def test_eval_files_with_different_sources(self):
run_predict(
predict_args(data=FileDataParams(
pred_extension=".ext-pred.txt",
images=sorted(
glob_all([
os.path.join(this_dir, "data", "uw3_50lines", "test",
"*.png")
])),
)))
r = run_eval(
eval_args(
gt_data=FileDataParams(texts=sorted(
glob_all([
os.path.join(this_dir, "data", "uw3_50lines", "test",
"*.gt.txt")
]))),
pred_data=FileDataParams(texts=sorted(
glob_all([
os.path.join(
this_dir,
"data",
"uw3_50lines",
"test",
"*.ext-pred.txt",
)
]))),
))
self.assertLess(r["avg_ler"],
0.0009,
msg="Current best model yields about 0.09% CER")
def test_prediction_hdf5(self):
run_predict(
predict_args(data=Hdf5(files=[
os.path.join(this_dir, "data", "uw3_50lines", "uw3-50lines.h5")
], )))
run_eval(
eval_args(gt_data=Hdf5(files=[
os.path.join(this_dir, "data", "uw3_50lines", "uw3-50lines.h5")
], )))
def test_eval_pagexml(self):
run_predict(
predict_args(data=PageXML(images=[
os.path.join(this_dir, "data", "avicanon_pagexml",
"008.nrm.png")
], )))
run_eval(
eval_args(gt_data=PageXML(xml_files=[
os.path.join(this_dir, "data", "avicanon_pagexml", "008.xml")
], )))
def test_eval_hdf5(self):
run_predict(
predict_args(data=Hdf5(files=[
os.path.join(this_dir, "data", "uw3_50lines", "uw3-50lines.h5")
], )))
r = run_eval(
eval_args(gt_data=Hdf5(files=[
os.path.join(this_dir, "data", "uw3_50lines", "uw3-50lines.h5")
], )))
self.assertLess(r["avg_ler"],
0.006,
msg="Current best model yields about 0.55% CER")
def test_prediction_abbyy(self):
run_predict(
predict_args(data=Abbyy(images=[
os.path.join(this_dir, "data",
"hiltl_die_bank_des_verderbens_abbyyxml", "*.jpg")
], )))
run_eval(
eval_args(gt_data=Abbyy(xml_files=[
os.path.join(this_dir, "data",
"hiltl_die_bank_des_verderbens_abbyyxml",
"*.abbyy.xml")
], )))
def test_eval_list_files(self):
run_predict(
predict_args(data=FileDataParams(images=sorted(
glob_all([
os.path.join(this_dir, "data", "uw3_50lines", "test.files")
])))))
r = run_eval(
eval_args(gt_data=FileDataParams(texts=sorted(
glob_all([
os.path.join(this_dir, "data", "uw3_50lines",
"test.gt.files")
])))))
self.assertLess(r["avg_ler"],
0.0009,
msg="Current best model yields about 0.09% CER")
def test_prediction_files_with_different_extension(self):
run_predict(
predict_args(data=FileDataParams(
pred_extension='.ext-pred.txt',
images=sorted(
glob_all([
os.path.join(this_dir, "data", "uw3_50lines", "test",
"*.png")
])))))
run_eval(
eval_args(gt_data=FileDataParams(
pred_extension='.ext-pred.txt',
texts=sorted(
glob_all([
os.path.join(this_dir, "data", "uw3_50lines", "test",
"*.gt.txt")
])))))
def test_prediction_files(self):
run_predict(
predict_args(data=FileDataParams(images=sorted(
glob_all([
os.path.join(this_dir, "data", "uw3_50lines", "test",
"*.png")
])))))
run_eval(
eval_args(gt_data=FileDataParams(texts=sorted(
glob_all([
os.path.join(this_dir, "data", "uw3_50lines", "test",
"*.gt.txt")
])))))
args = eval_args(gt_data=FileDataParams(texts=sorted(
glob_all([
os.path.join(this_dir, "data", "uw3_50lines", "test",
"*.gt.txt")
]))))
with tempfile.TemporaryDirectory() as d:
args.xlsx_output = os.path.join(d, 'output.xlsx')
run_eval(args)
def test_eval_files(self):
run_predict(
predict_args(data=FileDataParams(images=sorted(
glob_all([
os.path.join(this_dir, "data", "uw3_50lines", "test",
"*.png")
])))))
r = run_eval(
eval_args(gt_data=FileDataParams(texts=sorted(
glob_all([
os.path.join(this_dir, "data", "uw3_50lines", "test",
"*.gt.txt")
])))))
self.assertLess(r["avg_ler"],
0.0009,
msg="Current best model yields about 0.09% CER")
args = eval_args(gt_data=FileDataParams(texts=sorted(
glob_all([
os.path.join(this_dir, "data", "uw3_50lines", "test",
"*.gt.txt")
]))))
with tempfile.TemporaryDirectory() as d:
args.xlsx_output = os.path.join(d, "output.xlsx")
run_eval(args)