pengjunjie/ragflow
1
0
Fork 1
mirror of https://github.com/infiniflow/ragflow.git synced 2025-12-08 20:42:30 +08:00
Code Issues Packages Projects Releases Wiki Activity

apply pep8 formalize (#155)

Browse Source
This commit is contained in:
KevinHuSh
2024-03-27 11:33:46 +08:00
committed by GitHub
parent a02e836790
commit fd7fcb5baf
55 changed files with 1568 additions and 753 deletions
Download Patch File Download Diff File Expand all files Collapse all files

34
deepdoc/vision/t_ocr.py
View File

@ -11,12 +11,20 @@
# limitations under the License.
#
import os, sys
sys.path.insert(0, os.path.abspath(os.path.join(os.path.dirname(os.path.abspath(__file__)), '../../')))
import numpy as np
import argparse
from deepdoc.vision import OCR, init_in_out
from deepdoc.vision.seeit import draw_box
from deepdoc.vision import OCR, init_in_out
import argparse
import numpy as np
import os
import sys
sys.path.insert(
0,
os.path.abspath(
os.path.join(
os.path.dirname(
os.path.abspath(__file__)),
'../../')))
def main(args):
ocr = OCR()
@ -26,14 +34,14 @@ def main(args):
bxs = ocr(np.array(img))
bxs = [(line[0], line[1][0]) for line in bxs]
bxs = [{
"text": t,
"bbox": [b[0][0], b[0][1], b[1][0], b[-1][1]],
"type": "ocr",
"score": 1} for b, t in bxs if b[0][0] <= b[1][0] and b[0][1] <= b[-1][1]]
"text": t,
"bbox": [b[0][0], b[0][1], b[1][0], b[-1][1]],
"type": "ocr",
"score": 1} for b, t in bxs if b[0][0] <= b[1][0] and b[0][1] <= b[-1][1]]
img = draw_box(images[i], bxs, ["ocr"], 1.)
img.save(outputs[i], quality=95)
with open(outputs[i] + ".txt", "w+") as f: f.write("\n".join([o["text"] for o in bxs]))
with open(outputs[i] + ".txt", "w+") as f:
f.write("\n".join([o["text"] for o in bxs]))
if __name__ == "__main__":
@ -42,6 +50,6 @@ if __name__ == "__main__":
help="Directory where to store images or PDFs, or a file path to a single image or PDF",
required=True)
parser.add_argument('--output_dir', help="Directory where to store the output images. Default: './ocr_outputs'",
default="./ocr_outputs")
default="./ocr_outputs")
args = parser.parse_args()
main(args)
main(args)