def main():
opts = get_test_args()
print("load data ...")
# DHA config
coll_name = 'default'
dic_path = '/hanmail/projects/dha/dha_resources-2.9.41-default/'
dha = pydha.Index()
dha.init(dic_path, coll_name)
converter = DataConverter(dha, 'data')
print("load model ...")
model = ELMo(opts, [converter.word_vocab_size, converter.char_vocab_size])
model.load_state_dict(torch.load('model.pt', map_location='cpu'))
loss = torch.nn.CrossEntropyLoss()
model.eval()
print("Evaluating ...")
with torch.no_grad():
while True:
sentence = input()
word_idx, char_idx, parsed_word, parsed_pos, cpos, clen = converter.get_id_sequence(
sentence)
pred = model(word_idx, char_idx)
print(converter.id2word[torch.argmax(pred[-1])])
('EM', results['EM'])]
if args.use_squad_v2:
results_list.append(('AvNA', results['AvNA']))
results = OrderedDict(results_list)
# Log to console
results_str = ', '.join(f'{k}: {v:05.2f}' for k, v in results.items())
log.info(f'{args.split.title()} {results_str}')
# Log to TensorBoard
tbx = SummaryWriter(args.save_dir)
util.visualize(tbx,
pred_dict=pred_dict,
eval_path=eval_file,
step=0,
split=args.split,
num_visuals=args.num_visuals)
# Write submission file
sub_path = join(args.save_dir, args.split + '_' + args.sub_file)
log.info(f'Writing submission file to {sub_path}...')
with open(sub_path, 'w', newline='', encoding='utf-8') as csv_fh:
csv_writer = csv.writer(csv_fh, delimiter=',')
csv_writer.writerow(['Id', 'Predicted'])
for uuid in sorted(sub_dict):
csv_writer.writerow([uuid, sub_dict[uuid]])
if __name__ == '__main__':
main(get_test_args())
log.info('Args: {}'.format(dumps(vars(args), indent=4, sort_keys=True)))
device, gpu_ids = util.get_available_devices()
args.batch_size *= max(1, len(gpu_ids))
# Get embeddings
log.info('Loading embeddings...')
word_vectors = util.torch_from_json(args.word_emb_file)
# Get model
log.info('Building model...')
model = BiDAF(word_vectors=word_vectors, hidden_size=args.hidden_size)
model = nn.DataParallel(model, gpu_ids)
log.info('Loading checkpoint from {}...'.format(args.load_path))
model = util.load_model(model, args.load_path, gpu_ids, return_step=False)
model = model.to(device)
model.eval()
y_pred = model(cw_idxs, qn_idxs)
return y_pred
if __name__ == '__main__':
context = input("Enter the context: ")
question = input("Enter a question: ")
data = [context, question]
word2idx_dict = json_load(".data/word2idx.json")
char2idx_dict = json_load(".data/char2idx.json")
is_test = True
context_idxs, context_char_idxs, ques_idxs, ques_char_idxs = convert_to_features(
get_test_args(), data, word2idx_dict, char2idx_dict, is_test)
predict(get_test_args(), context_idxs, ques_idxs)
import pandas as pd
from tqdm import tqdm
import numpy as np
import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
import torch.optim.lr_scheduler as sched
import torch.utils.data as data
from torch.utils.data import DataLoader, TensorDataset
from torch import Tensor
if __name__ == '__main__':
args = get_test_args()
# Set up logging
args.save_dir = util.get_save_dir(args.save_dir, args.name, subdir='test')
log = util.get_logger(args.save_dir, args.name)
device, gpu_ids = util.get_available_devices()
args.batch_size *= max(1, len(gpu_ids))
log.info(f'Args: {dumps(vars(args), indent=4, sort_keys=True)}')
# Load the checkpoint if given as parameter
if args.load_path:
log.info(f'Loading checkpoint from {args.load_path}...')
model = util.load_model(args.load_path)
else:
csv_writer.writerow([uuid, sub_dict[uuid]])
return results['F1']
if __name__ == '__main__':
max_steps = 2
substitute_F1_values = []
add_F1_values = []
delete_F1_values = []
for nb in range(0, max_steps):
proposed_actions = ('delete', nb)
delete_F1_values.append(main(get_test_args(),
actions=proposed_actions))
#
#
#
# #proposed_actions = ('delete', nb)
# #delete_F1_values.append(main(get_test_args(), actions = proposed_actions))
#
# print("Computing add2")
# for nb in range(0, max_steps):
# proposed_actions = ('add2', nb)
# add_F1_values.append(main(get_test_args(), actions=proposed_actions))
# print(">>>", nb, " : ", add_F1_values)
# print("add OK")
# print("result for ",proposed_actions[0], ": ", substitute_F1_values)
