"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,
num_rolling_checkpoints=5,
iterations_per_update=10,
save_checkpoint_interval=5,
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(
"--tpp_levels",
type=int,
default=[1, 2, 3, 4, 5],
nargs="*",
help="Temporal Pyramid Pooling levels",
for t in range(output.size(0)):
for k in range(output.size(1)):
print(
"{:d}\t{:d}\t{:d}\t0,{:.10g},{:d}".format(
t, t + 1, k + 1, -float(output[t, k]), k + 1),
file=fileout,
)
print(output.size(0), 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("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)
model = DortmundCRNN(
"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,
num_rolling_checkpoints=5,
iterations_per_update=10,
save_checkpoint_interval=5,
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(
"--image_sequencer",
type=str,
default="avgpool-16",
help="Average adaptive pooling of the images before the LSTM layers",
)
add_argument(
"--use_adam_optim",
type=str2bool,
nargs="?",
const=True,
default=False,
help="If true, use Adam optimizer instead of SGD",
from torch.utils.data import DataLoader
from tqdm import tqdm
import laia
import laia.logging as log
from laia.data import TextImageFromTextTableDataset
from laia.models.kws.dortmund_phocnet import DortmundPHOCNet
from laia.plugins.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("syms", help="Symbols table mapping from strings to integers")
add_argument("img_dir", help="Directory containing word images")
add_argument("candidates", help="Transcription of each candidate image")
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)
from laia.data import ImageDataLoader
from laia.data import TextImageFromTextTableDataset
from laia.decoders import CTCGreedyDecoder
from laia.models.htr.dortmund_crnn import DortmundCRNN
from laia.plugins.arguments import add_argument, add_defaults, args
from laia.plugins.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(
"--output_symbols",
type=str2bool,
nargs="?",
const=True,
default=False,
help="Print the output with symbols instead of integers",
)
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("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="")
if x.shape != 3:
x = np.expand_dims(x, axis=-1)
x = np.transpose(x, (2, 0, 1))
return torch.from_numpy(x)
if __name__ == "__main__":
import matplotlib.pyplot as plt
import laia.random
from laia.data import TextImageFromTextTableDataset, ImageDataLoader
from laia.plugins.arguments import add_argument, add_defaults, args
add_defaults("seed")
add_argument("--num_images",
type=int,
help="Show only this number of images")
add_argument("--shuffle",
action="store_true",
help="Shuffle the list of images")
add_argument("img_dir", help="Directory containing images")
add_argument("txt_table", help="Transcriptions of each image")
args = args()
laia.random.manual_seed(args.seed)
dataset = TextImageFromTextTableDataset(
args.txt_table, args.img_dir, img_transform=DortmundImageToTensor())
dataset_loader = ImageDataLoader(dataset=dataset,
image_channels=1,
shuffle=args.shuffle)
from tqdm import tqdm
import laia
import laia.logging as log
from laia.data import TextImageFromTextTableDataset
from laia.models.kws.dortmund_phocnet import DortmundPHOCNet
from laia.plugins.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(
"--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="*",