Spaces:
Runtime error
Runtime error
vtccvision
commited on
Commit
β’
e4b9ee5
1
Parent(s):
a70acb7
Init
Browse files- .gitattributes +3 -8
- .gitignore +3 -0
- README.md +5 -5
- app.py +46 -0
- requirements-lock.txt +104 -0
- requirements.txt +4 -0
.gitattributes
CHANGED
@@ -2,27 +2,20 @@
|
|
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
|
@@ -30,5 +23,7 @@ saved_model/**/* 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 |
-
*.
|
34 |
*tfevents* 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 |
*.ftz filter=lfs diff=lfs merge=lfs -text
|
6 |
*.gz filter=lfs diff=lfs merge=lfs -text
|
7 |
*.h5 filter=lfs diff=lfs merge=lfs -text
|
8 |
*.joblib filter=lfs diff=lfs merge=lfs -text
|
9 |
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
|
|
10 |
*.model filter=lfs diff=lfs merge=lfs -text
|
11 |
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
12 |
*.onnx filter=lfs diff=lfs merge=lfs -text
|
13 |
*.ot filter=lfs diff=lfs merge=lfs -text
|
14 |
*.parquet filter=lfs diff=lfs merge=lfs -text
|
15 |
*.pb filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
16 |
*.pt filter=lfs diff=lfs merge=lfs -text
|
17 |
*.pth filter=lfs diff=lfs merge=lfs -text
|
18 |
*.rar filter=lfs diff=lfs merge=lfs -text
|
|
|
19 |
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
20 |
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
21 |
*.tflite filter=lfs diff=lfs merge=lfs -text
|
|
|
23 |
*.wasm filter=lfs diff=lfs merge=lfs -text
|
24 |
*.xz filter=lfs diff=lfs merge=lfs -text
|
25 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
26 |
+
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
27 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
28 |
+
sample_cord_receipt(receipt_00004).png filter=lfs diff=lfs merge=lfs -text
|
29 |
+
sample_image_cord_test_receipt_00004.png filter=lfs diff=lfs merge=lfs -text
|
.gitignore
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
env
|
2 |
+
__pycache__
|
3 |
+
*.png
|
README.md
CHANGED
@@ -1,10 +1,10 @@
|
|
1 |
---
|
2 |
-
title: Cord V2
|
3 |
-
emoji:
|
4 |
-
colorFrom:
|
5 |
-
colorTo:
|
6 |
sdk: gradio
|
7 |
-
sdk_version: 3.
|
8 |
app_file: app.py
|
9 |
pinned: false
|
10 |
---
|
|
|
1 |
---
|
2 |
+
title: Donut Base Finetuned Cord V2
|
3 |
+
emoji: π©
|
4 |
+
colorFrom: blue
|
5 |
+
colorTo: gray
|
6 |
sdk: gradio
|
7 |
+
sdk_version: 3.0.26
|
8 |
app_file: app.py
|
9 |
pinned: false
|
10 |
---
|
app.py
ADDED
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
"""
|
2 |
+
Donut
|
3 |
+
Copyright (c) 2022-present NAVER Corp.
|
4 |
+
MIT License
|
5 |
+
|
6 |
+
https://github.com/clovaai/donut
|
7 |
+
"""
|
8 |
+
import gradio as gr
|
9 |
+
import torch
|
10 |
+
from PIL import Image
|
11 |
+
|
12 |
+
from donut import DonutModel
|
13 |
+
|
14 |
+
def demo_process(input_img):
|
15 |
+
global pretrained_model, task_prompt, task_name
|
16 |
+
# input_img = Image.fromarray(input_img)
|
17 |
+
output = pretrained_model.inference(image=input_img, prompt=task_prompt)["predictions"][0]
|
18 |
+
return output
|
19 |
+
|
20 |
+
task_prompt = f"<s_cord-v2>"
|
21 |
+
|
22 |
+
image = Image.open("./sample_image_cord_test_receipt_00004.png")
|
23 |
+
image.save("cord_sample_receipt1.png")
|
24 |
+
image = Image.open("./sample_image_cord_test_receipt_00012.png")
|
25 |
+
image.save("cord_sample_receipt2.png")
|
26 |
+
|
27 |
+
pretrained_model = DonutModel.from_pretrained("naver-clova-ix/donut-base-finetuned-cord-v2")
|
28 |
+
pretrained_model.eval()
|
29 |
+
|
30 |
+
demo = gr.Interface(
|
31 |
+
fn=demo_process,
|
32 |
+
inputs= gr.inputs.Image(type="pil"),
|
33 |
+
outputs="json",
|
34 |
+
title=f"Donut π© demonstration for `cord-v2` task",
|
35 |
+
description="""This model is trained with 800 Indonesian receipt images of CORD dataset. <br>
|
36 |
+
Demonstrations for other types of documents/tasks are available at https://github.com/clovaai/donut <br>
|
37 |
+
More CORD receipt images are available at https://huggingface.co/datasets/naver-clova-ix/cord-v2
|
38 |
+
|
39 |
+
More details are available at:
|
40 |
+
- Paper: https://arxiv.org/abs/2111.15664
|
41 |
+
- GitHub: https://github.com/clovaai/donut""",
|
42 |
+
examples=[["cord_sample_receipt1.png"], ["cord_sample_receipt2.png"]],
|
43 |
+
cache_examples=False,
|
44 |
+
)
|
45 |
+
|
46 |
+
demo.launch(server_name="0.0.0.0")
|
requirements-lock.txt
ADDED
@@ -0,0 +1,104 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
aiofiles==23.1.0
|
2 |
+
aiohttp==3.8.4
|
3 |
+
aiosignal==1.3.1
|
4 |
+
altair==4.2.2
|
5 |
+
anyio==3.6.2
|
6 |
+
async-timeout==4.0.2
|
7 |
+
attrs==23.1.0
|
8 |
+
certifi==2022.12.7
|
9 |
+
charset-normalizer==3.1.0
|
10 |
+
click==8.1.3
|
11 |
+
cmake==3.26.3
|
12 |
+
contourpy==1.0.7
|
13 |
+
cycler==0.11.0
|
14 |
+
datasets==2.11.0
|
15 |
+
dill==0.3.6
|
16 |
+
donut-python==1.0.9
|
17 |
+
entrypoints==0.4
|
18 |
+
fastapi==0.95.1
|
19 |
+
ffmpy==0.3.0
|
20 |
+
filelock==3.11.0
|
21 |
+
fonttools==4.39.3
|
22 |
+
frozenlist==1.3.3
|
23 |
+
fsspec==2023.4.0
|
24 |
+
gradio==3.27.0
|
25 |
+
gradio_client==0.1.3
|
26 |
+
h11==0.14.0
|
27 |
+
httpcore==0.17.0
|
28 |
+
httpx==0.24.0
|
29 |
+
huggingface-hub==0.13.4
|
30 |
+
idna==3.4
|
31 |
+
Jinja2==3.1.2
|
32 |
+
joblib==1.2.0
|
33 |
+
jsonschema==4.17.3
|
34 |
+
kiwisolver==1.4.4
|
35 |
+
lightning-utilities==0.8.0
|
36 |
+
linkify-it-py==2.0.0
|
37 |
+
lit==16.0.1
|
38 |
+
markdown-it-py==2.2.0
|
39 |
+
MarkupSafe==2.1.2
|
40 |
+
matplotlib==3.7.1
|
41 |
+
mdit-py-plugins==0.3.3
|
42 |
+
mdurl==0.1.2
|
43 |
+
mpmath==1.3.0
|
44 |
+
multidict==6.0.4
|
45 |
+
multiprocess==0.70.14
|
46 |
+
munch==2.5.0
|
47 |
+
networkx==3.1
|
48 |
+
nltk==3.8.1
|
49 |
+
numpy==1.24.2
|
50 |
+
nvidia-cublas-cu11==11.10.3.66
|
51 |
+
nvidia-cuda-cupti-cu11==11.7.101
|
52 |
+
nvidia-cuda-nvrtc-cu11==11.7.99
|
53 |
+
nvidia-cuda-runtime-cu11==11.7.99
|
54 |
+
nvidia-cudnn-cu11==8.5.0.96
|
55 |
+
nvidia-cufft-cu11==10.9.0.58
|
56 |
+
nvidia-curand-cu11==10.2.10.91
|
57 |
+
nvidia-cusolver-cu11==11.4.0.1
|
58 |
+
nvidia-cusparse-cu11==11.7.4.91
|
59 |
+
nvidia-nccl-cu11==2.14.3
|
60 |
+
nvidia-nvtx-cu11==11.7.91
|
61 |
+
orjson==3.8.10
|
62 |
+
packaging==23.1
|
63 |
+
pandas==2.0.0
|
64 |
+
Pillow==9.5.0
|
65 |
+
pyarrow==11.0.0
|
66 |
+
pydantic==1.10.7
|
67 |
+
pydub==0.25.1
|
68 |
+
pyparsing==3.0.9
|
69 |
+
pyrsistent==0.19.3
|
70 |
+
python-dateutil==2.8.2
|
71 |
+
python-multipart==0.0.6
|
72 |
+
pytorch-lightning==2.0.1.post0
|
73 |
+
pytz==2023.3
|
74 |
+
PyYAML==6.0
|
75 |
+
regex==2023.3.23
|
76 |
+
requests==2.28.2
|
77 |
+
responses==0.18.0
|
78 |
+
ruamel.yaml==0.17.21
|
79 |
+
ruamel.yaml.clib==0.2.7
|
80 |
+
sconf==0.2.5
|
81 |
+
semantic-version==2.10.0
|
82 |
+
sentencepiece==0.1.98
|
83 |
+
six==1.16.0
|
84 |
+
sniffio==1.3.0
|
85 |
+
starlette==0.26.1
|
86 |
+
sympy==1.11.1
|
87 |
+
timm==0.6.13
|
88 |
+
tokenizers==0.13.3
|
89 |
+
toolz==0.12.0
|
90 |
+
torch==2.0.0
|
91 |
+
torchmetrics==0.11.4
|
92 |
+
torchvision==0.15.1
|
93 |
+
tqdm==4.65.0
|
94 |
+
transformers==4.24.0
|
95 |
+
triton==2.0.0
|
96 |
+
typing_extensions==4.5.0
|
97 |
+
tzdata==2023.3
|
98 |
+
uc-micro-py==1.0.1
|
99 |
+
urllib3==1.26.15
|
100 |
+
uvicorn==0.21.1
|
101 |
+
websockets==11.0.2
|
102 |
+
xxhash==3.2.0
|
103 |
+
yarl==1.8.2
|
104 |
+
zss==1.2.0
|
requirements.txt
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
torch
|
2 |
+
donut-python
|
3 |
+
gradio
|
4 |
+
transformers==4.24.0
|