add-model (#1)
Browse files- update model (b39ef9809dcaa1b118d9418088d941f88c346fd4)
- update model (4053384cfc6dde424dbdc31a4d7991fe31ccdf67)
- update model (0828c8041827d0ba9384b95ee2c203dde7321505)
Co-authored-by: Prasanna Sridhar <imgprcsng@users.noreply.huggingface.co>
- README.md +41 -3
- config.json +20 -0
- model.safetensors +3 -0
README.md
CHANGED
@@ -1,3 +1,41 @@
|
|
1 |
-
---
|
2 |
-
|
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 |
+

|
28 |
+
|
29 |
+
## Architecture
|
30 |
+
|
31 |
+

|
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
|