Initial commit

checkpoint_best_regular.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd2c43f732a56467e00d9e1e7f87b83e8d3b60b681a8763200d22caa1b83080e
+size 2070726177

config_args_all.json

@@ -0,0 +1,207 @@
+{
+  "config_file": "config/cfg_odvg_libero.py",
+  "options": {
+    "text_encoder_type": "./bert-base-uncased"
+  },
+  "datasets": "config/libero_vg.json",
+  "remove_difficult": false,
+  "fix_size": false,
+  "output_dir": "./logs",
+  "note": "",
+  "device": "cuda",
+  "seed": 42,
+  "resume": "",
+  "pretrain_model_path": "./groundingdino_swint_ogc.pth",
+  "finetune_ignore": null,
+  "start_epoch": 0,
+  "eval": false,
+  "num_workers": 6,
+  "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,
+  "gpu": 0,
+  "distributed": true,
+  "dist_backend": "nccl",
+  "data_aug_scales": [
+    192,
+    208,
+    224,
+    240
+  ],
+  "data_aug_max_size": 240,
+  "data_aug_scales2_resize": [
+    256
+  ],
+  "data_aug_scales2_crop": [
+    224,
+    224
+  ],
+  "data_aug_scale_overlap": null,
+  "batch_size": 55,
+  "modelname": "groundingdino",
+  "backbone": "swin_T_224_1k",
+  "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": "./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": 30,
+  "lr": 0.001,
+  "backbone_freeze_keywords": null,
+  "freeze_keywords": [],
+  "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": 50,
+  "lr_drop": 10,
+  "save_checkpoint_interval": 10,
+  "clip_max_norm": 0.1,
+  "onecyclelr": false,
+  "multi_step_lr": false,
+  "lr_drop_list": [
+    10,
+    20,
+    30,
+    40
+  ],
+  "frozen_weights": null,
+  "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": null,
+  "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": 40,
+  "batch_norm_type": "FrozenBatchNorm2d",
+  "masks": false,
+  "aux_loss": true,
+  "set_cost_class": 1.0,
+  "set_cost_bbox": 5.0,
+  "set_cost_giou": 2.0,
+  "cls_loss_coef": 2.5,
+  "bbox_loss_coef": 5.0,
+  "giou_loss_coef": 2.0,
+  "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": 2.5,
+  "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_ema": true,
+  "ema_decay": 0.9997,
+  "ema_epoch": 0,
+  "use_detached_boxes_dec_out": false,
+  "use_coco_eval": false,
+  "dn_scalar": 100,
+  "label_list": [
+    "alphabet soup",
+    "basket",
+    "bbq sauce",
+    "black bowl",
+    "book",
+    "butter",
+    "cabinet",
+    "caddy",
+    "chocolate pudding",
+    "cream cheese",
+    "gripper",
+    "ketchup",
+    "left moka pot",
+    "left plate",
+    "microwave",
+    "milk",
+    "moka pot",
+    "orange juice",
+    "plate",
+    "right moka pot",
+    "right plate",
+    "salad dressing",
+    "stove",
+    "tomato sauce",
+    "white mug",
+    "wine bottle",
+    "wine rack",
+    "yellow and white mug"
+  ]
+}

config_args_raw.json

@@ -0,0 +1,32 @@
+{
+  "config_file": "config/cfg_odvg_libero.py",
+  "options": {
+    "text_encoder_type": "./bert-base-uncased"
+  },
+  "datasets": "config/libero_vg.json",
+  "remove_difficult": false,
+  "fix_size": false,
+  "output_dir": "./logs",
+  "note": "",
+  "device": "cuda",
+  "seed": 42,
+  "resume": "",
+  "pretrain_model_path": "./groundingdino_swint_ogc.pth",
+  "finetune_ignore": null,
+  "start_epoch": 0,
+  "eval": false,
+  "num_workers": 6,
+  "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,
+  "gpu": 0,
+  "distributed": true,
+  "dist_backend": "nccl"
+}

config_cfg.py

@@ -0,0 +1,124 @@
+data_aug_scales = [192, 208, 224, 240]
+data_aug_max_size = 240
+data_aug_scales2_resize = [256]
+data_aug_scales2_crop = [224, 224]
+data_aug_scale_overlap = None
+batch_size = 55
+modelname = 'groundingdino'
+backbone = 'swin_T_224_1k'
+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 = './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 = 30
+lr = 0.001
+backbone_freeze_keywords = None
+freeze_keywords = []
+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 = 50
+lr_drop = 10
+save_checkpoint_interval = 10
+clip_max_norm = 0.1
+onecyclelr = False
+multi_step_lr = False
+lr_drop_list = [10, 20, 30, 40]
+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 = 40
+batch_norm_type = 'FrozenBatchNorm2d'
+masks = False
+aux_loss = True
+set_cost_class = 1.0
+set_cost_bbox = 5.0
+set_cost_giou = 2.0
+cls_loss_coef = 2.5
+bbox_loss_coef = 5.0
+giou_loss_coef = 2.0
+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 = 2.5
+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_ema = True
+ema_decay = 0.9997
+ema_epoch = 0
+use_detached_boxes_dec_out = False
+use_coco_eval = False
+dn_scalar = 100
+label_list = [
+    'alphabet soup', 'basket', 'bbq sauce', 'black bowl', 'book', 'butter',
+    'cabinet', 'caddy', 'chocolate pudding', 'cream cheese', 'gripper',
+    'ketchup', 'left moka pot', 'left plate', 'microwave', 'milk', 'moka pot',
+    'orange juice', 'plate', 'right moka pot', 'right plate', 'salad dressing',
+    'stove', 'tomato sauce', 'white mug', 'wine bottle', 'wine rack',
+    'yellow and white mug'
+]

eval/000.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3f62bc22f5cf10bedd33108439618b479bc3e85d7fe9887237ef982c4b391e2
+size 5934741

eval/latest.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f114726fc6442b4e6c2f09e700dabf1288d9fb41babc6fe2d58f62783be85ebb
+size 6064615