nikigoli imgprcsng commited on
Commit
a07c2b0
·
verified ·
1 Parent(s): ff6263f

add-model (#1)

Browse files

- update model (b39ef9809dcaa1b118d9418088d941f88c346fd4)
- update model (4053384cfc6dde424dbdc31a4d7991fe31ccdf67)
- update model (0828c8041827d0ba9384b95ee2c203dde7321505)


Co-authored-by: Prasanna Sridhar <imgprcsng@users.noreply.huggingface.co>

Files changed (3) hide show
  1. README.md +41 -3
  2. config.json +20 -0
  3. model.safetensors +3 -0
README.md CHANGED
@@ -1,3 +1,41 @@
1
- ---
2
- license: mit
3
- ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - en
4
+ library_name: CountGD
5
+ license: mit
6
+ tags:
7
+ - computer-vision
8
+ - counting
9
+ - grounding-dino
10
+ - model_hub_mixin
11
+ - multi-modal
12
+ - open-vocabulary
13
+ - pytorch_model_hub_mixin
14
+ - transformers
15
+ ---
16
+
17
+ # CountGD
18
+
19
+ A Multi-Modal Open-World Counting Model for counting objects in an image with text and image prompts.
20
+ For more details, please check out the following links
21
+
22
+ - Project page: https://www.robots.ox.ac.uk/~vgg/research/countgd/
23
+ - Code: https://github.com/niki-amini-naieni/CountGD
24
+ - Demo: https://huggingface.co/spaces/nikigoli/countgd
25
+ - Paper: https://arxiv.org/abs/2407.04619
26
+
27
+ ![Sample prediction](https://github.com/niki-amini-naieni/CountGD/blob/main/img/teaser.jpg)
28
+
29
+ ## Architecture
30
+
31
+ ![CountGD Architecture](https://github.com/niki-amini-naieni/CountGD/blob/main/img/architecture.jpg)
32
+
33
+
34
+ ## Citation
35
+
36
+ @article{AminiNaieni24,
37
+ author = "Amini-Naieni, N. and Han, T. and Zisserman, A.",
38
+ title = "CountGD: Multi-Modal Open-World Counting",
39
+ booktitle = "arxiv",
40
+ year = "2024",
41
+ }
config.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "aux_loss": true,
3
+ "dec_pred_bbox_embed_share": true,
4
+ "dn_box_noise_scale": 1.0,
5
+ "dn_label_noise_ratio": 0.5,
6
+ "dn_labelbook_size": 91,
7
+ "dn_number": 0,
8
+ "iter_update": true,
9
+ "max_text_len": 256,
10
+ "nheads": 8,
11
+ "num_feature_levels": 4,
12
+ "num_patterns": 0,
13
+ "num_queries": 900,
14
+ "query_dim": 4,
15
+ "sub_sentence_present": true,
16
+ "text_encoder_type": "checkpoints/bert-base-uncased",
17
+ "two_stage_bbox_embed_share": false,
18
+ "two_stage_class_embed_share": false,
19
+ "two_stage_type": "standard"
20
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e3baed25e5299034301b00c2647fb23503dd306c468259114a4957198424e4c
3
+ size 937560192