model.load_state_dict(torch.load(PATH, map_location=device))
model = model.to(device)
print(model)
for i in range(len(labels)):
s1_embed, s1_len = get_batch_from_idx(s1[i].split(), embeddings, config)
s2_embed, s2_len = get_batch_from_idx(s2[i].split(), embeddings, config)
u = torch.sum(s1_embed,0).to(device)
v = torch.sum(s1_embed,0).to(device)
feats = torch.cat((u, v, torch.abs(u- v), u*v), 0).to(device)
with torch.no_grad():
out = model.forward(feats).to(device)
pred = torch.max(out,0)[1]
if label[i] == 0:
tot1 += 1
if label
# s1_embed, s1_len = get_batch_from_idx(s1[i].split(), embeddings, config)
# s2_embed, s2_len = get_batch_from_idx(s2[i].split(), embeddings, config)
# s1_embed = s1_embed.expand(1,s1_len, -1).transpose(0,1)
# s2_embed = s2_embed.expand(1,s2_len, -1).transpose(0,1)
# s1_len = torch.as_tensor(s1_len, dtype=torch.int64).expand(1)
# s2_len = torch.as_tensor(s2_len, dtype=torch.int64).expand(1)
print("\n\n Hi I am the " + str(FLAGS.model_name) + " model...!!")
print("\n Hhhhmmmmm....lemme think...\n")
if config['model_name'] == 'base':
model = Classifier(config).to(device)
PATH = FLAGS.model_path
model.load_state_dict(torch.load(PATH, map_location=device))
model = model.to(device)
u = torch.sum(s1_embed, 0).to(device)
v = torch.sum(s1_embed, 0).to(device)
feats = torch.cat((u, v, torch.abs(u - v), u * v), 0).to(device)
with torch.no_grad():
out = model.forward(feats).to(device)
pred = torch.max(out, 0)[1]
else:
if config['model_name'] == 'lstm':
PATH = FLAGS.model_path
elif config['model_name'] == 'bilstm':
PATH = FLAGS.model_path
elif config['model_name'] == 'bilstm_pool':
PATH = FLAGS.model_path
model = LSTM_main(config).to(device)
model.load_state_dict(torch.load(PATH, map_location=device))
model = model.to(device)
