Commit ·
9156bad
verified ·
0
Parent(s):
Duplicate from ShilongLiu/GroundingDINO
Browse filesCo-authored-by: Shilong Liu <ShilongLiu@users.noreply.huggingface.co>
- .gitattributes +35 -0
- GD_GLIGEN.png +0 -0
- GroundingDINO_SwinB.cfg.py +43 -0
- GroundingDINO_SwinT_OGC.cfg.py +43 -0
- README.md +32 -0
- art_dog_birthdaycake.png +0 -0
- cats.png +0 -0
- demo_audio.mp3 +0 -0
- gdsd_example.png +3 -0
- groundingdino_swinb_cogcoor.pth +3 -0
- groundingdino_swint_ogc.pth +3 -0
- pandas.png +0 -0
- sketch_person.png +0 -0
.gitattributes
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
*.7z filter=lfs diff=lfs merge=lfs -text
|
| 2 |
+
*.arrow filter=lfs diff=lfs merge=lfs -text
|
| 3 |
+
*.bin filter=lfs diff=lfs merge=lfs -text
|
| 4 |
+
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
| 5 |
+
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
| 6 |
+
*.ftz filter=lfs diff=lfs merge=lfs -text
|
| 7 |
+
*.gz filter=lfs diff=lfs merge=lfs -text
|
| 8 |
+
*.h5 filter=lfs diff=lfs merge=lfs -text
|
| 9 |
+
*.joblib filter=lfs diff=lfs merge=lfs -text
|
| 10 |
+
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
| 11 |
+
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
| 12 |
+
*.model filter=lfs diff=lfs merge=lfs -text
|
| 13 |
+
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
| 14 |
+
*.npy filter=lfs diff=lfs merge=lfs -text
|
| 15 |
+
*.npz filter=lfs diff=lfs merge=lfs -text
|
| 16 |
+
*.onnx filter=lfs diff=lfs merge=lfs -text
|
| 17 |
+
*.ot filter=lfs diff=lfs merge=lfs -text
|
| 18 |
+
*.parquet filter=lfs diff=lfs merge=lfs -text
|
| 19 |
+
*.pb filter=lfs diff=lfs merge=lfs -text
|
| 20 |
+
*.pickle filter=lfs diff=lfs merge=lfs -text
|
| 21 |
+
*.pkl filter=lfs diff=lfs merge=lfs -text
|
| 22 |
+
*.pt filter=lfs diff=lfs merge=lfs -text
|
| 23 |
+
*.pth filter=lfs diff=lfs merge=lfs -text
|
| 24 |
+
*.rar filter=lfs diff=lfs merge=lfs -text
|
| 25 |
+
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
| 26 |
+
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
| 27 |
+
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
| 28 |
+
*.tflite filter=lfs diff=lfs merge=lfs -text
|
| 29 |
+
*.tgz filter=lfs diff=lfs merge=lfs -text
|
| 30 |
+
*.wasm filter=lfs diff=lfs merge=lfs -text
|
| 31 |
+
*.xz filter=lfs diff=lfs merge=lfs -text
|
| 32 |
+
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 33 |
+
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 34 |
+
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 35 |
+
gdsd_example.png filter=lfs diff=lfs merge=lfs -text
|
GD_GLIGEN.png
ADDED
|
GroundingDINO_SwinB.cfg.py
ADDED
|
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
batch_size = 1
|
| 2 |
+
modelname = "groundingdino"
|
| 3 |
+
backbone = "swin_B_384_22k"
|
| 4 |
+
position_embedding = "sine"
|
| 5 |
+
pe_temperatureH = 20
|
| 6 |
+
pe_temperatureW = 20
|
| 7 |
+
return_interm_indices = [1, 2, 3]
|
| 8 |
+
backbone_freeze_keywords = None
|
| 9 |
+
enc_layers = 6
|
| 10 |
+
dec_layers = 6
|
| 11 |
+
pre_norm = False
|
| 12 |
+
dim_feedforward = 2048
|
| 13 |
+
hidden_dim = 256
|
| 14 |
+
dropout = 0.0
|
| 15 |
+
nheads = 8
|
| 16 |
+
num_queries = 900
|
| 17 |
+
query_dim = 4
|
| 18 |
+
num_patterns = 0
|
| 19 |
+
num_feature_levels = 4
|
| 20 |
+
enc_n_points = 4
|
| 21 |
+
dec_n_points = 4
|
| 22 |
+
two_stage_type = "standard"
|
| 23 |
+
two_stage_bbox_embed_share = False
|
| 24 |
+
two_stage_class_embed_share = False
|
| 25 |
+
transformer_activation = "relu"
|
| 26 |
+
dec_pred_bbox_embed_share = True
|
| 27 |
+
dn_box_noise_scale = 1.0
|
| 28 |
+
dn_label_noise_ratio = 0.5
|
| 29 |
+
dn_label_coef = 1.0
|
| 30 |
+
dn_bbox_coef = 1.0
|
| 31 |
+
embed_init_tgt = True
|
| 32 |
+
dn_labelbook_size = 2000
|
| 33 |
+
max_text_len = 256
|
| 34 |
+
text_encoder_type = "bert-base-uncased"
|
| 35 |
+
use_text_enhancer = True
|
| 36 |
+
use_fusion_layer = True
|
| 37 |
+
use_checkpoint = True
|
| 38 |
+
use_transformer_ckpt = True
|
| 39 |
+
use_text_cross_attention = True
|
| 40 |
+
text_dropout = 0.0
|
| 41 |
+
fusion_dropout = 0.0
|
| 42 |
+
fusion_droppath = 0.1
|
| 43 |
+
sub_sentence_present = True
|
GroundingDINO_SwinT_OGC.cfg.py
ADDED
|
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
batch_size = 1
|
| 2 |
+
modelname = "groundingdino"
|
| 3 |
+
backbone = "swin_T_224_1k"
|
| 4 |
+
position_embedding = "sine"
|
| 5 |
+
pe_temperatureH = 20
|
| 6 |
+
pe_temperatureW = 20
|
| 7 |
+
return_interm_indices = [1, 2, 3]
|
| 8 |
+
backbone_freeze_keywords = None
|
| 9 |
+
enc_layers = 6
|
| 10 |
+
dec_layers = 6
|
| 11 |
+
pre_norm = False
|
| 12 |
+
dim_feedforward = 2048
|
| 13 |
+
hidden_dim = 256
|
| 14 |
+
dropout = 0.0
|
| 15 |
+
nheads = 8
|
| 16 |
+
num_queries = 900
|
| 17 |
+
query_dim = 4
|
| 18 |
+
num_patterns = 0
|
| 19 |
+
num_feature_levels = 4
|
| 20 |
+
enc_n_points = 4
|
| 21 |
+
dec_n_points = 4
|
| 22 |
+
two_stage_type = "standard"
|
| 23 |
+
two_stage_bbox_embed_share = False
|
| 24 |
+
two_stage_class_embed_share = False
|
| 25 |
+
transformer_activation = "relu"
|
| 26 |
+
dec_pred_bbox_embed_share = True
|
| 27 |
+
dn_box_noise_scale = 1.0
|
| 28 |
+
dn_label_noise_ratio = 0.5
|
| 29 |
+
dn_label_coef = 1.0
|
| 30 |
+
dn_bbox_coef = 1.0
|
| 31 |
+
embed_init_tgt = True
|
| 32 |
+
dn_labelbook_size = 2000
|
| 33 |
+
max_text_len = 256
|
| 34 |
+
text_encoder_type = "bert-base-uncased"
|
| 35 |
+
use_text_enhancer = True
|
| 36 |
+
use_fusion_layer = True
|
| 37 |
+
use_checkpoint = True
|
| 38 |
+
use_transformer_ckpt = True
|
| 39 |
+
use_text_cross_attention = True
|
| 40 |
+
text_dropout = 0.0
|
| 41 |
+
fusion_dropout = 0.0
|
| 42 |
+
fusion_droppath = 0.1
|
| 43 |
+
sub_sentence_present = True
|
README.md
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
datasets:
|
| 4 |
+
- detection-datasets/coco
|
| 5 |
+
- conceptual_captions
|
| 6 |
+
language:
|
| 7 |
+
- en
|
| 8 |
+
tags:
|
| 9 |
+
- detection
|
| 10 |
+
- open-world
|
| 11 |
+
- open-set
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
|
| 15 |
+
# Grounding DINO
|
| 16 |
+
|
| 17 |
+
[📃Paper](https://arxiv.org/abs/2303.05499) |
|
| 18 |
+
[📽️Video](https://www.youtube.com/watch?v=wxWDt5UiwY8) |
|
| 19 |
+
[📯Demo on Colab](https://colab.research.google.com/github/roboflow-ai/notebooks/blob/main/notebooks/zero-shot-object-detection-with-grounding-dino.ipynb) |
|
| 20 |
+
[🤗Demo on HF (Coming soon)]()
|
| 21 |
+
|
| 22 |
+
## Citation
|
| 23 |
+
|
| 24 |
+
If you find our work helpful for your research, please consider citing the following BibTeX entry.
|
| 25 |
+
|
| 26 |
+
```bibtex
|
| 27 |
+
@inproceedings{ShilongLiu2023GroundingDM,
|
| 28 |
+
title={Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection},
|
| 29 |
+
author={Shilong Liu and Zhaoyang Zeng and Tianhe Ren and Feng Li and Hao Zhang and Jie Yang and Chunyuan Li and Jianwei Yang and Hang Su and Jun Zhu and Lei Zhang},
|
| 30 |
+
year={2023}
|
| 31 |
+
}
|
| 32 |
+
```
|
art_dog_birthdaycake.png
ADDED
|
cats.png
ADDED
|
demo_audio.mp3
ADDED
|
Binary file (20.3 kB). View file
|
|
|
gdsd_example.png
ADDED
|
Git LFS Details
|
groundingdino_swinb_cogcoor.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:46270f7a822e6906b655b729c90613e48929d0f2bb8b9b76fd10a856f3ac6ab7
|
| 3 |
+
size 938057991
|
groundingdino_swint_ogc.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3b3ca2563c77c69f651d7bd133e97139c186df06231157a64c507099c52bc799
|
| 3 |
+
size 693997677
|
pandas.png
ADDED
|
sketch_person.png
ADDED
|