From 7f3fd8f3186931fb03d5c8700180c1e82fd3da09 Mon Sep 17 00:00:00 2001
From: Manuel Schmid <dev@mash1t.de>
Date: Sun, 16 Jun 2024 23:22:10 +0200
Subject: [PATCH] feat: update GroundingDINO from SwinT (tiny) to SwinB (base)

---
 .../config/GroundingDINO_SwinB_cfg.py         | 43 +++++++++++++++++++
 extras/GroundingDINO/util/inference.py        |  6 +--
 2 files changed, 46 insertions(+), 3 deletions(-)
 create mode 100644 extras/GroundingDINO/config/GroundingDINO_SwinB_cfg.py

diff --git a/extras/GroundingDINO/config/GroundingDINO_SwinB_cfg.py b/extras/GroundingDINO/config/GroundingDINO_SwinB_cfg.py
new file mode 100644
index 00000000..bc2788a8
--- /dev/null
+++ b/extras/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
\ No newline at end of file
diff --git a/extras/GroundingDINO/util/inference.py b/extras/GroundingDINO/util/inference.py
index bc8b6429..11e1a77c 100644
--- a/extras/GroundingDINO/util/inference.py
+++ b/extras/GroundingDINO/util/inference.py
@@ -14,7 +14,7 @@ from groundingdino.util.inference import load_model, preprocess_caption, get_phr
 
 class GroundingDinoModel(Model):
     def __init__(self):
-        self.config_file = 'extras/GroundingDINO/config/GroundingDINO_SwinT_OGC.py'
+        self.config_file = 'extras/GroundingDINO/config/GroundingDINO_SwinB_cfg.py'
         self.model = None
         self.load_device = torch.device('cpu')
         self.offload_device = torch.device('cpu')
@@ -28,8 +28,8 @@ class GroundingDinoModel(Model):
     ) -> Tuple[sv.Detections, torch.Tensor, torch.Tensor, List[str]]:
         if self.model is None:
             filename = load_file_from_url(
-                url="https://github.com/IDEA-Research/GroundingDINO/releases/download/v0.1.0-alpha/groundingdino_swint_ogc.pth",
-                file_name='groundingdino_swint_ogc.pth',
+                url="https://github.com/IDEA-Research/GroundingDINO/releases/download/v0.1.0-alpha2/groundingdino_swinb_cogcoor.pth",
+                file_name='groundingdino_swinb_cogcoor.pth',
                 model_dir=path_inpaint)
             model = load_model(model_config_path=self.config_file, model_checkpoint_path=filename)