def predict_cnn(config):
# load tokenizer and torchtext Field
pickle_tokenizer = open('pickles/tokenizer.pickle', 'rb')
cohesion_scores = pickle.load(pickle_tokenizer)
tokenizer = LTokenizer(scores=cohesion_scores)
pickle_vocab = open('pickles/text.pickle', 'rb')
text = pickle.load(pickle_vocab)
model = CNN(config)
model.load_state_dict(torch.load(config.save_model))
model.to(device)
model.eval()
tokenized = tokenizer.tokenize(config.input)
min_len = config.filter_sizes[-1]
# if user's input sentence is shorter than the largest filter size, add pad tokens to input sentence
if len(tokenized) < min_len:
tokenized += ['<pad>'] * (min_len - len(tokenized))
indexed = [text.vocab.stoi[token] for token in tokenized]
length = [len(indexed)]
tensor = torch.LongTensor(indexed).to(device)
tensor = tensor.unsqueeze(1)
length_tensor = torch.LongTensor(length)
prediction = torch.sigmoid(model(tensor, length_tensor))
label = torch.round(prediction)
if label == 1:
label = 'Positive'
else:
label = 'Negative'
sentiment_percent = prediction.item()
print(f'[in] >> {config.input}')
print(f'[out] >> {sentiment_percent*100:.2f} % : {label}')
num_input_channels = next(iter(trainer.train_dataloader))[0].shape[2]
encoder_params = CNN.generate_params()
rnn_params = RNN.generate_params()
model = CRNN(input_len=input_len,
output_len=output_len,
num_input_channels=num_input_channels,
encoder_params=encoder_params,
rnn_params=rnn_params)
elif args.model_type == 'mlp':
input_len = reduce(lambda x, y: x * y,
next(iter(trainer.train_dataloader))[0].shape[1:])
params = MLP.generate_params()
model = MLP(input_len=input_len,
output_len=output_len,
params=params,
**params)
else:
raise ValueError('"{}" is not a valid model.'.format(args.model_type))
model = model.to(device)
# Train Network
trainer.train(model=model,
min_epochs=args.min_epochs,
max_epochs=args.max_epochs,
patience=args.patience,
verbose=args.verbose,
test_subject_id=test_subject_id,
validation_subject_id=validation_subject_id)
print('\n' + '#' * 50 + '\n')
if __name__ == '__main__':
if not args.debug_mode:
import wandb
wandb.init(project=args.project,
name=args.name,
tags=args.tags,
config=args)
train_data = dataset.MDB_Dataset('MusicDelta_80sRock')
test_data = dataset.MDB_Dataset('MusicDelta_80sRock')
else:
train_data = dataset.MDB_Dataset('MusicDelta_80sRock')
test_data = dataset.MDB_Dataset('MusicDelta_80sRock')
print_args(args)
# get_model
if args.model_arc == 'CNN':
model = CNN(hidden_channel_num=10, output_number=4)
else:
raise AssertionError
model = model.to(args.device)
optimizer = torch.optim.Adam(model.parameters(), lr=args.learning_rate)
if not args.debug_mode:
wandb.watch(model)
trainer = Trainer(model, optimizer, args.device, args.debug_mode,
args.test_per_epoch, args.num_epochs, args.weight_path,
train_data, test_data)
trainer.train()
