file=fileout,
end=' ')
print('', file=fileout)
if add_boundary_blank:
print('{:.10g}'.format(0.0), file=fileout, end=' ')
for k in range(1, output.size(1)):
print('{:.10g}'.format(-1e30), file=fileout, end=' ')
print('', file=fileout)
print(']', file=fileout)
if __name__ == '__main__':
add_defaults('gpu')
add_argument('--adaptive_pool_height',
type=int,
default=16,
help='Average adaptive pooling of the images before the '
'LSTM layers')
add_argument('--lstm_hidden_size', type=int, default=128)
add_argument('--lstm_num_layers', type=int, default=1)
add_argument('--add_softmax', action='store_true')
add_argument('--add_boundary_blank', action='store_true')
add_argument('syms', help='Symbols table mapping from strings to integers')
add_argument('img_dir', help='Directory containing word images')
add_argument('gt_file', help='')
add_argument('checkpoint', help='')
add_argument('output', type=argparse.FileType('w'))
args = args()
# Build neural network
syms = SymbolsTable(args.syms)
from __future__ import absolute_import
import argparse
import torch.nn as nn
from laia.models.htr.gated_crnn import GatedCRNN
from laia.common import ModelSaver
from laia.common.arguments import add_argument, args, add_defaults
from laia.common.arguments_types import NumberInClosedRange, TupleList, \
str2bool
from laia.utils import SymbolsTable
if __name__ == '__main__':
add_defaults('train_path')
add_argument('num_input_channels',
type=NumberInClosedRange(int, vmin=1),
help='Number of channels of the input images')
add_argument('syms',
type=argparse.FileType('r'),
help='Symbols table mapping from strings to integers')
add_argument('--cnn_num_features',
type=NumberInClosedRange(int, vmin=1),
nargs='+',
default=[8, 16, 32, 64, 128],
help='Number of features in each convolutional layer')
add_argument('--cnn_kernel_size',
type=TupleList(int, dimensions=2),
nargs='+',
default=[3, (2, 4), 3, (2, 4), 3],
help='Kernel size of each convolution. '
'Use a list of integers, or a list of strings '
from torch.utils.data import DataLoader
from tqdm import tqdm
import laia
import laia.common.logging as log
from dortmund_utils import build_dortmund_model
from laia.data import TextImageFromTextTableDataset
from laia.common.arguments import add_argument, add_defaults, args
from laia.utils import ImageToTensor
from laia.utils.phoc import pphoc
if __name__ == '__main__':
add_defaults('gpu')
add_argument('--phoc_levels',
type=int,
default=[1, 2, 3, 4, 5],
nargs='+',
help='PHOC levels used to encode the transcript')
add_argument('syms', help='Symbols table mapping from strings to integers')
add_argument('img_dir', help='Directory containing word images')
add_argument('queries', help='Transcription of each query image')
add_argument('model_checkpoint', help='Filepath of the model checkpoint')
add_argument('output',
type=argparse.FileType('w'),
help='Filepath of the output file')
args = args()
syms = laia.utils.SymbolsTable(args.syms)
phoc_size = sum(args.phoc_levels) * len(syms)
model = build_dortmund_model(phoc_size)
log.info('Model has {} parameters',
import torch
from dortmund_utils import build_ctc_model
from laia.data import ImageDataLoader
from laia.data import TextImageFromTextTableDataset
from laia.decoders import CTCGreedyDecoder
from laia.common.arguments import add_argument, add_defaults, args
from laia.common.arguments_types import str2bool
from laia.utils import ImageToTensor, TextToTensor
from laia.utils.symbols_table import SymbolsTable
if __name__ == '__main__':
add_defaults('gpu')
add_argument('--adaptive_pool_height', type=int, default=16,
help='Average adaptive pooling of the images before the '
'LSTM layers')
add_argument('--lstm_hidden_size', type=int, default=128)
add_argument('--lstm_num_layers', type=int, default=1)
add_argument(
"--output_symbols",
type=str2bool,
nargs="?",
const=True,
default=False,
help="Print the output with symbols instead of integers",
)
add_argument('syms', help='Symbols table mapping from strings to integers')
add_argument('img_dir', help='Directory containing word images')
add_argument('gt_file', help='')
add_argument('checkpoint', help='')
'max_epochs',
'max_updates',
'train_samples_per_epoch',
'valid_samples_per_epoch',
'seed',
'train_path',
# Override default values for these arguments, but use the
# same help/checks:
learning_rate=0.0001,
momentum=0.9,
iterations_per_update=10,
show_progress_bar=True,
use_distortions=True,
weight_l2_penalty=0.00005)
add_argument('--load_checkpoint',
type=str,
help='Path to the checkpoint to load.')
add_argument('--continue_epoch', type=int)
add_argument('--phoc_levels',
type=int,
default=[1, 2, 3, 4, 5],
nargs='+',
help='PHOC levels used to encode the transcript')
add_argument('--exclude_words_ap',
type=FileType('r'),
help='List of words to exclude in the Average Precision '
'computation')
add_argument('--use_new_phoc', action='store_true')
add_argument('syms', help='Symbols table mapping from strings to integers')
add_argument('tr_img_dir', help='Directory containing word images')
add_argument('tr_txt_table',
import editdistance
def cer_score_dict(decoded, target, ids):
cer_dict = {}
for ref, hyp, x in zip(target, decoded, ids):
cer_dict[x] = editdistance.eval(ref, hyp) / len(ref)
return cer_dict
if __name__ == "__main__":
add_defaults("batch_size", "gpu", "train_path", logging_level="WARNING")
add_argument(
"--syms",
type=argparse.FileType("r"),
help="Symbols table mapping from strings to integers",
)
add_argument("--img_dirs",
type=str,
nargs="+",
help="Directory containing word images")
add_argument(
"--txt_table",
type=argparse.FileType("r"),
help="Character transcriptions of each image.",
)
add_argument(
"--delimiters",
type=str,
nargs="+",
'gpu',
'max_epochs',
'max_updates',
'train_samples_per_epoch',
'seed',
'train_path',
# Override default values for these arguments, but use the
# same help/checks:
learning_rate=0.0001,
momentum=0.9,
iterations_per_update=10,
show_progress_bar=True,
use_distortions=True,
weight_l2_penalty=0.00005)
add_argument('--load_checkpoint',
type=str,
help='Path to the checkpoint to load.')
add_argument('--continue_epoch', type=int)
add_argument('--phoc_levels',
type=int,
default=[1, 2, 3, 4, 5],
nargs='+',
help='PHOC levels used to encode the transcript')
add_argument('syms', help='Symbols table mapping from strings to integers')
add_argument('img_dir', help='Directory containing word images')
add_argument('tr_txt_table',
help='Character transcriptions of each training image')
add_argument('qry_txt_table',
help='Character transcriptions of each test query image')
add_argument('doc_txt_table',
help='Character transcriptions of each test document image')
file=fileout,
end=" ")
print("", file=fileout)
if add_boundary_blank:
print("{:.10g}".format(0.0), file=fileout, end=" ")
for k in range(1, output.size(1)):
print("{:.10g}".format(-1e30), file=fileout, end=" ")
print("", file=fileout)
print("]", file=fileout)
if __name__ == "__main__":
add_defaults("gpu")
add_argument(
"--image_sequencer",
type=str,
default="avgpool-16",
help="Average adaptive pooling of the images before the LSTM layers",
)
add_argument("--lstm_hidden_size", type=int, default=128)
add_argument("--lstm_num_layers", type=int, default=1)
add_argument("--add_softmax", action="store_true")
add_argument("--add_boundary_blank", action="store_true")
add_argument("syms", help="Symbols table mapping from strings to integers")
add_argument("img_dir", help="Directory containing word images")
add_argument("gt_file", help="")
add_argument("checkpoint", help="")
add_argument("output", type=argparse.FileType("w"))
args = args()
# Build neural network
syms = SymbolsTable(args.syms)
p0 = -math.expm1(lp1)
lp0 = math.log(p0) if p0 > 0 else float('-inf')
for k, p in enumerate([lp0, lp1], 1):
if not math.isinf(p):
print('{:d}\t{:d}\t{:d}\t0,{:.10g},{:d}'.format(
t, t + 1, k, -float(p), k),
file=fileout)
print(output.size(0), file=fileout)
print('', file=fileout)
if __name__ == '__main__':
add_defaults('gpu')
add_argument('--phoc_levels',
type=int,
default=[1, 2, 3, 4, 5],
nargs='+',
help='PHOC levels used to encode the transcript')
add_argument('--add_sigmoid', action='store_true')
add_argument('syms', help='Symbols table mapping from strings to integers')
add_argument('img_dir', help='Directory containing word images')
add_argument('gt_file', help='')
add_argument('checkpoint', help='')
add_argument('output', type=argparse.FileType('w'))
args = args()
# Build neural network
syms = SymbolsTable(args.syms)
phoc_size = sum(args.phoc_levels) * len(syms)
model = build_dortmund_model(phoc_size)
from laia.utils import SymbolsTable, ImageToTensor, TextToTensor
from laia.utils.dortmund_image_to_tensor import DortmundImageToTensor
from torch.optim import SGD
if __name__ == '__main__':
add_defaults('batch_size',
'learning_rate',
'gpu',
'max_epochs',
'train_path',
'train_samples_per_epoch',
'iterations_per_update',
momentum=0.9,
show_progress_bar=True)
add_argument('fixed_height',
type=int,
help='Resize images to this fixed height size')
add_argument('syms',
type=argparse.FileType('r'),
help='Symbols table mapping from strings to integers')
add_argument('img_dir', help='Directory containing word images')
add_argument('tr_txt_table',
type=argparse.FileType('r'),
help='Character transcriptions of each training image')
add_argument('va_txt_table',
type=argparse.FileType('r'),
help='Character transcriptions of each validation image')
args = args()
syms = SymbolsTable(args.syms)
logger = laia.common.logging.get_logger('laia.egs.washington.train_ctc')
if __name__ == '__main__':
add_defaults('gpu', 'max_epochs', 'max_updates', 'train_samples_per_epoch',
'valid_samples_per_epoch', 'seed', 'train_path',
# Override default values for these arguments, but use the
# same help/checks:
batch_size=1,
learning_rate=0.0001,
momentum=0.9,
iterations_per_update=10,
show_progress_bar=True,
use_distortions=True,
weight_l2_penalty=0.00005)
add_argument('--load_checkpoint', type=str,
help='Path to the checkpoint to load.')
add_argument('--continue_epoch', type=int)
add_argument('--train_laia', action='store_true',
help='Train Laia-based model')
add_argument('--adaptive_pool_height', type=int, default=16,
help='Average adaptive pooling of the images before the '
'LSTM layers')
add_argument('--cnn_num_filters', type=int, nargs='+',
default=[16, 32, 48, 64])
add_argument('--cnn_maxpool_size', type=int, nargs='*', default=[2, 2])
add_argument('--lstm_hidden_size', type=int, default=128)
add_argument('--lstm_num_layers', type=int, default=1)
add_argument('--min_size', type=int, default=None)
add_argument('syms', help='Symbols table mapping from strings to integers')
add_argument('tr_img_dir', help='Directory containing word images')
add_argument('tr_txt_table',
from tqdm import tqdm
import laia
from laia.models.kws.dortmund_phocnet import DortmundPHOCNet
import laia.common.logging as log
from dortmund_utils import build_dortmund_model
from laia.data import TextImageFromTextTableDataset
from laia.common.arguments import add_argument, add_defaults, args
from laia.utils import ImageToTensor
if __name__ == "__main__":
add_defaults("gpu")
add_argument(
"--phoc_levels",
type=int,
default=[1, 2, 3, 4, 5],
nargs="+",
help="PHOC levels used to encode the transcript",
)
add_argument(
"--tpp_levels",
type=int,
default=[1, 2, 3, 4, 5],
nargs="*",
help="Temporal Pyramid Pooling levels",
)
add_argument(
"--spp_levels",
type=int,
default=None,
nargs="*",