parser.add_argument("--batch_size", type=int, default=64)
parser.add_argument("--N", type=int, default=2)
args = parser.parse_args()
raw_path = os.path.join("..", "raw")
data_path = os.path.join("..", "data")
source_path = os.path.join(data_path, f"{args.source}.txt")
output_path = os.path.join("..", "output", args.source, args.mode)
target_path = os.path.join(output_path, "checkpoint_weights.hdf5")
max_text_length = 128
charset_base = string.printable[:95]
charset_special = """ÀÁÂÃÄÅÇÈÉÊËÌÍÎÏÑÒÓÔÕÖÙÚÛÜÝàáâãäåçèéêëìíîïñòóôõöùúûüý"""
if args.transform:
data = Dataset(source=os.path.join(raw_path, args.source))
data.read_lines(maxlen=max_text_length)
valid_noised = pp.add_noise(data.dataset['valid'], max_text_length)
test_noised = pp.add_noise(data.dataset['test'], max_text_length)
valid_metrics = ev.ocr_metrics(ground_truth=data.dataset['valid'],
data=valid_noised)
info = "\n".join([
f"####",
f"#### {args.source} partitions (number of sentences)",
f"####",
f"#### Total: {data.size['total']}",
f"####",
f"#### Train: {data.size['train']}",
args = parser.parse_args()
raw_path = os.path.join("..", "raw", args.source)
source_path = os.path.join("..", "data", f"{args.source}.hdf5")
output_path = os.path.join("..", "output", args.source, args.arch)
target_path = os.path.join(output_path, "checkpoint_weights.hdf5")
input_size = (1024, 128, 1)
max_text_length = 128
charset_base = string.printable[:95]
if args.transform:
assert os.path.exists(raw_path)
print(f"The {args.source} dataset will be transformed...")
ds = Dataset(source=raw_path, name=args.source)
ds.read_partitions()
print("Partitions will be preprocessed...")
ds.preprocess_partitions(input_size=input_size)
print("Partitions will be saved...")
os.makedirs(os.path.dirname(source_path), exist_ok=True)
for i in ds.partitions:
with h5py.File(source_path, "a") as hf:
hf.create_dataset(f"{i}/dt",
data=ds.dataset[i]['dt'],
compression="gzip",
compression_opts=9)
hf.create_dataset(f"{i}/gt",
args = parser.parse_args()
raw_path = os.path.join("..", "raw", args.source)
source_path = os.path.join("..", "data", f"{args.source}.hdf5")
output_path = os.path.join("..", "output", args.source, args.arch)
target_path = os.path.join(output_path, "checkpoint_weights.hdf5")
input_size = (1024, 128, 1)
max_text_length = 128
charset_base = string.printable[:95]
if args.transform:
assert os.path.exists(raw_path)
print(f"The {args.source} dataset will be transformed...")
ds = Dataset(source=raw_path, name=args.source)
ds.read_partitions()
print("Partitions will be preprocessed...")
ds.preprocess_partitions(input_size=input_size)
print("Partitions will be saved...")
os.makedirs(os.path.dirname(source_path), exist_ok=True)
for i in ds.partitions:
with h5py.File(source_path, "a") as hf:
hf.create_dataset(f"{i}/dt",
data=ds.dataset[i]['dt'],
compression="gzip",
compression_opts=9)
hf.create_dataset(f"{i}/gt",
os.makedirs(output_path, exist_ok = True)
if args.transform:
# from data.create_hdf5 import Dataset
# if os.path.isfile(source_path):
# print("Dataset file already exists")
# else:
# ds = Dataset()
# ds.save_partitions()
from data.reader import Dataset
print(f"iam dataset will be transformed...")
ds = Dataset(source=os.path.join(raw_path, "iam"), name="iam")
ds.read_partitions()
ds.save_partitions(source_path, target_image_size, maxTextLength)
elif args.predict:
input_image_path = os.path.join(output_path, "prediction")
output_image_path = os.path.join(input_image_path, "out")
os.makedirs(output_image_path, exist_ok=True)
if args.image:
images = sorted(glob(os.path.join(input_image_path, args.image)))
else:
images = sorted(glob(os.path.join(input_image_path, "*.png")))
from network.model import MyModel
raw_path = os.path.join("raw")
source_path = os.path.join("data", f"{ds_names_str}.hdf5")
output_path = os.path.join("output", ds_names_str, args.arch)
target_path = os.path.join(output_path, "checkpoint_weights.hdf5")
if args.charset_path is not None:
with open(args.charset_path, 'r') as f:
charset_base = f.readline().strip()
print('hej')
else:
charset_base = string.printable[:95]
if args.transform:
print(os.getcwd())
print(f"{ds_names_str} dataset will be transformed...")
ds = Dataset(source=raw_path, name=args.ds_names)
ds.read_partitions()
ds.save_partitions(source_path,
input_size,
max_text_length,
binarize=args.binarize)
elif args.cv2:
with h5py.File(source_path, "r") as hf:
dt = hf['test']['dt'][:256]
gt = hf['test']['gt'][:256]
predict_file = os.path.join(output_path, "predict.txt")
predicts = [''] * len(dt)
if os.path.isfile(predict_file):
parser.add_argument("--epochs", type=int, default=1000)
parser.add_argument("--batch_size", type=int, default=16)
args = parser.parse_args()
raw_path = os.path.join("..", "raw", args.source)
source_path = os.path.join("..", "data", f"{args.source}.hdf5")
output_path = os.path.join("..", "output", args.source, args.arch)
target_path = os.path.join(output_path, "checkpoint_weights.hdf5")
input_size = (1024, 128, 1)
max_text_length = 128
charset_base = string.printable[:95]
if args.transform:
print(f"{args.source} dataset will be transformed...")
ds = Dataset(source=raw_path, name=args.source)
ds.read_partitions()
ds.save_partitions(source_path, input_size, max_text_length)
elif args.cv2:
with h5py.File(source_path, "r") as hf:
dt = hf['test']['dt'][:256]
gt = hf['test']['gt'][:256]
predict_file = os.path.join(output_path, "predict.txt")
predicts = [''] * len(dt)
if os.path.isfile(predict_file):
with open(predict_file, "r") as lg:
predicts = [line[5:] for line in lg if line.startswith("TE_P")]
