Darwin Bautista
commited on
Commit
·
a1526c3
1
Parent(s):
3c59be4
Initial commit of weights
Browse files- README.md +39 -0
- pytorch_model.bin +3 -0
- torchscript_model.bin +3 -0
README.md
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
language:
|
3 |
+
- en
|
4 |
+
license: apache-2.0
|
5 |
+
tags:
|
6 |
+
- image-to-text
|
7 |
+
---
|
8 |
+
|
9 |
+
# PARSeq small v1.0
|
10 |
+
|
11 |
+
PARSeq model pre-trained on various real [STR datasets](https://github.com/baudm/parseq/blob/main/Datasets.md) at image size 128x32 with a patch size of 8x4.
|
12 |
+
|
13 |
+
## Model description
|
14 |
+
|
15 |
+
PARSeq (Permuted Autoregressive Sequence) models unify the prevailing modeling/decoding schemes in Scene Text Recognition (STR). In particular, with a single model, it allows for context-free non-autoregressive inference (like CRNN and ViTSTR), context-aware autoregressive inference (like TRBA), and bidirectional iterative refinement (like ABINet).
|
16 |
+
|
17 |
+

|
18 |
+
|
19 |
+
## Intended uses & limitations
|
20 |
+
|
21 |
+
You can use the model for STR on images containing Latin characters (62 case-sensitive alphanumeric + 32 punctuation marks).
|
22 |
+
|
23 |
+
### How to use
|
24 |
+
|
25 |
+
*TODO*
|
26 |
+
|
27 |
+
### BibTeX entry and citation info
|
28 |
+
|
29 |
+
```bibtex
|
30 |
+
@InProceedings{bautista2022parseq,
|
31 |
+
author={Bautista, Darwin and Atienza, Rowel},
|
32 |
+
title={Scene Text Recognition with Permuted Autoregressive Sequence Models},
|
33 |
+
booktitle={Proceedings of the 17th European Conference on Computer Vision (ECCV)},
|
34 |
+
month={10},
|
35 |
+
year={2022},
|
36 |
+
publisher={Springer International Publishing},
|
37 |
+
address={Cham}
|
38 |
+
}
|
39 |
+
```
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bb5792a68e367476abca029cbf8699abc805f3d3dc7e57aae45c8ec4f7b7cd00
|
3 |
+
size 95392675
|
torchscript_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fbd7482c5ef7702a92c1a51f1eefe89f320853550496b88cb4042702caed09a9
|
3 |
+
size 95443044
|