 512, + "backbone.0.layers.2.blocks.15.norm1.weight": 512, + "backbone.0.layers.2.blocks.15.norm1.bias": 512, + "backbone.0.layers.2.blocks.15.attn.relative_position_bias_table": 8464, + "backbone.0.layers.2.blocks.15.attn.qkv.weight": 786432, + "backbone.0.layers.2.blocks.15.attn.qkv.bias": 1536, + "backbone.0.layers.2.blocks.15.attn.proj.weight": 262144, + "backbone.0.layers.2.blocks.15.attn.proj.bias": 512, + "backbone.0.layers.2.blocks.15.norm2.weight": 512, + "backbone.0.layers.2.blocks.15.norm2.bias": 512, + "backbone.0.layers.2.blocks.15.mlp.fc1.weight": 1048576, + "backbone.0.layers.2.blocks.15.mlp.fc1.bias": 2048, + "backbone.0.layers.2.blocks.15.mlp.fc2.weight": 1048576, + "backbone.0.layers.2.blocks.15.mlp.fc2.bias": 512, + "backbone.0.layers.2.blocks.16.norm1.weight": 512, + "backbone.0.layers.2.blocks.16.norm1.bias": 512, + "backbone.0.layers.2.blocks.16.attn.relative_position_bias_table": 8464, + "backbone.0.layers.2.blocks.16.attn.qkv.weight": 786432, + "backbone.0.layers.2.blocks.16.attn.qkv.bias": 1536, + "backbone.0.layers.2.blocks.16.attn.proj.weight": 262144, + "backbone.0.layers.2.blocks.16.attn.proj.bias": 512, + "backbone.0.layers.2.blocks.16.norm2.weight": 512, + "backbone.0.layers.2.blocks.16.norm2.bias": 512, + "backbone.0.layers.2.blocks.16.mlp.fc1.weight": 1048576, + "backbone.0.layers.2.blocks.16.mlp.fc1.bias": 2048, + "backbone.0.layers.2.blocks.16.mlp.fc2.weight": 1048576, + "backbone.0.layers.2.blocks.16.mlp.fc2.bias": 512, + "backbone.0.layers.2.blocks.17.norm1.weight": 512, + "backbone.0.layers.2.blocks.17.norm1.bias": 512, + "backbone.0.layers.2.blocks.17.attn.relative_position_bias_table": 8464, + "backbone.0.layers.2.blocks.17.attn.qkv.weight": 786432, + "backbone.0.layers.2.blocks.17.attn.qkv.bias": 1536, + "backbone.0.layers.2.blocks.17.attn.proj.weight": 262144, + "backbone.0.layers.2.blocks.17.attn.proj.bias": 512, + "backbone.0.layers.2.blocks.17.norm2.weight": 512, + "backbone.0.layers.2.blocks.17.norm2.bias": 512, + "backbone.0.layers.2.blocks.17.mlp.fc1.weight": 1048576, + "backbone.0.layers.2.blocks.17.mlp.fc1.bias": 2048, + "backbone.0.layers.2.blocks.17.mlp.fc2.weight": 1048576, + "backbone.0.layers.2.blocks.17.mlp.fc2.bias": 512, + "backbone.0.layers.2.downsample.reduction.weight": 2097152, + "backbone.0.layers.2.downsample.norm.weight": 2048, + "backbone.0.layers.2.downsample.norm.bias": 2048, + "backbone.0.layers.3.blocks.0.norm1.weight": 1024, + "backbone.0.layers.3.blocks.0.norm1.bias": 1024, + "backbone.0.layers.3.blocks.0.attn.relative_position_bias_table": 16928, + "backbone.0.layers.3.blocks.0.attn.qkv.weight": 3145728, + "backbone.0.layers.3.blocks.0.attn.qkv.bias": 3072, + "backbone.0.layers.3.blocks.0.attn.proj.weight": 1048576, + "backbone.0.layers.3.blocks.0.attn.proj.bias": 1024, + "backbone.0.layers.3.blocks.0.norm2.weight": 1024, + "backbone.0.layers.3.blocks.0.norm2.bias": 1024, + "backbone.0.layers.3.blocks.0.mlp.fc1.weight": 4194304, + "backbone.0.layers.3.blocks.0.mlp.fc1.bias": 4096, + "backbone.0.layers.3.blocks.0.mlp.fc2.weight": 4194304, + "backbone.0.layers.3.blocks.0.mlp.fc2.bias": 1024, + "backbone.0.layers.3.blocks.1.norm1.weight": 1024, + "backbone.0.layers.3.blocks.1.norm1.bias": 1024, + "backbone.0.layers.3.blocks.1.attn.relative_position_bias_table": 16928, + "backbone.0.layers.3.blocks.1.attn.qkv.weight": 3145728, + "backbone.0.layers.3.blocks.1.attn.qkv.bias": 3072, + "backbone.0.layers.3.blocks.1.attn.proj.weight": 1048576, + "backbone.0.layers.3.blocks.1.attn.proj.bias": 1024, + "backbone.0.layers.3.blocks.1.norm2.weight": 1024, + "backbone.0.layers.3.blocks.1.norm2.bias": 1024, + "backbone.0.layers.3.blocks.1.mlp.fc1.weight": 4194304, + "backbone.0.layers.3.blocks.1.mlp.fc1.bias": 4096, + "backbone.0.layers.3.blocks.1.mlp.fc2.weight": 4194304, + "backbone.0.layers.3.blocks.1.mlp.fc2.bias": 1024, + "backbone.0.norm1.weight": 256, + "backbone.0.norm1.bias": 256, + "backbone.0.norm2.weight": 512, + "backbone.0.norm2.bias": 512, + "backbone.0.norm3.weight": 1024, + "backbone.0.norm3.bias": 1024 +} +INFO  2024-03-29 17:46:28,634 | params after freezing: +{ + "transformer.level_embed": 1024, + "transformer.encoder.layers.0.self_attn.sampling_offsets.weight": 65536, + "transformer.encoder.layers.0.self_attn.sampling_offsets.bias": 256, + "transformer.encoder.layers.0.self_attn.attention_weights.weight": 32768, + "transformer.encoder.layers.0.self_attn.attention_weights.bias": 128, + "transformer.encoder.layers.0.self_attn.value_proj.weight": 65536, + "transformer.encoder.layers.0.self_attn.value_proj.bias": 256, + "transformer.encoder.layers.0.self_attn.output_proj.weight": 65536, + "transformer.encoder.layers.0.self_attn.output_proj.bias": 256, + "transformer.encoder.layers.0.norm1.weight": 256, + "transformer.encoder.layers.0.norm1.bias": 256, + "transformer.encoder.layers.0.linear1.weight": 524288, + "transformer.encoder.layers.0.linear1.bias": 2048, + "transformer.encoder.layers.0.linear2.weight": 524288, + "transformer.encoder.layers.0.linear2.bias": 256, + "transformer.encoder.layers.0.norm2.weight": 256, + "transformer.encoder.layers.0.norm2.bias": 256, + "transformer.encoder.layers.1.self_attn.sampling_offsets.weight": 65536, + "transformer.encoder.layers.1.self_attn.sampling_offsets.bias": 256, + "transformer.encoder.layers.1.self_attn.attention_weights.weight": 32768, + "transformer.encoder.layers.1.self_attn.attention_weights.bias": 128, + "transformer.encoder.layers.1.self_attn.value_proj.weight": 65536, + "transformer.encoder.layers.1.self_attn.value_proj.bias": 256, + "transformer.encoder.layers.1.self_attn.output_proj.weight": 65536, + "transformer.encoder.layers.1.self_attn.output_proj.bias": 256, + "transformer.encoder.layers.1.norm1.weight": 256, + "transformer.encoder.layers.1.norm1.bias": 256, + "transformer.encoder.layers.1.linear1.weight": 524288, + "transformer.encoder.layers.1.linear1.bias": 2048, + "transformer.encoder.layers.1.linear2.weight": 524288, + "transformer.encoder.layers.1.linear2.bias": 256, + "transformer.encoder.layers.1.norm2.weight": 256, + "transformer.encoder.layers.1.norm2.bias": 256, + "transformer.encoder.layers.2.self_attn.sampling_offsets.weight": 65536, + "transformer.encoder.layers.2.self_attn.sampling_offsets.bias": 256, + "transformer.encoder.layers.2.self_attn.attention_weights.weight": 32768, + "transformer.encoder.layers.2.self_attn.attention_weights.bias": 128, + "transformer.encoder.layers.2.self_attn.value_proj.weight": 65536, + "transformer.encoder.layers.2.self_attn.value_proj.bias": 256, + "transformer.encoder.layers.2.self_attn.output_proj.weight": 65536, + "transformer.encoder.layers.2.self_attn.output_proj.bias": 256, + "transformer.encoder.layers.2.norm1.weight": 256, + "transformer.encoder.layers.2.norm1.bias": 256, + "transformer.encoder.layers.2.linear1.weight": 524288, + "transformer.encoder.layers.2.linear1.bias": 2048, + "transformer.encoder.layers.2.linear2.weight": 524288, + "transformer.encoder.layers.2.linear2.bias": 256, + "transformer.encoder.layers.2.norm2.weight": 256, + "transformer.encoder.layers.2.norm2.bias": 256, + "transformer.encoder.layers.3.self_attn.sampling_offsets.weight": 65536, + "transformer.encoder.layers.3.self_attn.sampling_offsets.bias": 256, + "transformer.encoder.layers.3.self_attn.attention_weights.weight": 32768, + "transformer.encoder.layers.3.self_attn.attention_weights.bias": 128, + "transformer.encoder.layers.3.self_attn.value_proj.weight": 65536, + "transformer.encoder.layers.3.self_attn.value_proj.bias": 256, + "transformer.encoder.layers.3.self_attn.output_proj.weight": 65536, + "transformer.encoder.layers.3.self_attn.output_proj.bias": 256, + "transformer.encoder.layers.3.norm1.weight": 256, + "transformer.encoder.layers.3.norm1.bias": 256, + "transformer.encoder.layers.3.linear1.weight": 524288, + "transformer.encoder.layers.3.linear1.bias": 2048, + "transformer.encoder.layers.3.linear2.weight": 524288, + "transformer.encoder.layers.3.linear2.bias": 256, + "transformer.encoder.layers.3.norm2.weight": 256, + "transformer.encoder.layers.3.norm2.bias": 256, + "transformer.encoder.layers.4.self_attn.sampling_offsets.weight": 65536, + "transformer.encoder.layers.4.self_attn.sampling_offsets.bias": 256, + "transformer.encoder.layers.4.self_attn.attention_weights.weight": 32768, + "transformer.encoder.layers.4.self_attn.attention_weights.bias": 128, + "transformer.encoder.layers.4.self_attn.value_proj.weight": 65536, + "transformer.encoder.layers.4.self_attn.value_proj.bias": 256, + "transformer.encoder.layers.4.self_attn.output_proj.weight": 65536, + "transformer.encoder.layers.4.self_attn.output_proj.bias": 256, + "transformer.encoder.layers.4.norm1.weight": 256, + "transformer.encoder.layers.4.norm1.bias": 256, + "transformer.encoder.layers.4.linear1.weight": 524288, + "transformer.encoder.layers.4.linear1.bias": 2048, + "transformer.encoder.layers.4.linear2.weight": 524288, + "transformer.encoder.layers.4.linear2.bias": 256, + "transformer.encoder.layers.4.norm2.weight": 256, + "transformer.encoder.layers.4.norm2.bias": 256, + "transformer.encoder.layers.5.self_attn.sampling_offsets.weight": 65536, + "transformer.encoder.layers.5.self_attn.sampling_offsets.bias": 256, + "transformer.encoder.layers.5.self_attn.attention_weights.weight": 32768, + "transformer.encoder.layers.5.self_attn.attention_weights.bias": 128, + "transformer.encoder.layers.5.self_attn.value_proj.weight": 65536, + "transformer.encoder.layers.5.self_attn.value_proj.bias": 256, + "transformer.encoder.layers.5.self_attn.output_proj.weight": 65536, + "transformer.encoder.layers.5.self_attn.output_proj.bias": 256, + "transformer.encoder.layers.5.norm1.weight": 256, + "transformer.encoder.layers.5.norm1.bias": 256, + "transformer.encoder.layers.5.linear1.weight": 524288, + "transformer.encoder.layers.5.linear1.bias": 2048, + "transformer.encoder.layers.5.linear2.weight": 524288, + "transformer.encoder.layers.5.linear2.bias": 256, + "transformer.encoder.layers.5.norm2.weight": 256, + "transformer.encoder.layers.5.norm2.bias": 256, + "transformer.encoder.text_layers.0.self_attn.in_proj_weight": 196608, + "transformer.encoder.text_layers.0.self_attn.in_proj_bias": 768, + "transformer.encoder.text_layers.0.self_attn.out_proj.weight": 65536, + "transformer.encoder.text_layers.0.self_attn.out_proj.bias": 256, + "transformer.encoder.text_layers.0.linear1.weight": 262144, + "transformer.encoder.text_layers.0.linear1.bias": 1024, + "transformer.encoder.text_layers.0.linear2.weight": 262144, + "transformer.encoder.text_layers.0.linear2.bias": 256, + "transformer.encoder.text_layers.0.norm1.weight": 256, + "transformer.encoder.text_layers.0.norm1.bias": 256, + "transformer.encoder.text_layers.0.norm2.weight": 256, + "transformer.encoder.text_layers.0.norm2.bias": 256, + "transformer.encoder.text_layers.1.self_attn.in_proj_weight": 196608, + "transformer.encoder.text_layers.1.self_attn.in_proj_bias": 768, + "transformer.encoder.text_layers.1.self_attn.out_proj.weight": 65536, + "transformer.encoder.text_layers.1.self_attn.out_proj.bias": 256, + "transformer.encoder.text_layers.1.linear1.weight": 262144, + "transformer.encoder.text_layers.1.linear1.bias": 1024, + "transformer.encoder.text_layers.1.linear2.weight": 262144, + "transformer.encoder.text_layers.1.linear2.bias": 256, + "transformer.encoder.text_layers.1.norm1.weight": 256, + "transformer.encoder.text_layers.1.norm1.bias": 256, + "transformer.encoder.text_layers.1.norm2.weight": 256, + "transformer.encoder.text_layers.1.norm2.bias": 256, + "transformer.encoder.text_layers.2.self_attn.in_proj_weight": 196608, + "transformer.encoder.text_layers.2.self_attn.in_proj_bias": 768, + "transformer.encoder.text_layers.2.self_attn.out_proj.weight": 65536, + "transformer.encoder.text_layers.2.self_attn.out_proj.bias": 256, + "transformer.encoder.text_layers.2.linear1.weight": 262144, + "transformer.encoder.text_layers.2.linear1.bias": 1024, + "transformer.encoder.text_layers.2.linear2.weight": 262144, + "transformer.encoder.text_layers.2.linear2.bias": 256, + "transformer.encoder.text_layers.2.norm1.weight": 256, + "transformer.encoder.text_layers.2.norm1.bias": 256, + "transformer.encoder.text_layers.2.norm2.weight": 256, + "transformer.encoder.text_layers.2.norm2.bias": 256, + "transformer.encoder.text_layers.3.self_attn.in_proj_weight": 196608, + "transformer.encoder.text_layers.3.self_attn.in_proj_bias": 768, + "transformer.encoder.text_layers.3.self_attn.out_proj.weight": 65536, + "transformer.encoder.text_layers.3.self_attn.out_proj.bias": 256, + "transformer.encoder.text_layers.3.linear1.weight": 262144, + "transformer.encoder.text_layers.3.linear1.bias": 1024, + "transformer.encoder.text_layers.3.linear2.weight": 262144, + "transformer.encoder.text_layers.3.linear2.bias": 256, + "transformer.encoder.text_layers.3.norm1.weight": 256, + "transformer.encoder.text_layers.3.norm1.bias": 256, + "transformer.encoder.text_layers.3.norm2.weight": 256, + "transformer.encoder.text_layers.3.norm2.bias": 256, + "transformer.encoder.text_layers.4.self_attn.in_proj_weight": 196608, + "transformer.encoder.text_layers.4.self_attn.in_proj_bias": 768, + "transformer.encoder.text_layers.4.self_attn.out_proj.weight": 65536, + "transformer.encoder.text_layers.4.self_attn.out_proj.bias": 256, + "transformer.encoder.text_layers.4.linear1.weight": 262144, + "transformer.encoder.text_layers.4.linear1.bias": 1024, + "transformer.encoder.text_layers.4.linear2.weight": 262144, + "transformer.encoder.text_layers.4.linear2.bias": 256, + "transformer.encoder.text_layers.4.norm1.weight": 256, + "transformer.encoder.text_layers.4.norm1.bias": 256, + "transformer.encoder.text_layers.4.norm2.weight": 256, + "transformer.encoder.text_layers.4.norm2.bias": 256, + "transformer.encoder.text_layers.5.self_attn.in_proj_weight": 196608, + "transformer.encoder.text_layers.5.self_attn.in_proj_bias": 768, + "transformer.encoder.text_layers.5.self_attn.out_proj.weight": 65536, + "transformer.encoder.text_layers.5.self_attn.out_proj.bias": 256, + "transformer.encoder.text_layers.5.linear1.weight": 262144, + "transformer.encoder.text_layers.5.linear1.bias": 1024, + "transformer.encoder.text_layers.5.linear2.weight": 262144, + "transformer.encoder.text_layers.5.linear2.bias": 256, + "transformer.encoder.text_layers.5.norm1.weight": 256, + "transformer.encoder.text_layers.5.norm1.bias": 256, + "transformer.encoder.text_layers.5.norm2.weight": 256, + "transformer.encoder.text_layers.5.norm2.bias": 256, + "transformer.encoder.fusion_layers.0.gamma_v": 256, + "transformer.encoder.fusion_layers.0.gamma_l": 256, + "transformer.encoder.fusion_layers.0.layer_norm_v.weight": 256, + "transformer.encoder.fusion_layers.0.layer_norm_v.bias": 256, + "transformer.encoder.fusion_layers.0.layer_norm_l.weight": 256, + "transformer.encoder.fusion_layers.0.layer_norm_l.bias": 256, + "transformer.encoder.fusion_layers.0.attn.v_proj.weight": 262144, + "transformer.encoder.fusion_layers.0.attn.v_proj.bias": 1024, + "transformer.encoder.fusion_layers.0.attn.l_proj.weight": 262144, + "transformer.encoder.fusion_layers.0.attn.l_proj.bias": 1024, + "transformer.encoder.fusion_layers.0.attn.values_v_proj.weight": 262144, + "transformer.encoder.fusion_layers.0.attn.values_v_proj.bias": 1024, + "transformer.encoder.fusion_layers.0.attn.values_l_proj.weight": 262144, + "transformer.encoder.fusion_layers.0.attn.values_l_proj.bias": 1024, + "transformer.encoder.fusion_layers.0.attn.out_v_proj.weight": 262144, + "transformer.encoder.fusion_layers.0.attn.out_v_proj.bias": 256, + "transformer.encoder.fusion_layers.0.attn.out_l_proj.weight": 262144, + "transformer.encoder.fusion_layers.0.attn.out_l_proj.bias": 256, + "transformer.encoder.fusion_layers.1.gamma_v": 256, + "transformer.encoder.fusion_layers.1.gamma_l": 256, + "transformer.encoder.fusion_layers.1.layer_norm_v.weight": 256, + "transformer.encoder.fusion_layers.1.layer_norm_v.bias": 256, + "transformer.encoder.fusion_layers.1.layer_norm_l.weight": 256, + "transformer.encoder.fusion_layers.1.layer_norm_l.bias": 256, + "transformer.encoder.fusion_layers.1.attn.v_proj.weight": 262144, + "transformer.encoder.fusion_layers.1.attn.v_proj.bias": 1024, + "transformer.encoder.fusion_layers.1.attn.l_proj.weight": 262144, + "transformer.encoder.fusion_layers.1.attn.l_proj.bias": 1024, + "transformer.encoder.fusion_layers.1.attn.values_v_proj.weight": 262144, + "transformer.encoder.fusion_layers.1.attn.values_v_proj.bias": 1024, + "transformer.encoder.fusion_layers.1.attn.values_l_proj.weight": 262144, + "transformer.encoder.fusion_layers.1.attn.values_l_proj.bias": 1024, + "transformer.encoder.fusion_layers.1.attn.out_v_proj.weight": 262144, + "transformer.encoder.fusion_layers.1.attn.out_v_proj.bias": 256, + "transformer.encoder.fusion_layers.1.attn.out_l_proj.weight": 262144, + "transformer.encoder.fusion_layers.1.attn.out_l_proj.bias": 256, + "transformer.encoder.fusion_layers.2.gamma_v": 256, + "transformer.encoder.fusion_layers.2.gamma_l": 256, + "transformer.encoder.fusion_layers.2.layer_norm_v.weight": 256, + "transformer.encoder.fusion_layers.2.layer_norm_v.bias": 256, + "transformer.encoder.fusion_layers.2.layer_norm_l.weight": 256, + "transformer.encoder.fusion_layers.2.layer_norm_l.bias": 256, + "transformer.encoder.fusion_layers.2.attn.v_proj.weight": 262144, + "transformer.encoder.fusion_layers.2.attn.v_proj.bias": 1024, + "transformer.encoder.fusion_layers.2.attn.l_proj.weight": 262144, + "transformer.encoder.fusion_layers.2.attn.l_proj.bias": 1024, + "transformer.encoder.fusion_layers.2.attn.values_v_proj.weight": 262144, + "transformer.encoder.fusion_layers.2.attn.values_v_proj.bias": 1024, + "transformer.encoder.fusion_layers.2.attn.values_l_proj.weight": 262144, + "transformer.encoder.fusion_layers.2.attn.values_l_proj.bias": 1024, + "transformer.encoder.fusion_layers.2.attn.out_v_proj.weight": 262144, + "transformer.encoder.fusion_layers.2.attn.out_v_proj.bias": 256, + "transformer.encoder.fusion_layers.2.attn.out_l_proj.weight": 262144, + "transformer.encoder.fusion_layers.2.attn.out_l_proj.bias": 256, + "transformer.encoder.fusion_layers.3.gamma_v": 256, + "transformer.encoder.fusion_layers.3.gamma_l": 256, + "transformer.encoder.fusion_layers.3.layer_norm_v.weight": 256, + "transformer.encoder.fusion_layers.3.layer_norm_v.bias": 256, + "transformer.encoder.fusion_layers.3.layer_norm_l.weight": 256, + "transformer.encoder.fusion_layers.3.layer_norm_l.bias": 256, + "transformer.encoder.fusion_layers.3.attn.v_proj.weight": 262144, + "transformer.encoder.fusion_layers.3.attn.v_proj.bias": 1024, + "transformer.encoder.fusion_layers.3.attn.l_proj.weight": 262144, + "transformer.encoder.fusion_layers.3.attn.l_proj.bias": 1024, + "transformer.encoder.fusion_layers.3.attn.values_v_proj.weight": 262144, + "transformer.encoder.fusion_layers.3.attn.values_v_proj.bias": 1024, + "transformer.encoder.fusion_layers.3.attn.values_l_proj.weight": 262144, + "transformer.encoder.fusion_layers.3.attn.values_l_proj.bias": 1024, + "transformer.encoder.fusion_layers.3.attn.out_v_proj.weight": 262144, + "transformer.encoder.fusion_layers.3.attn.out_v_proj.bias": 256, + "transformer.encoder.fusion_layers.3.attn.out_l_proj.weight": 262144, + "transformer.encoder.fusion_layers.3.attn.out_l_proj.bias": 256, + "transformer.encoder.fusion_layers.4.gamma_v": 256, + "transformer.encoder.fusion_layers.4.gamma_l": 256, + "transformer.encoder.fusion_layers.4.layer_norm_v.weight": 256, + "transformer.encoder.fusion_layers.4.layer_norm_v.bias": 256, + "transformer.encoder.fusion_layers.4.layer_norm_l.weight": 256, + "transformer.encoder.fusion_layers.4.layer_norm_l.bias": 256, + "transformer.encoder.fusion_layers.4.attn.v_proj.weight": 262144, + "transformer.encoder.fusion_layers.4.attn.v_proj.bias": 1024, + "transformer.encoder.fusion_layers.4.attn.l_proj.weight": 262144, + "transformer.encoder.fusion_layers.4.attn.l_proj.bias": 1024, + "transformer.encoder.fusion_layers.4.attn.values_v_proj.weight": 262144, + "transformer.encoder.fusion_layers.4.attn.values_v_proj.bias": 1024, + "transformer.encoder.fusion_layers.4.attn.values_l_proj.weight": 262144, + "transformer.encoder.fusion_layers.4.attn.values_l_proj.bias": 1024, + "transformer.encoder.fusion_layers.4.attn.out_v_proj.weight": 262144, + "transformer.encoder.fusion_layers.4.attn.out_v_proj.bias": 256, + "transformer.encoder.fusion_layers.4.attn.out_l_proj.weight": 262144, + "transformer.encoder.fusion_layers.4.attn.out_l_proj.bias": 256, + "transformer.encoder.fusion_layers.5.gamma_v": 256, + "transformer.encoder.fusion_layers.5.gamma_l": 256, + "transformer.encoder.fusion_layers.5.layer_norm_v.weight": 256, + "transformer.encoder.fusion_layers.5.layer_norm_v.bias": 256, + "transformer.encoder.fusion_layers.5.layer_norm_l.weight": 256, + "transformer.encoder.fusion_layers.5.layer_norm_l.bias": 256, + "transformer.encoder.fusion_layers.5.attn.v_proj.weight": 262144, + "transformer.encoder.fusion_layers.5.attn.v_proj.bias": 1024, + "transformer.encoder.fusion_layers.5.attn.l_proj.weight": 262144, + "transformer.encoder.fusion_layers.5.attn.l_proj.bias": 1024, + "transformer.encoder.fusion_layers.5.attn.values_v_proj.weight": 262144, + "transformer.encoder.fusion_layers.5.attn.values_v_proj.bias": 1024, + "transformer.encoder.fusion_layers.5.attn.values_l_proj.weight": 262144, + "transformer.encoder.fusion_layers.5.attn.values_l_proj.bias": 1024, + "transformer.encoder.fusion_layers.5.attn.out_v_proj.weight": 262144, + "transformer.encoder.fusion_layers.5.attn.out_v_proj.bias": 256, + "transformer.encoder.fusion_layers.5.attn.out_l_proj.weight": 262144, + "transformer.encoder.fusion_layers.5.attn.out_l_proj.bias": 256, + "transformer.decoder.layers.0.cross_attn.sampling_offsets.weight": 65536, + "transformer.decoder.layers.0.cross_attn.sampling_offsets.bias": 256, + "transformer.decoder.layers.0.cross_attn.attention_weights.weight": 32768, + "transformer.decoder.layers.0.cross_attn.attention_weights.bias": 128, + "transformer.decoder.layers.0.cross_attn.value_proj.weight": 65536, + "transformer.decoder.layers.0.cross_attn.value_proj.bias": 256, + "transformer.decoder.layers.0.cross_attn.output_proj.weight": 65536, + "transformer.decoder.layers.0.cross_attn.output_proj.bias": 256, + "transformer.decoder.layers.0.norm1.weight": 256, + "transformer.decoder.layers.0.norm1.bias": 256, + "transformer.decoder.layers.0.ca_text.in_proj_weight": 196608, + "transformer.decoder.layers.0.ca_text.in_proj_bias": 768, + "transformer.decoder.layers.0.ca_text.out_proj.weight": 65536, + "transformer.decoder.layers.0.ca_text.out_proj.bias": 256, + "transformer.decoder.layers.0.catext_norm.weight": 256, + "transformer.decoder.layers.0.catext_norm.bias": 256, + "transformer.decoder.layers.0.self_attn.in_proj_weight": 196608, + "transformer.decoder.layers.0.self_attn.in_proj_bias": 768, + "transformer.decoder.layers.0.self_attn.out_proj.weight": 65536, + "transformer.decoder.layers.0.self_attn.out_proj.bias": 256, + "transformer.decoder.layers.0.norm2.weight": 256, + "transformer.decoder.layers.0.norm2.bias": 256, + "transformer.decoder.layers.0.linear1.weight": 524288, + "transformer.decoder.layers.0.linear1.bias": 2048, + "transformer.decoder.layers.0.linear2.weight": 524288, + "transformer.decoder.layers.0.linear2.bias": 256, + "transformer.decoder.layers.0.norm3.weight": 256, + "transformer.decoder.layers.0.norm3.bias": 256, + "transformer.decoder.layers.1.cross_attn.sampling_offsets.weight": 65536, + "transformer.decoder.layers.1.cross_attn.sampling_offsets.bias": 256, + "transformer.decoder.layers.1.cross_attn.attention_weights.weight": 32768, + "transformer.decoder.layers.1.cross_attn.attention_weights.bias": 128, + "transformer.decoder.layers.1.cross_attn.value_proj.weight": 65536, + "transformer.decoder.layers.1.cross_attn.value_proj.bias": 256, + "transformer.decoder.layers.1.cross_attn.output_proj.weight": 65536, + "transformer.decoder.layers.1.cross_attn.output_proj.bias": 256, + "transformer.decoder.layers.1.norm1.weight": 256, + "transformer.decoder.layers.1.norm1.bias": 256, + "transformer.decoder.layers.1.ca_text.in_proj_weight": 196608, + "transformer.decoder.layers.1.ca_text.in_proj_bias": 768, + "transformer.decoder.layers.1.ca_text.out_proj.weight": 65536, + "transformer.decoder.layers.1.ca_text.out_proj.bias": 256, + "transformer.decoder.layers.1.catext_norm.weight": 256, + "transformer.decoder.layers.1.catext_norm.bias": 256, + "transformer.decoder.layers.1.self_attn.in_proj_weight": 196608, + "transformer.decoder.layers.1.self_attn.in_proj_bias": 768, + "transformer.decoder.layers.1.self_attn.out_proj.weight": 65536, + "transformer.decoder.layers.1.self_attn.out_proj.bias": 256, + "transformer.decoder.layers.1.norm2.weight": 256, + "transformer.decoder.layers.1.norm2.bias": 256, + "transformer.decoder.layers.1.linear1.weight": 524288, + "transformer.decoder.layers.1.linear1.bias": 2048, + "transformer.decoder.layers.1.linear2.weight": 524288, + "transformer.decoder.layers.1.linear2.bias": 256, + "transformer.decoder.layers.1.norm3.weight": 256, + "transformer.decoder.layers.1.norm3.bias": 256, + "transformer.decoder.layers.2.cross_attn.sampling_offsets.weight": 65536, + "transformer.decoder.layers.2.cross_attn.sampling_offsets.bias": 256, + "transformer.decoder.layers.2.cross_attn.attention_weights.weight": 32768, + "transformer.decoder.layers.2.cross_attn.attention_weights.bias": 128, + "transformer.decoder.layers.2.cross_attn.value_proj.weight": 65536, + "transformer.decoder.layers.2.cross_attn.value_proj.bias": 256, + "transformer.decoder.layers.2.cross_attn.output_proj.weight": 65536, + "transformer.decoder.layers.2.cross_attn.output_proj.bias": 256, + "transformer.decoder.layers.2.norm1.weight": 256, + "transformer.decoder.layers.2.norm1.bias": 256, + "transformer.decoder.layers.2.ca_text.in_proj_weight": 196608, + "transformer.decoder.layers.2.ca_text.in_proj_bias": 768, + "transformer.decoder.layers.2.ca_text.out_proj.weight": 65536, + "transformer.decoder.layers.2.ca_text.out_proj.bias": 256, + "transformer.decoder.layers.2.catext_norm.weight": 256, + "transformer.decoder.layers.2.catext_norm.bias": 256, + "transformer.decoder.layers.2.self_attn.in_proj_weight": 196608, + "transformer.decoder.layers.2.self_attn.in_proj_bias": 768, + "transformer.decoder.layers.2.self_attn.out_proj.weight": 65536, + "transformer.decoder.layers.2.self_attn.out_proj.bias": 256, + "transformer.decoder.layers.2.norm2.weight": 256, + "transformer.decoder.layers.2.norm2.bias": 256, + "transformer.decoder.layers.2.linear1.weight": 524288, + "transformer.decoder.layers.2.linear1.bias": 2048, + "transformer.decoder.layers.2.linear2.weight": 524288, + "transformer.decoder.layers.2.linear2.bias": 256, + "transformer.decoder.layers.2.norm3.weight": 256, + "transformer.decoder.layers.2.norm3.bias": 256, + "transformer.decoder.layers.3.cross_attn.sampling_offsets.weight": 65536, + "transformer.decoder.layers.3.cross_attn.sampling_offsets.bias": 256, + "transformer.decoder.layers.3.cross_attn.attention_weights.weight": 32768, + "transformer.decoder.layers.3.cross_attn.attention_weights.bias": 128, + "transformer.decoder.layers.3.cross_attn.value_proj.weight": 65536, + "transformer.decoder.layers.3.cross_attn.value_proj.bias": 256, + "transformer.decoder.layers.3.cross_attn.output_proj.weight": 65536, + "transformer.decoder.layers.3.cross_attn.output_proj.bias": 256, + "transformer.decoder.layers.3.norm1.weight": 256, + "transformer.decoder.layers.3.norm1.bias": 256, + "transformer.decoder.layers.3.ca_text.in_proj_weight": 196608, + "transformer.decoder.layers.3.ca_text.in_proj_bias": 768, + "transformer.decoder.layers.3.ca_text.out_proj.weight": 65536, + "transformer.decoder.layers.3.ca_text.out_proj.bias": 256, + "transformer.decoder.layers.3.catext_norm.weight": 256, + "transformer.decoder.layers.3.catext_norm.bias": 256, + "transformer.decoder.layers.3.self_attn.in_proj_weight": 196608, + "transformer.decoder.layers.3.self_attn.in_proj_bias": 768, + "transformer.decoder.layers.3.self_attn.out_proj.weight": 65536, + "transformer.decoder.layers.3.self_attn.out_proj.bias": 256, + "transformer.decoder.layers.3.norm2.weight": 256, + "transformer.decoder.layers.3.norm2.bias": 256, + "transformer.decoder.layers.3.linear1.weight": 524288, + "transformer.decoder.layers.3.linear1.bias": 2048, + "transformer.decoder.layers.3.linear2.weight": 524288, + "transformer.decoder.layers.3.linear2.bias": 256, + "transformer.decoder.layers.3.norm3.weight": 256, + "transformer.decoder.layers.3.norm3.bias": 256, + "transformer.decoder.layers.4.cross_attn.sampling_offsets.weight": 65536, + "transformer.decoder.layers.4.cross_attn.sampling_offsets.bias": 256, + "transformer.decoder.layers.4.cross_attn.attention_weights.weight": 32768, + "transformer.decoder.layers.4.cross_attn.attention_weights.bias": 128, + "transformer.decoder.layers.4.cross_attn.value_proj.weight": 65536, + "transformer.decoder.layers.4.cross_attn.value_proj.bias": 256, + "transformer.decoder.layers.4.cross_attn.output_proj.weight": 65536, + "transformer.decoder.layers.4.cross_attn.output_proj.bias": 256, + "transformer.decoder.layers.4.norm1.weight": 256, + "transformer.decoder.layers.4.norm1.bias": 256, + "transformer.decoder.layers.4.ca_text.in_proj_weight": 196608, + "transformer.decoder.layers.4.ca_text.in_proj_bias": 768, + "transformer.decoder.layers.4.ca_text.out_proj.weight": 65536, + "transformer.decoder.layers.4.ca_text.out_proj.bias": 256, + "transformer.decoder.layers.4.catext_norm.weight": 256, + "transformer.decoder.layers.4.catext_norm.bias": 256, + "transformer.decoder.layers.4.self_attn.in_proj_weight": 196608, + "transformer.decoder.layers.4.self_attn.in_proj_bias": 768, + "transformer.decoder.layers.4.self_attn.out_proj.weight": 65536, + "transformer.decoder.layers.4.self_attn.out_proj.bias": 256, + "transformer.decoder.layers.4.norm2.weight": 256, + "transformer.decoder.layers.4.norm2.bias": 256, + "transformer.decoder.layers.4.linear1.weight": 524288, + "transformer.decoder.layers.4.linear1.bias": 2048, + "transformer.decoder.layers.4.linear2.weight": 524288, + "transformer.decoder.layers.4.linear2.bias": 256, + "transformer.decoder.layers.4.norm3.weight": 256, + "transformer.decoder.layers.4.norm3.bias": 256, + "transformer.decoder.layers.5.cross_attn.sampling_offsets.weight": 65536, + "transformer.decoder.layers.5.cross_attn.sampling_offsets.bias": 256, + "transformer.decoder.layers.5.cross_attn.attention_weights.weight": 32768, + "transformer.decoder.layers.5.cross_attn.attention_weights.bias": 128, + "transformer.decoder.layers.5.cross_attn.value_proj.weight": 65536, + "transformer.decoder.layers.5.cross_attn.value_proj.bias": 256, + "transformer.decoder.layers.5.cross_attn.output_proj.weight": 65536, + "transformer.decoder.layers.5.cross_attn.output_proj.bias": 256, + "transformer.decoder.layers.5.norm1.weight": 256, + "transformer.decoder.layers.5.norm1.bias": 256, + "transformer.decoder.layers.5.ca_text.in_proj_weight": 196608, + "transformer.decoder.layers.5.ca_text.in_proj_bias": 768, + "transformer.decoder.layers.5.ca_text.out_proj.weight": 65536, + "transformer.decoder.layers.5.ca_text.out_proj.bias": 256, + "transformer.decoder.layers.5.catext_norm.weight": 256, + "transformer.decoder.layers.5.catext_norm.bias": 256, + "transformer.decoder.layers.5.self_attn.in_proj_weight": 196608, + "transformer.decoder.layers.5.self_attn.in_proj_bias": 768, + "transformer.decoder.layers.5.self_attn.out_proj.weight": 65536, + "transformer.decoder.layers.5.self_attn.out_proj.bias": 256, + "transformer.decoder.layers.5.norm2.weight": 256, + "transformer.decoder.layers.5.norm2.bias": 256, + "transformer.decoder.layers.5.linear1.weight": 524288, + "transformer.decoder.layers.5.linear1.bias": 2048, + "transformer.decoder.layers.5.linear2.weight": 524288, + "transformer.decoder.layers.5.linear2.bias": 256, + "transformer.decoder.layers.5.norm3.weight": 256, + "transformer.decoder.layers.5.norm3.bias": 256, + "transformer.decoder.norm.weight": 256, + "transformer.decoder.norm.bias": 256, + "transformer.decoder.ref_point_head.layers.0.weight": 131072, + "transformer.decoder.ref_point_head.layers.0.bias": 256, + "transformer.decoder.ref_point_head.layers.1.weight": 65536, + "transformer.decoder.ref_point_head.layers.1.bias": 256, + "transformer.decoder.bbox_embed.0.layers.0.weight": 65536, + "transformer.decoder.bbox_embed.0.layers.0.bias": 256, + "transformer.decoder.bbox_embed.0.layers.1.weight": 65536, + "transformer.decoder.bbox_embed.0.layers.1.bias": 256, + "transformer.decoder.bbox_embed.0.layers.2.weight": 1024, + "transformer.decoder.bbox_embed.0.layers.2.bias": 4, + "transformer.tgt_embed.weight": 230400, + "transformer.enc_output.weight": 65536, + "transformer.enc_output.bias": 256, + "transformer.enc_output_norm.weight": 256, + "transformer.enc_output_norm.bias": 256, + "transformer.enc_out_bbox_embed.layers.0.weight": 65536, + "transformer.enc_out_bbox_embed.layers.0.bias": 256, + "transformer.enc_out_bbox_embed.layers.1.weight": 65536, + "transformer.enc_out_bbox_embed.layers.1.bias": 256, + "transformer.enc_out_bbox_embed.layers.2.weight": 1024, + "transformer.enc_out_bbox_embed.layers.2.bias": 4, + "feature_map_proj.weight": 458752, + "feature_map_proj.bias": 256, + "feature_map_encoder.layers.0.norm1.weight": 256, + "feature_map_encoder.layers.0.norm1.bias": 256, + "feature_map_encoder.layers.0.norm2.weight": 256, + "feature_map_encoder.layers.0.norm2.bias": 256, + "feature_map_encoder.layers.0.self_attn.in_proj_weight": 196608, + "feature_map_encoder.layers.0.self_attn.in_proj_bias": 768, + "feature_map_encoder.layers.0.self_attn.out_proj.weight": 65536, + "feature_map_encoder.layers.0.self_attn.out_proj.bias": 256, + "feature_map_encoder.layers.0.mlp.linear1.weight": 524288, + "feature_map_encoder.layers.0.mlp.linear1.bias": 2048, + "feature_map_encoder.layers.0.mlp.linear2.weight": 524288, + "feature_map_encoder.layers.0.mlp.linear2.bias": 256, + "feature_map_encoder.layers.1.norm1.weight": 256, + "feature_map_encoder.layers.1.norm1.bias": 256, + "feature_map_encoder.layers.1.norm2.weight": 256, + "feature_map_encoder.layers.1.norm2.bias": 256, + "feature_map_encoder.layers.1.self_attn.in_proj_weight": 196608, + "feature_map_encoder.layers.1.self_attn.in_proj_bias": 768, + "feature_map_encoder.layers.1.self_attn.out_proj.weight": 65536, + "feature_map_encoder.layers.1.self_attn.out_proj.bias": 256, + "feature_map_encoder.layers.1.mlp.linear1.weight": 524288, + "feature_map_encoder.layers.1.mlp.linear1.bias": 2048, + "feature_map_encoder.layers.1.mlp.linear2.weight": 524288, + "feature_map_encoder.layers.1.mlp.linear2.bias": 256, + "feature_map_encoder.layers.2.norm1.weight": 256, + "feature_map_encoder.layers.2.norm1.bias": 256, + "feature_map_encoder.layers.2.norm2.weight": 256, + "feature_map_encoder.layers.2.norm2.bias": 256, + "feature_map_encoder.layers.2.self_attn.in_proj_weight": 196608, + "feature_map_encoder.layers.2.self_attn.in_proj_bias": 768, + "feature_map_encoder.layers.2.self_attn.out_proj.weight": 65536, + "feature_map_encoder.layers.2.self_attn.out_proj.bias": 256, + "feature_map_encoder.layers.2.mlp.linear1.weight": 524288, + "feature_map_encoder.layers.2.mlp.linear1.bias": 2048, + "feature_map_encoder.layers.2.mlp.linear2.weight": 524288, + "feature_map_encoder.layers.2.mlp.linear2.bias": 256, + "feature_map_encoder.norm.weight": 256, + "feature_map_encoder.norm.bias": 256, + "feat_map.weight": 196608, + "feat_map.bias": 256, + "input_proj.0.0.weight": 65536, + "input_proj.0.0.bias": 256, + "input_proj.0.1.weight": 256, + "input_proj.0.1.bias": 256, + "input_proj.1.0.weight": 131072, + "input_proj.1.0.bias": 256, + "input_proj.1.1.weight": 256, + "input_proj.1.1.bias": 256, + "input_proj.2.0.weight": 262144, + "input_proj.2.0.bias": 256, + "input_proj.2.1.weight": 256, + "input_proj.2.1.bias": 256, + "input_proj.3.0.weight": 2359296, + "input_proj.3.0.bias": 256, + "input_proj.3.1.weight": 256, + "input_proj.3.1.bias": 256 +} +DEBUG  2024-03-29 17:46:28,636 | build dataset ... ... +DEBUG  2024-03-29 17:46:29,266 | build dataset, done. +DEBUG  2024-03-29 17:46:29,267 | number of training dataset: 1, samples: 3659 +INFO  2024-03-29 17:46:29,889 | Ignore keys: [] +INFO  2024-03-29 17:46:30,040 | _IncompatibleKeys(missing_keys=['feature_map_proj.weight', 'feature_map_proj.bias', 'feature_map_encoder.layers.0.norm1.weight', 'feature_map_encoder.layers.0.norm1.bias', 'feature_map_encoder.layers.0.norm2.weight', 'feature_map_encoder.layers.0.norm2.bias', 'feature_map_encoder.layers.0.self_attn.in_proj_weight', 'feature_map_encoder.layers.0.self_attn.in_proj_bias', 'feature_map_encoder.layers.0.self_attn.out_proj.weight', 'feature_map_encoder.layers.0.self_attn.out_proj.bias', 'feature_map_encoder.layers.0.mlp.linear1.weight', 'feature_map_encoder.layers.0.mlp.linear1.bias', 'feature_map_encoder.layers.0.mlp.linear2.weight', 'feature_map_encoder.layers.0.mlp.linear2.bias', 'feature_map_encoder.layers.1.norm1.weight', 'feature_map_encoder.layers.1.norm1.bias', 'feature_map_encoder.layers.1.norm2.weight', 'feature_map_encoder.layers.1.norm2.bias', 'feature_map_encoder.layers.1.self_attn.in_proj_weight', 'feature_map_encoder.layers.1.self_attn.in_proj_bias', 'feature_map_encoder.layers.1.self_attn.out_proj.weight', 'feature_map_encoder.layers.1.self_attn.out_proj.bias', 'feature_map_encoder.layers.1.mlp.linear1.weight', 'feature_map_encoder.layers.1.mlp.linear1.bias', 'feature_map_encoder.layers.1.mlp.linear2.weight', 'feature_map_encoder.layers.1.mlp.linear2.bias', 'feature_map_encoder.layers.2.norm1.weight', 'feature_map_encoder.layers.2.norm1.bias', 'feature_map_encoder.layers.2.norm2.weight', 'feature_map_encoder.layers.2.norm2.bias', 'feature_map_encoder.layers.2.self_attn.in_proj_weight', 'feature_map_encoder.layers.2.self_attn.in_proj_bias', 'feature_map_encoder.layers.2.self_attn.out_proj.weight', 'feature_map_encoder.layers.2.self_attn.out_proj.bias', 'feature_map_encoder.layers.2.mlp.linear1.weight', 'feature_map_encoder.layers.2.mlp.linear1.bias', 'feature_map_encoder.layers.2.mlp.linear2.weight', 'feature_map_encoder.layers.2.mlp.linear2.bias', 'feature_map_encoder.norm.weight', 'feature_map_encoder.norm.bias'], unexpected_keys=['label_enc.weight', 'bert.embeddings.position_ids'])