add grounding dino new config & fix scripts bugs (#112)

GroundingDINO/demo/inference_on_a_image.py

@@ -143,7 +143,7 @@ def get_grounding_output(model, image, caption, box_threshold, text_threshold, w
  text_prompt = args.text_prompt
  output_dir = args.output_dir
  box_threshold = args.box_threshold
- text_threshold = args.box_threshold
+ text_threshold = args.text_threshold
 
  # make dir
  os.makedirs(output_dir, exist_ok=True)

GroundingDINO/groundingdino/config/GroundingDINO_SwinB.cfg.py

@@ -0,0 +1,43 @@
+batch_size = 1
+modelname = "groundingdino"
+backbone = "swin_B_384_22k"
+position_embedding = "sine"
+pe_temperatureH = 20
+pe_temperatureW = 20
+return_interm_indices = [1, 2, 3]
+backbone_freeze_keywords = None
+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 = 2000
+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

automatic_label_demo.py

@@ -224,7 +224,7 @@ def save_mask_data(output_dir, caption, mask_list, box_list, label_list):
  openai_proxy = args.openai_proxy
  output_dir = args.output_dir
  box_threshold = args.box_threshold
- text_threshold = args.box_threshold
+ text_threshold = args.text_threshold
  iou_threshold = args.iou_threshold
  device = args.device
 

grounded_sam_demo.py

@@ -158,7 +158,7 @@ def save_mask_data(output_dir, mask_list, box_list, label_list):
  text_prompt = args.text_prompt
  output_dir = args.output_dir
  box_threshold = args.box_threshold
- text_threshold = args.box_threshold
+ text_threshold = args.text_threshold
  device = args.device
 
  # make dir

grounded_sam_inpainting_demo.py

@@ -138,7 +138,7 @@ def show_box(box, ax, label):
  inpaint_prompt = args.inpaint_prompt
  output_dir = args.output_dir
  box_threshold = args.box_threshold
- text_threshold = args.box_threshold
+ text_threshold = args.text_threshold
  inpaint_mode = args.inpaint_mode
  device = args.device
 

grounded_sam_whisper_inpainting_demo.py

@@ -190,7 +190,7 @@ def filter_prompts_with_chatgpt(caption, max_tokens=100, model="gpt-3.5-turbo"):
 
  output_dir = args.output_dir
  box_threshold = args.box_threshold
- text_threshold = args.box_threshold
+ text_threshold = args.text_threshold
  inpaint_mode = args.inpaint_mode
  device = args.device