def main(results):
# restore config and model
dir_output = results
config_data = Config(dir_output + "data.json")
config_vocab = Config(dir_output + "vocab.json")
config_model = Config(dir_output + "model.json")
vocab = Vocab(config_vocab)
model = Img2SeqModel(config_model, dir_output, vocab)
model.build_pred()
model.restore_session(dir_output + "model.weights/")
# load dataset
test_set = DataGenerator(index_file=config_data.index_test,
path_formulas=config_data.path_formulas_test,
dir_images=config_data.dir_images_test,
max_iter=config_data.max_iter,
path_matching=config_data.path_matching_test,
form_prepro=vocab.form_prepro)
# use model to write predictions in files
config_eval = Config({
"dir_answers": dir_output + "formulas_test/",
"batch_size": 20
})
files, perplexity = model.write_prediction(config_eval, test_set)
formula_ref, formula_hyp = files[0], files[1]
# score the ref and prediction files
scores = score_files(formula_ref, formula_hyp)
scores["perplexity"] = perplexity
msg = " - ".join(["{} {:04.2f}".format(k, v) for k, v in scores.items()])
model.logger.info("- Test Txt: {}".format(msg))
def main(data, vocab, training, model, output):
# Load configs
dir_output = output
config = Config([data, vocab, training, model])
config.save(dir_output)
vocab = Vocab(config)
# Load datasets
train_set = DataGenerator(path_formulas=config.path_formulas_train,
dir_images=config.dir_images_train, img_prepro=greyscale,
max_iter=config.max_iter, bucket=config.bucket_train,
path_matching=config.path_matching_train,
max_len=config.max_length_formula,
form_prepro=vocab.form_prepro)
val_set = DataGenerator(path_formulas=config.path_formulas_val,
dir_images=config.dir_images_val, img_prepro=greyscale,
max_iter=config.max_iter, bucket=config.bucket_val,
path_matching=config.path_matching_val,
max_len=config.max_length_formula,
form_prepro=vocab.form_prepro)
# Define learning rate schedule
n_batches_epoch = ((len(train_set) + config.batch_size - 1) //
config.batch_size)
lr_schedule = LRSchedule(lr_init=config.lr_init,
start_decay=config.start_decay*n_batches_epoch,
end_decay=config.end_decay*n_batches_epoch,
end_warm=config.end_warm*n_batches_epoch,
lr_warm=config.lr_warm,
lr_min=config.lr_min)
# Build model and train
model = Img2SeqModel(config, dir_output, vocab)
model.build_train(config)
model.train(config, train_set, val_set, lr_schedule)
def main(results):
# restore config and model
dir_output = results
config_data = Config(dir_output + "data.json")
config_vocab = Config(dir_output + "vocab.json")
config_model = Config(dir_output + "model.json")
vocab = Vocab(config_vocab)
model = Img2SeqModel(config_model, dir_output, vocab)
model.build_pred()
model.restore_session(dir_output + "model.weights/")
# load dataset
test_set = DataGenerator(path_formulas=config_data.path_formulas_test,
dir_images=config_data.dir_images_test, img_prepro=greyscale,
max_iter=config_data.max_iter, bucket=config_data.bucket_test,
path_matching=config_data.path_matching_test,
max_len=config_data.max_length_formula,
form_prepro=vocab.form_prepro,)
# build images from formulas
formula_ref = path.join(dir_output, "formulas_test/ref.txt")
formula_hyp = path.join(dir_output, "formulas_test/hyp_0.txt")
images_ref = path.join(dir_output, "images_test/ref/")
images_test = path.join(dir_output, "images_test/hyp_0/")
build_images(load_formulas(formula_ref), images_ref)
build_images(load_formulas(formula_hyp), images_test)
# score the repositories
scores = score_dirs(images_ref, images_test, greyscale)
msg = " - ".join(["{} {:04.2f}".format(k, v) for k, v in scores.items()])
model.logger.info("- Eval Img: {}".format(msg))
def main(image, vocab, model, output):
dir_output = output
img_path = image
# 加载配置，根据配置初始化字典和模型
config = Config([vocab, model])
vocab = Vocab(config)
img2SeqModel = Img2SeqModel(config, dir_output, vocab)
img2SeqModel.build_pred()
vis_img_with_attention(img2SeqModel, img_path, dir_output)
def getModelForPrediction():
# restore config and model
dir_output = "./results/full/"
config_vocab = Config(dir_output + "vocab.json")
config_model = Config(dir_output + "model.json")
vocab = Vocab(config_vocab)
model = Img2SeqModel(config_model, dir_output, vocab)
model.build_pred()
# model.restore_session(dir_output + "model_weights/model.cpkt")
return model
def main(data, vocab, training, model, output):
# Load configs
dir_output = output
config = Config([data, vocab, training, model])
config.save(dir_output)
vocab = Vocab(config)
# Load datasets
train_set = DataGenerator(path_formulas=config.path_formulas_train,
dir_images=config.dir_images_train, img_prepro=greyscale,
max_iter=config.max_iter, bucket=config.bucket_train,
path_matching=config.path_matching_train,
max_len=config.max_length_formula,
form_prepro=vocab.form_prepro)
all_img = []
all_formula = []
for i, (_img, _formula) in enumerate(minibatches(train_set, batch_size)):
all_img.append(_img)
if _formula is not None:
_formula, _formula_length = pad_batch_formulas(
_formula,
vocab.id_pad,
vocab.id_end
)
all_formula.append(_formula)
np.save('np_formula', np.array(all_formula))
np.save('np_img', np.array(all_img))
print("DONE EXPORTING NUMPY FILES")
return None
val_set = DataGenerator(path_formulas=config.path_formulas_val,
dir_images=config.dir_images_val, img_prepro=greyscale,
max_iter=config.max_iter, bucket=config.bucket_val,
path_matching=config.path_matching_val,
max_len=config.max_length_formula,
form_prepro=vocab.form_prepro)
# Define learning rate schedule
n_batches_epoch = ((len(train_set) + config.batch_size - 1) //
config.batch_size)
lr_schedule = LRSchedule(lr_init=config.lr_init,
start_decay=config.start_decay*n_batches_epoch,
end_decay=config.end_decay*n_batches_epoch,
end_warm=config.end_warm*n_batches_epoch,
lr_warm=config.lr_warm,
lr_min=config.lr_min)
# Build model and train
model = Img2SeqModel(config, dir_output, vocab)
model.build_train(config)
model.train(config, train_set, val_set, lr_schedule)
def load_model(dir_output="results/full/",
vocab_config='vocab.json',
model_config='model.json',
model_path='model.weights/'):
config_vocab = Config(os.path.join(dir_output, vocab_config))
config_model = Config(os.path.join(dir_output, model_config))
vocab = Vocab(config_vocab)
model = Img2SeqModel(config_model, dir_output, vocab)
model.build_pred()
model.restore_session(os.path.join(dir_output, model_path))
return model
def get_im2latex_model(weight_dir):
"""
Load up model from the given weight location
:param weight_dir: weight location
:return: trained model
"""
os.environ["TF_CPP_MIN_LOG_LEVEL"] = "3"
tf.logging.set_verbosity(tf.logging.ERROR)
config_vocab = Config(weight_dir + "vocab.json")
config_model = Config(weight_dir + "model.json")
vocab = Vocab(config_vocab)
model = Img2SeqModel(config_model, weight_dir, vocab)
model.build_pred()
model.restore_session(weight_dir + "model.weights/")
return model
def img2latex_api(weight_dir, img_path, downsample_image_ratio, cropping,
padding, gray_scale):
os.environ['TF_CPP_MIN_LOG_LEVEL'] = '3'
tf.logging.set_verbosity(tf.logging.ERROR)
config_vocab = Config(weight_dir + "vocab.json")
config_model = Config(weight_dir + "model.json")
vocab = Vocab(config_vocab)
model = Img2SeqModel(config_model, weight_dir, vocab)
model.build_pred()
model.restore_session(weight_dir + "model.weights/")
seq = iaa.Sequential([iaa.GammaContrast(2)])
latex, _, _ = img2latex(model,
img_path,
downsample_image_ratio=downsample_image_ratio,
cropping=cropping,
padding=padding,
img_augment=seq,
gray_scale=gray_scale)
processed_latex = postprocess(latex)
return processed_latex
def predict(trained_model):
"""
Args:
trained_model (Img2SeqModel):
"""
if len(sys.argv) <= 1:
print "Usage"
print "python predict.py abs/path/to/image.png"
return
image_path = sys.argv[1]
img = imread(image_path)
img = greyscale(img)
res = trained_model.predict(img)
trained_model.logger.info(res[0])
if __name__ == "__main__":
# restore config and model
dir_output = "results/full/"
config_vocab = Config(dir_output + "vocab.json")
config_model = Config(dir_output + "model.json")
vocab = Vocab(config_vocab)
model = Img2SeqModel(config_model, dir_output, vocab)
model.build_pred()
model.restore_session(dir_output + "model.weights/")
# interactive_shell(model)
predict(model)
import os
from model.img2seq import Img2SeqModel
from model.utils.general import Config, run
from model.utils.text import Vocab
APP_ROOT = os.path.dirname(
os.path.abspath(__file__)) # refers to application_top
MODEL_FOLDER = os.path.join(APP_ROOT, 'full')
print("loading model ...")
config_vocab = Config(os.path.join(MODEL_FOLDER, "vocab.json"))
config_model = Config(os.path.join(MODEL_FOLDER, "model.json"))
vocab = Vocab(config_vocab)
model = Img2SeqModel(config_model, "/tmp/mxlatexfull", vocab)
model.build_pred()
model.restore_session(os.path.join(MODEL_FOLDER, "model.weights/"))
