def test_build_vocab_idx():
inst_file = '/home/peng/Workspace/data/multi30k/train.en'
min_word_count = 2
words_inst = read_instances_from_file(inst_file, 30, False)
words_inst = [w for w in words_inst if w]
word2idx = build_vocab_idx(words_inst, min_word_count)
print(word2idx)
def main():
'''Main Function'''
parser = argparse.ArgumentParser(description='translate.py')
parser.add_argument('-model', required=True, help='Path to model .pt file')
parser.add_argument(
'-src',
required=True,
help='Source sequence to decode (one line per sequence)')
parser.add_argument(
'-vocab',
required=True,
help='Source sequence to decode (one line per sequence)')
parser.add_argument('-output',
default='pred.txt',
help="""Path to output the predictions (each line will
be the decoded sequence""")
parser.add_argument('-beam_size', type=int, default=5, help='Beam size')
parser.add_argument('-batch_size', type=int, default=30, help='Batch size')
parser.add_argument('-n_best',
type=int,
default=1,
help="""If verbose is set, will output the n_best
decoded sentences""")
parser.add_argument('-no_cuda', action='store_true')
opt = parser.parse_args()
opt.cuda = not opt.no_cuda
# Prepare DataLoader
preprocess_data = torch.load(opt.vocab)
preprocess_settings = preprocess_data['settings']
test_src_word_insts = read_instances_from_file(
opt.src, preprocess_settings.max_word_seq_len,
preprocess_settings.keep_case)
test_src_insts = convert_instance_to_idx_seq(
test_src_word_insts, preprocess_data['dict']['src'])
test_data = DataLoader(preprocess_data['dict']['src'],
preprocess_data['dict']['tgt'],
src_insts=test_src_insts,
cuda=opt.cuda,
shuffle=False,
batch_size=opt.batch_size)
translator = Translator(opt)
translator.model.eval()
with open(opt.output, 'w') as f:
for batch in tqdm(test_data,
mininterval=2,
desc=' - (Test)',
leave=False):
all_hyp, all_scores = translator.translate_batch(batch)
for idx_seqs in all_hyp:
for idx_seq in idx_seqs:
pred_line = ' '.join(
[test_data.tgt_idx2word[idx] for idx in idx_seq])
f.write(pred_line + '\n')
print('[Info] Finished.')
def test_read_instances_from_file():
inst_file = '/home/peng/Workspace/data/multi30k/train.en'
max_sent_len = 40
keep_case = True
words_inst = read_instances_from_file(inst_file, max_sent_len, keep_case)
for sent in words_inst:
print(sent)
def main():
parser = argparse.ArgumentParser()
parser.add_argument('-model', required=True, help='Path to model .pt file')
parser.add_argument(
'-src',
required=True,
help='Source sequence to decode (one line per sequence)')
parser.add_argument(
'-vocab',
required=True,
help='Source sequence to decode (one line per sequence)')
parser.add_argument('-output',
default='pred.txt',
help="""Path to output the predictions (each line will
be the decoded sequence""")
parser.add_argument('-beam_size', type=int, default=5, help='Beam size')
parser.add_argument('-batch_size', type=int, default=30, help='Batch size')
parser.add_argument('-n_best',
type=int,
default=1,
help="""If verbose is set, will output the n_best
decoded sentences""")
parser.add_argument('-no_cuda', action='store_true') # 有动作就设置为true
opt = parser.parse_args()
opt.cuda = not opt.no_cuda
# Prepare DataLoader
preprocess_data = torch.load(opt.vocab)
preprocess_settings = preprocess_data['settings']
test_src_word_insts = read_instances_from_file(
opt.src, preprocess_settings.max_word_seq_len,
preprocess_settings.keep_case)
test_src_insts = convert_instance_to_idx_seq(
test_src_word_insts, preprocess_data['dict']['src'])
test_loader = torch.utils.data.DataLoader(TranslationDataset(
src_word2idx=preprocess_data['dict']['src'],
tgt_word2idx=preprocess_data['dict']['tgt'],
src_insts=test_src_insts),
num_workers=2,
batch_size=opt.batch_size,
collate_fn=collate_fn)
translator = Translator(opt)
with open(opt.output, 'w') as f:
for batch in tqdm(test_loader,
mininterval=2,
desc=' - (Test)',
leave=False):
all_hyp, all_scores = translator.translate_batch(*batch)
for hyp_stream in all_hyp:
for hyp in hyp_stream:
pred_sent = ' '.join(
[test_loader.dataset.tgt_idx2word[idx] for idx in hyp])
f.write(pred_sent + '\n')
print('[Info] Finished')
def main():
'''Main Function'''
parser = argparse.ArgumentParser(description='translate.py')
parser.add_argument('-model', required=True,
help='Path to model .pt file')
parser.add_argument('-src', required=True,
help='Source sequence to decode (one line per sequence)')
parser.add_argument('-vocab', required=True,
help='Source sequence to decode (one line per sequence)')
parser.add_argument('-output', default='pred.txt',
help="""Path to output the predictions (each line will
be the decoded sequence""")
parser.add_argument('-beam_size', type=int, default=5,
help='Beam size')
parser.add_argument('-batch_size', type=int, default=30,
help='Batch size')
parser.add_argument('-n_best', type=int, default=1,
help="""If verbose is set, will output the n_best
decoded sentences""")
parser.add_argument('-no_cuda', action='store_true')
opt = parser.parse_args()
opt.cuda = not opt.no_cuda
# Prepare DataLoader
preprocess_data = torch.load(opt.vocab)
preprocess_settings = preprocess_data['settings']
test_src_word_insts = read_instances_from_file(
opt.src,
preprocess_settings.max_word_seq_len,
preprocess_settings.keep_case)
test_src_insts = convert_instance_to_idx_seq(
test_src_word_insts, preprocess_data['dict']['src'])
test_data = DataLoader(
preprocess_data['dict']['src'],
preprocess_data['dict']['tgt'],
src_insts=test_src_insts,
cuda=opt.cuda,
shuffle=False,
batch_size=opt.batch_size)
translator = Translator(opt)
translator.model.eval()
with open(opt.output, 'w') as f:
for batch in tqdm(test_data, mininterval=2, desc=' - (Test)', leave=False):
all_hyp, all_scores = translator.translate_batch(batch)
for idx_seqs in all_hyp:
for idx_seq in idx_seqs:
pred_line = ' '.join([test_data.tgt_idx2word[idx] for idx in idx_seq])
f.write(pred_line + '\n')
print('[Info] Finished.')
def main():
"""Main Function"""
parser = argparse.ArgumentParser(description='translate.py')
parser.add_argument('-model', required=True, help='Path to model .pt file')
parser.add_argument('-src',
required=True,
help='Source sequence to decode '
'(one line per sequence)')
parser.add_argument('-tgt',
required=True,
help='Target sequence to decode '
'(one line per sequence)')
parser.add_argument('-vocab',
required=True,
help='Source sequence to decode '
'(one line per sequence)')
parser.add_argument('-log',
default='translate_log.txt',
help="""Path to log the translation(test_inference)
loss""")
parser.add_argument('-output',
default='pred.txt',
help="""Path to output the predictions (each line will
be the decoded sequence""")
parser.add_argument('-beam_size', type=int, default=5, help='Beam size')
parser.add_argument('-batch_size', type=int, default=2, help='Batch size')
parser.add_argument('-n_best',
type=int,
default=1,
help="""If verbose is set, will output the n_best
decoded sentences""")
parser.add_argument('-no_cuda', action='store_true')
opt = parser.parse_args()
opt.cuda = not opt.no_cuda
# Prepare DataLoader
preprocess_data = torch.load(opt.vocab)
preprocess_settings = preprocess_data['settings']
test_src_word_insts = read_instances_from_file(
opt.src, preprocess_settings.max_word_seq_len,
preprocess_settings.keep_case)
test_tgt_word_insts = read_instances_from_file(
opt.tgt, preprocess_settings.max_word_seq_len,
preprocess_settings.keep_case)
test_src_insts = convert_instance_to_idx_seq(
test_src_word_insts, preprocess_data['dict']['src'])
test_tgt_insts = convert_instance_to_idx_seq(
test_tgt_word_insts, preprocess_data['dict']['tgt'])
test_loader = torch.utils.data.DataLoader(TranslationDataset(
src_word2idx=preprocess_data['dict']['src'],
tgt_word2idx=preprocess_data['dict']['tgt'],
src_insts=test_src_insts,
tgt_insts=test_tgt_insts),
num_workers=2,
batch_size=opt.batch_size,
collate_fn=paired_collate_fn)
translator = Translator(opt)
n_word_total = 0
n_word_correct = 0
with open(opt.output, 'w') as f:
for batch in tqdm(test_loader,
mininterval=2,
desc=' - (Test)',
leave=False):
# all_hyp, all_scores = translator.translate_batch(*batch)
all_hyp, all_scores = translator.translate_batch(
batch[0], batch[1])
# print(all_hyp)
# print(all_hyp[0])
# print(len(all_hyp[0]))
# pad with 0's fit to max_len in insts_group
src_seqs = batch[0]
# print(src_seqs.shape)
tgt_seqs = batch[2]
# print(tgt_seqs.shape)
gold = tgt_seqs[:, 1:]
# print(gold.shape)
max_len = gold.shape[1]
pred_seq = []
for item in all_hyp:
curr_item = item[0]
curr_len = len(curr_item)
# print(curr_len, max_len)
# print(curr_len)
if curr_len < max_len:
diff = max_len - curr_len
curr_item.extend([0] * diff)
else: # TODO: why does this case happen?
curr_item = curr_item[:max_len]
pred_seq.append(curr_item)
pred_seq = torch.LongTensor(np.array(pred_seq))
pred_seq = pred_seq.view(opt.batch_size * max_len)
n_correct = cal_performance(pred_seq, gold)
non_pad_mask = gold.ne(Constants.PAD)
n_word = non_pad_mask.sum().item()
n_word_total += n_word
n_word_correct += n_correct
# trs_log = "transformer_loss: {} |".format(trs_loss)
#
# with open(opt.log, 'a') as log_tf:
# log_tf.write(trs_log + '\n')
count = 0
for pred_seqs in all_hyp:
src_seq = src_seqs[count]
tgt_seq = tgt_seqs[count]
for pred_seq in pred_seqs:
src_line = ' '.join([
test_loader.dataset.src_idx2word[idx]
for idx in src_seq.data.cpu().numpy()
])
tgt_line = ' '.join([
test_loader.dataset.tgt_idx2word[idx]
for idx in tgt_seq.data.cpu().numpy()
])
pred_line = ' '.join([
test_loader.dataset.tgt_idx2word[idx]
for idx in pred_seq
])
f.write(
"\n ---------------------------------------------------------------------------------------------------------------------------------------------- \n"
)
f.write("\n [src] " + src_line + '\n')
f.write("\n [tgt] " + tgt_line + '\n')
f.write("\n [pred] " + pred_line + '\n')
count += 1
accuracy = n_word_correct / n_word_total
accr_log = "accuracy: {} |".format(accuracy)
# print(accr_log)
with open(opt.log, 'a') as log_tf:
log_tf.write(accr_log + '\n')
print('[Info] Finished.')
def main():
"""Main Function"""
parser = argparse.ArgumentParser(description="translate.py")
parser.add_argument("-model", required=True, help="Path to model .pt file")
parser.add_argument(
"-src",
required=True,
help="Source sequence to decode (one line per sequence)")
parser.add_argument(
"-vocab",
required=True,
help="Source sequence to decode (one line per sequence)")
parser.add_argument("-output",
default="pred.txt",
help="""Path to output the predictions (each line will
be the decoded sequence""")
parser.add_argument("-beam_size", type=int, default=5, help="Beam size")
parser.add_argument("-batch_size", type=int, default=30, help="Batch size")
parser.add_argument("-n_best",
type=int,
default=1,
help="""If verbose is set, will output the n_best
decoded sentences""")
parser.add_argument("-no_cuda", action="store_true")
opt = parser.parse_args()
opt.cuda = not opt.no_cuda
# Prepare DataLoader
preprocess_data = torch.load(opt.vocab)
preprocess_settings = preprocess_data["settings"]
test_src_word_insts = read_instances_from_file(
opt.src, preprocess_settings.max_word_seq_len,
preprocess_settings.keep_case)
test_src_insts = convert_instance_to_idx_seq(
test_src_word_insts, preprocess_data["dict"]["src"])
test_loader = torch.utils.data.DataLoader(TranslationDataset(
src_word2idx=preprocess_data["dict"]["src"],
tgt_word2idx=preprocess_data["dict"]["tgt"],
src_insts=test_src_insts),
num_workers=2,
batch_size=opt.batch_size,
collate_fn=collate_fn)
translator = Translator(opt)
with open(opt.output, "w") as f:
for batch in tqdm(test_loader,
mininterval=2,
desc=" - (Test)",
leave=False):
all_hyp, all_scores = translator.translate_batch(*batch)
for idx_seqs in all_hyp:
for idx_seq in idx_seqs:
pred_line = " ".join([
test_loader.dataset.tgt_idx2word[idx]
for idx in idx_seq
])
f.write(pred_line + "\n")
print("[Info] Finished.")
def main():
'''Main Function'''
parser = argparse.ArgumentParser(description='translate.py')
parser.add_argument('-model', required=True, help='Path to model .pt file')
parser.add_argument(
'-src',
required=True,
help='Source sequence to decode (one line per sequence)')
parser.add_argument('-vocab',
required=True,
help='preprocess file to provide vocabulary')
parser.add_argument('-output',
default='pred.txt',
help="""Path to output the predictions (each line will
be the decoded sequence""")
parser.add_argument('-beam_size', type=int, default=5, help='Beam size')
parser.add_argument('-batch_size', type=int, default=30, help='Batch size')
parser.add_argument('-lambda_1',
type=float,
default=2 / 3,
help='diversity factor for hamming diversity')
parser.add_argument('-lambda_2',
type=float,
default=2 / 3,
help='diversity factor for bi-gram diversity')
parser.add_argument('-lambda_3',
type=float,
default=2 / 3,
help='diversity factor for tri-gram diversity')
parser.add_argument('-no_cuda', action='store_true')
opt = parser.parse_args()
opt.cuda = not opt.no_cuda
# Prepare DataLoader
preprocess_data = torch.load(opt.vocab)
preprocess_settings = preprocess_data['settings']
test_src_word_insts = read_instances_from_file(
opt.src, preprocess_settings.max_word_seq_len,
preprocess_settings.keep_case)
test_src_insts = convert_instance_to_idx_seq(
test_src_word_insts, preprocess_data['dict']['src'])
test_data = DataLoader(preprocess_data['dict']['src'],
preprocess_data['dict']['tgt'],
src_insts=test_src_insts,
cuda=opt.cuda,
shuffle=False,
batch_size=opt.batch_size)
translator = Translator_idbs(opt)
translator.model.eval()
print('[Info] Start translating...')
f = open(opt.output, 'w')
for batch in tqdm(test_data, mininterval=2, desc=' - (Test)',
leave=False):
all_hyp = translator.translate_batch(batch)
for idx_seq in all_hyp:
pred_line = ' '.join(
[test_data.tgt_idx2word[idx] for idx in idx_seq]) #转化成单词拼接起来
f.write(pred_line + '\n')
f.flush()
f.close()
print('[Info] Finished.')
def main():
'''Main Function'''
parser = argparse.ArgumentParser(description='translate.py')
parser.add_argument('-model', required=True, help='Path to model .pt file')
parser.add_argument(
'-src',
required=True,
help='Source sequence to decode (one line per sequence)')
parser.add_argument(
'-target',
required=True,
help='Target sequence to decode (one line per sequence)')
parser.add_argument(
'-vocab',
required=True,
help='Source sequence to decode (one line per sequence)')
parser.add_argument('-output',
default='pred.txt',
help="""Path to output the predictions (each line will
be the decoded sequence""")
parser.add_argument('-beam_size', type=int, default=5, help='Beam size')
parser.add_argument('-batch_size', type=int, default=30, help='Batch size')
parser.add_argument('-n_best',
type=int,
default=1,
help="""If verbose is set, will output the n_best
decoded sentences""")
parser.add_argument('-no_cuda', action='store_true')
parser.add_argument('-prune', action='store_true')
parser.add_argument('-prune_alpha', type=float, default=0.1)
parser.add_argument('-load_mask', type=str, default=None)
opt = parser.parse_args()
opt.cuda = not opt.no_cuda
# Prepare DataLoader
preprocess_data = torch.load(opt.vocab)
preprocess_settings = preprocess_data['settings']
refs = read_instances_from_file(opt.target,
preprocess_settings.max_word_seq_len,
preprocess_settings.keep_case)
test_src_word_insts = read_instances_from_file(
opt.src, preprocess_settings.max_word_seq_len,
preprocess_settings.keep_case)
test_src_insts = convert_instance_to_idx_seq(
test_src_word_insts, preprocess_data['dict']['src'])
test_loader = torch.utils.data.DataLoader(TranslationDataset(
src_word2idx=preprocess_data['dict']['src'],
tgt_word2idx=preprocess_data['dict']['tgt'],
src_insts=test_src_insts,
),
num_workers=2,
batch_size=opt.batch_size,
collate_fn=collate_fn)
translator = Translator(opt)
preds = []
preds_text = []
for batch in tqdm(test_loader,
mininterval=2,
desc=' - (Test)',
leave=False):
all_hyp, all_scores = translator.translate_batch(*batch)
for idx_seqs in all_hyp:
for idx_seq in idx_seqs:
sent = ' '.join(
[test_loader.dataset.tgt_idx2word[idx] for idx in idx_seq])
sent = sent.split("</s>")[0].strip()
sent = sent.replace("▁", " ")
preds_text.append(sent.strip())
preds.append(
[test_loader.dataset.tgt_idx2word[idx] for idx in idx_seq])
with open(opt.output, 'w') as f:
f.write('\n'.join(preds_text))
from evaluator import BLEUEvaluator
scorer = BLEUEvaluator()
length = min(len(preds), len(refs))
score = scorer.evaluate(refs[:length], preds[:length])
print(score)
def main():
'''Main Function'''
parser = argparse.ArgumentParser(description='sum_file.py')
parser.add_argument('-model', required=True,
help='Path to model .pt file')
parser.add_argument('-src', required=True,
help='Source sequence to decode (one line per sequence)')
parser.add_argument('-vocab', required=True,
help='Source sequence to decode (one line per sequence)')
parser.add_argument('-output', default='pred.txt',
help="""Path to output the predictions (each line will
be the decoded sequence""")
parser.add_argument('-beam_size', type=int, default=5,
help='Beam size')
parser.add_argument('-batch_size', type=int, default=30,
help='Batch size')
parser.add_argument('-n_best', type=int, default=1,
help="""If verbose is set, will output the n_best
decoded sentences""")
parser.add_argument('-no_cuda', action='store_true')
opt = parser.parse_args()
opt.cuda = not opt.no_cuda
# Prepare DataLoader
preprocess_data = torch.load(opt.vocab)
preprocess_settings = preprocess_data['settings']
test_src_word_insts = read_instances_from_file(
opt.src,
preprocess_settings.max_word_seq_len,
preprocess_settings.keep_case,
preprocess_settings.mode)
test_src_insts = convert_instance_to_idx_seq(
test_src_word_insts, preprocess_data['dict']['src'])
# prepare model
device = torch.device('cuda' if opt.cuda else 'cpu')
checkpoint = torch.load(opt.model)
model_opt = checkpoint['settings']
model_opt.bidirectional = True
encoder = EncoderRNN(model_opt.src_vocab_size, model_opt.max_token_seq_len, model_opt.d_model,
bidirectional=model_opt.bidirectional, variable_lengths=True)
decoder = DecoderRNN(model_opt.tgt_vocab_size, model_opt.max_token_seq_len, model_opt.d_model * 2 if model_opt.bidirectional else model_opt.d_model,
n_layers=model_opt.n_layer, dropout_p=model_opt.dropout, use_attention=True, bidirectional=model_opt.bidirectional,
eos_id=Constants.BOS, sos_id=Constants.EOS)
model = Seq2seq(encoder, decoder).to(device)
model = nn.DataParallel(model) # using Dataparallel because training used
model.load_state_dict(checkpoint['model'])
print('[Info] Trained model state loaded.')
predictor = Predictor(model, preprocess_data['dict']['tgt'])
with open(opt.output, 'w') as f:
for src_seq in tqdm(test_src_insts, mininterval=2, desc=' - (Test)', leave=False):
pred_line = ' '.join(predictor.predict(src_seq))
f.write(pred_line + '\n')
print('[Info] Finished.')
def main():
'''Main Function'''
parser = argparse.ArgumentParser(description='translate.py')
parser.add_argument('-model', required=True, help='Path to model .pt file')
parser.add_argument(
'-src',
required=True,
help='Source sequence to decode (one line per sequence)')
parser.add_argument(
'-vocab',
required=True,
help='Source sequence to decode (one line per sequence)')
parser.add_argument('-output',
default='pred.txt',
help="""Path to output the predictions (each line will
be the decoded sequence""")
parser.add_argument('-beam_size', type=int, default=5, help='Beam size')
parser.add_argument('-batch_size', type=int, default=30, help='Batch size')
parser.add_argument('-n_best',
type=int,
default=1,
help="""If verbose is set, will output the n_best
decoded sentences""")
parser.add_argument('-no_cuda', action='store_true')
opt = parser.parse_args()
opt.cuda = not opt.no_cuda
# Prepare DataLoader
preprocess_data = torch.load(opt.vocab)
preprocess_settings = preprocess_data['settings']
test_src_word_insts = read_instances_from_file(
opt.src, preprocess_settings.max_word_seq_len,
preprocess_settings.keep_case)
test_src_insts = convert_instance_to_idx_seq(
test_src_word_insts, preprocess_data['dict']['src'])
# pdb.set_trace()
# (Pdb) print(opt)
# Namespace(batch_size=30, beam_size=5, cuda=True, model='trained.chkpt',
# n_best=1, no_cuda=False, output='pred.txt', src='data/multi30k/test.en.atok',
# vocab='data/multi30k.atok.low.pt')
test_loader = torch.utils.data.DataLoader(TranslationDataset(
src_word2idx=preprocess_data['dict']['src'],
tgt_word2idx=preprocess_data['dict']['tgt'],
src_insts=test_src_insts),
num_workers=2,
batch_size=opt.batch_size,
collate_fn=collate_fn)
translator = Translator(opt)
with open(opt.output, 'w') as f:
for batch in tqdm(test_loader,
mininterval=2,
desc=' - (Test)',
leave=False):
all_hyp, all_scores = translator.translate_batch(*batch)
for idx_seqs in all_hyp:
for idx_seq in idx_seqs:
pred_line = ' '.join([
test_loader.dataset.tgt_idx2word[idx]
for idx in idx_seq
])
f.write(pred_line + '\n')
print('[Info] Finished.')
def prep(train_src,
train_tgt,
valid_src,
valid_tgt,
save_data,
max_word_seq_len=50,
min_word_count=5,
keep_case=True,
share_vocab=True,
vocab=None):
max_token_seq_len = max_word_seq_len + 2 # include the <s> and </s>
# opt = Settings(train_src, train_tgt, valid_src, valid_tgt, save_data, max_word_seq_len, min_word_count, keep_case, share_vocab, vocab)
# # Training set
# train_src_word_insts = prepro.read_instances_from_file(
# train_src, max_word_seq_len, keep_case)
# train_tgt_word_insts = prepro.read_instances_from_file(
# train_tgt, max_word_seq_len, keep_case)
# if len(train_src_word_insts) != len(train_tgt_word_insts):
# print('[Warning] The training instance count is not equal.')
# min_inst_count = min(len(train_src_word_insts), len(train_tgt_word_insts))
# train_src_word_insts = train_src_word_insts[:min_inst_count]
# train_tgt_word_insts = train_tgt_word_insts[:min_inst_count]
# #- Remove empty instances
# train_src_word_insts, train_tgt_word_insts = list(zip(*[
# (s, t) for s, t in zip(train_src_word_insts, train_tgt_word_insts) if s and t]))
# # Validation set
# valid_src_word_insts = prepro.read_instances_from_file(
# valid_src, max_word_seq_len, keep_case)
# valid_tgt_word_insts = prepro.read_instances_from_file(
# valid_tgt, max_word_seq_len, keep_case)
# if len(valid_src_word_insts) != len(valid_tgt_word_insts):
# print('[Warning] The validation instance count is not equal.')
# min_inst_count = min(len(valid_src_word_insts), len(valid_tgt_word_insts))
# valid_src_word_insts = valid_src_word_insts[:min_inst_count]
# valid_tgt_word_insts = valid_tgt_word_insts[:min_inst_count]
# #- Remove empty instances
# valid_src_word_insts, valid_tgt_word_insts = list(zip(*[
# (s, t) for s, t in zip(valid_src_word_insts, valid_tgt_word_insts) if s and t]))
src_word_insts = prepro.read_instances_from_file(train_src,
max_word_seq_len,
keep_case)
tgt_word_insts = prepro.read_instances_from_file(train_tgt,
max_word_seq_len,
keep_case)
if len(train_src_word_insts) != len(train_tgt_word_insts):
print('[Warning] The training instance count is not equal.')
min_inst_count = min(len(train_src_word_insts),
len(train_tgt_word_insts))
train_src_word_insts = train_src_word_insts[:min_inst_count]
train_tgt_word_insts = train_tgt_word_insts[:min_inst_count]
#- Remove empty instances
train_src_word_insts, train_tgt_word_insts = list(
zip(*[(s, t)
for s, t in zip(train_src_word_insts, train_tgt_word_insts)
if s and t]))
# Build vocabulary
if vocab:
predefined_data = torch.load(vocab)
assert 'dict' in predefined_data
print('[Info] Pre-defined vocabulary found.')
src_word2idx = predefined_data['dict']['src']
tgt_word2idx = predefined_data['dict']['tgt']
else:
if share_vocab:
print('[Info] Build shared vocabulary for source and target.')
word2idx = prepro.build_vocab_idx(
train_src_word_insts + train_tgt_word_insts, min_word_count)
src_word2idx = tgt_word2idx = word2idx
else:
print('[Info] Build vocabulary for source.')
src_word2idx = prepro.build_vocab_idx(train_src_word_insts,
min_word_count)
print('[Info] Build vocabulary for target.')
tgt_word2idx = prepro.build_vocab_idx(train_tgt_word_insts,
min_word_count)
# word to index
print('[Info] Convert source word instances into sequences of word index.')
train_src_insts = prepro.convert_instance_to_idx_seq(
train_src_word_insts, src_word2idx)
valid_src_insts = prepro.convert_instance_to_idx_seq(
valid_src_word_insts, src_word2idx)
print('[Info] Convert target word instances into sequences of word index.')
train_tgt_insts = prepro.convert_instance_to_idx_seq(
train_tgt_word_insts, tgt_word2idx)
valid_tgt_insts = prepro.convert_instance_to_idx_seq(
valid_tgt_word_insts, tgt_word2idx)
data = {
'settings': max_token_seq_len,
'dict': {
'src': src_word2idx,
'tgt': tgt_word2idx
},
'train': {
'src': train_src_insts,
'tgt': train_tgt_insts
},
'valid': {
'src': valid_src_insts,
'tgt': valid_tgt_insts
}
}
print('[Info] Dumping the processed data to pickle file', save_data)
torch.save(data, save_data)
print('[Info] Finish.')
def main():
'''Main Function'''
'''
这个模型是从英语到德语.
'''
parser = argparse.ArgumentParser(description='translate.py')
parser.add_argument('-model', required=False,
help='Path to model .pt file')
parser.add_argument('-src', required=False,
help='Source sequence to decode (one line per sequence)')
parser.add_argument('-vocab', required=False,
help='Source sequence to decode (one line per sequence)')
parser.add_argument('-output', default='2',
help="""Path to output the predictions (each line will
be the decoded sequence""")
parser.add_argument('-beam_size', type=int, default=5,
help='Beam size')
parser.add_argument('-batch_size', type=int, default=30,
help='Batch size')
parser.add_argument('-n_best', type=int, default=1,
help="""If verbose is set, will output the n_best
decoded sentences""")
parser.add_argument('-no_cuda', action='store_true')
#-vocab data/multi30k.atok.low.pt
opt = parser.parse_args()
opt.cuda = not opt.no_cuda
opt.cuda=False
opt.model='trained.chkpt'
opt.src='1'
opt.vocab='multi30k.atok.low.pt'
# Prepare DataLoader
preprocess_data = torch.load(opt.vocab)
tmp1=preprocess_data['dict']['src']
tmp2=preprocess_data['dict']['tgt']
with open('55','w')as f:
f.write(str(tmp1))
with open('66','w',encoding='utf-8')as f:
f.write(str(tmp2))
preprocess_settings = preprocess_data['settings']
test_src_word_insts = read_instances_from_file(
opt.src,
preprocess_settings.max_word_seq_len,
preprocess_settings.keep_case)
test_src_insts = convert_instance_to_idx_seq(
test_src_word_insts, preprocess_data['dict']['src'])
test_loader = torch.utils.data.DataLoader(
TranslationDataset(
src_word2idx=preprocess_data['dict']['src'],
tgt_word2idx=preprocess_data['dict']['tgt'],
src_insts=test_src_insts),
num_workers=2,
batch_size=opt.batch_size,
collate_fn=collate_fn)
translator = Translator(opt)
with open(opt.output, 'w') as f:
for batch in test_loader:
all_hyp, all_scores = translator.translate_batch(*batch)
for idx_seqs in all_hyp:
for idx_seq in idx_seqs:
print(idx_seq)
pred_line = ' '.join([test_loader.dataset.tgt_idx2word[idx] for idx in idx_seq]) # 把id转化会text
f.write(pred_line + '\n')
print('[Info] Finished.')
parser.add_argument('-batch_size', type=int, default=30, help='Batch size')
parser.add_argument('-n_best',
type=int,
default=1,
help="""If verbose is set, will output the n_best
decoded sentences""")
parser.add_argument('-no_cuda', action='store_true')
opt = parser.parse_args()
opt.cuda = not opt.no_cuda
# Prepare DataLoader
preprocess_data = torch.load(opt.vocab)
preprocess_settings = preprocess_data['settings']
test_src_word_insts = read_instances_from_file(
opt.src, preprocess_settings.max_word_seq_len,
preprocess_settings.keep_case)
test_src_insts = convert_instance_to_idx_seq(
test_src_word_insts, preprocess_data['dict']['src'])
test_loader = torch.utils.data.DataLoader(TranslationDataset(
src_word2idx=preprocess_data['dict']['src'],
tgt_word2idx=preprocess_data['dict']['tgt'],
src_insts=test_src_insts),
num_workers=2,
batch_size=opt.batch_size,
collate_fn=collate_fn)
translator = Translator(opt)
with open(opt.output, 'w') as f:
def main():
'''Main Function'''
parser = argparse.ArgumentParser(description='translate.py')
parser.add_argument('-image_dir', required=True, help='image directory')
parser.add_argument('-model', required=True, help='Path to model .pt file')
parser.add_argument('-img',
required=True,
help='Source image to decode (one line per sequence)')
parser.add_argument(
'-src',
required=True,
help='Source sequence to decode (one line per sequence)')
parser.add_argument(
'-vocab',
required=True,
help='Source sequence to decode (one line per sequence)')
parser.add_argument('-output',
default='pred.txt',
help="""Path to output the predictions (each line will
be the decoded sequence""")
parser.add_argument('-beam_size', type=int, default=5, help='Beam size')
parser.add_argument('-batch_size', type=int, default=30, help='Batch size')
parser.add_argument('-n_best',
type=int,
default=1,
help="""If verbose is set, will output the n_best
decoded sentences""")
parser.add_argument('-no_cuda', action='store_true')
parser.add_argument('-crop_size',
type=int,
default=224,
help='size for randomly cropping images')
opt = parser.parse_args()
opt.cuda = not opt.no_cuda
# Prepare DataLoader
preprocess_data = torch.load(opt.vocab)
preprocess_settings = preprocess_data['settings']
test_img_insts = read_instances_from_file(
opt.img, preprocess_settings.max_word_seq_len)
test_src_word_insts = read_instances_from_file(
opt.src, preprocess_settings.max_word_seq_len)
test_src_insts = convert_instance_to_idx_seq(
test_src_word_insts, preprocess_data['dict']['src'])
# Image Preprocessing
transform = transforms.Compose([
transforms.RandomResizedCrop(opt.crop_size),
transforms.RandomHorizontalFlip(),
transforms.ToTensor(),
transforms.Normalize((0.485, 0.456, 0.406), (0.229, 0.224, 0.225))
])
test_data = DataLoader(transform,
opt.image_dir,
preprocess_data['dict']['src'],
preprocess_data['dict']['tgt'],
image_insts=test_img_insts,
src_insts=test_src_insts,
cuda=opt.cuda,
shuffle=False,
batch_size=1)
translator = Translator(opt)
translator.model.eval()
inv_map = {v: k for k, v in preprocess_data['dict']['tgt'].items()}
target = open(opt.output, "wb")
for batch in tqdm(test_data, mininterval=2, desc=' - (Test)',
leave=False):
seq = translator.translate_batch(batch)
if seq is None:
line = "None\n"
target.write(line.encode("utf-8"))
continue
seq = seq[1:-1]
line = [inv_map[val] for val in seq]
line = " ".join(line) + "\n"
target.write(line.encode("utf-8"))
target.close()
print('[Info] Finished.')
def main():
parser = argparse.ArgumentParser(description='translate.py')
parser.add_argument('-model',
default='trained.chkpt',
help='Path to model .pt file')
parser.add_argument(
'-src',
default='data/multi30k/test.en.atok',
help='Source sequence to decode (one line per sequence)')
parser.add_argument(
'-ctx',
required=False,
default="",
help='Context sequence to decode (one line per sequence)')
parser.add_argument('-vocab',
default='data/multi30k.atok.low.pt',
help='Data that contains the source vocabulary')
parser.add_argument('-output',
default='pred.txt',
help="""Path to output the predictions (each line will
be the decoded sequence""")
parser.add_argument('-beam_size', type=int, default=5, help='Beam size')
parser.add_argument('-batch_size', type=int, default=30, help='Batch size')
parser.add_argument('-n_best',
type=int,
default=1,
help="""If verbose is set, will output the n_best
decoded sentences""")
parser.add_argument('-no_cuda', action='store_false')
parser.add_argument('-max_token_seq_len', type=int, default=100)
opt = parser.parse_args()
opt.cuda = not opt.no_cuda
# Prepare DataLoader
preprocess_data = torch.load(opt.vocab)
preprocess_settings = preprocess_data['settings']
test_src_word_insts = read_instances_from_file(
opt.src, opt.max_token_seq_len, preprocess_settings.keep_case)
test_src_insts = convert_instance_to_idx_seq(
test_src_word_insts, preprocess_data['dict']['src'])
if opt.ctx:
from preprocess_ctx import read_instances_from_file as read_instances_from_file_ctx
test_ctx_word_insts = read_instances_from_file_ctx(
opt.ctx,
opt.max_token_seq_len,
preprocess_settings.keep_case,
is_ctx=True)
test_ctx_insts = convert_instance_to_idx_seq(
test_ctx_word_insts, preprocess_data['dict']['src'])
test_data = DataLoader(preprocess_data['dict']['src'],
preprocess_data['dict']['tgt'],
src_insts=test_src_insts,
ctx_insts=(test_ctx_insts if opt.ctx else None),
cuda=opt.cuda,
shuffle=False,
batch_size=opt.batch_size,
is_train=False)
translator = Translator(opt)
translator.model.eval()
with open(opt.output, 'w') as f:
for batch in tqdm(test_data,
mininterval=2,
desc=' - (Test)',
leave=False):
print(---------1111111111)
all_hyp, all_scores = translator.translate_batch(*batch)
print(---------2222222222)
for idx_seqs in all_hyp:
for idx_seq in idx_seqs:
if idx_seq[-1] == 3: # if last word is EOS
idx_seq = idx_seq[:-1]
pred_line = ' '.join(
[test_data.tgt_idx2word[int(idx)] for idx in idx_seq])
f.write(pred_line + '\n')
print("end")
print('[Info] Finished.')
