device = torch.device('cpu')
from eval_utils import *
warnings.simplefilter("ignore")
from tqdm import tqdm
config = configs.CONFIG_MAP['mlp_mfcc']
model = config['model'](linear_layer_size=config['linear_layer_size'],
filter_sizes=config['filter_sizes'])
model.set_device(device)
model.to(device)
checkpoint_dir = '../../checkpoints/comparisons/baseline_mfcc_trained_on_audioset'
if os.path.exists(checkpoint_dir):
torch_utils.load_checkpoint(checkpoint_dir + '/best.pth.tar', model)
else:
print("Checkpoint not found")
model.eval()
swb_val_distractor_df = pd.read_csv(
'../../data/switchboard/annotations/clean_switchboard_val_distractor_annotations.csv'
)
swb_test_distractor_df = pd.read_csv(
'../../data/switchboard/annotations/clean_switchboard_test_distractor_annotations.csv'
)
swb_val_df = pd.read_csv(
'../../data/switchboard/annotations/clean_switchboard_val_laughter_annotations.csv'
)
enc = Encoder(INPUT_DIM, HID_DIM, ENC_DROPOUT)
dec = EmbeddingDecoder(OUTPUT_DIM, HID_DIM, DEC_EMB_DIM,
output_embedding_matrix, word_output_vocab, DEC_DROPOUT,
device)
model = Seq2Seq(enc, dec, device, max_label_len).to(device)
torch_utils.count_parameters(model)
model.apply(torch_utils.init_weights)
optimizer = optim.Adam(model.parameters())
criterion = nn.CrossEntropyLoss(
ignore_index=word_output_vocab[text_utils.PAD_SYMBOL])
if os.path.exists(checkpoint_path):
torch_utils.load_checkpoint(checkpoint_path, model, optimizer)
else:
print("Saving checkpoints to ", checkpoint_dir)
print("Beginning training...")
print("Batch Size: ", batch_size)
def text_log(checkpoint_dir):
text_path = os.path.join(checkpoint_dir, 'sample_preds.txt')
i = np.random.randint(len(test_phoneme_files))
device = model.device
model.set_device(torch.device('cpu'))
pdr = torch_utils.Predictor(train_dataset,
filepaths=test_tg_files[i:i + 1],
model=model,
save_to_textgrid = bool(strtobool(args.save_to_textgrid))
output_dir = args.output_dir
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
print(f"Using device {device}")
##### Load the Model
model = config['model'](dropout_rate=0.0,
linear_layer_size=config['linear_layer_size'],
filter_sizes=config['filter_sizes'])
feature_fn = config['feature_fn']
model.set_device(device)
if os.path.exists(model_path):
torch_utils.load_checkpoint(model_path + '/best.pth.tar', model)
model.eval()
else:
raise Exception(f"Model checkpoint not found at {model_path}")
##### Load the audio file and features
inference_dataset = data_loaders.SwitchBoardLaughterInferenceDataset(
audio_path=audio_path, feature_fn=feature_fn, sr=sample_rate)
collate_fn = partial(audio_utils.pad_sequences_with_labels,
expand_channel_dim=config['expand_channel_dim'])
inference_generator = torch.utils.data.DataLoader(inference_dataset,
num_workers=4,
batch_size=8,
# hyperparameters
# =============================================================================
json_path = os.path.join(args.exp_dir, 'params.json')
assert os.path.isfile(
json_path), "No json configuration file found at {}".format(json_path)
params = utils.Params(json_path)
# =============================================================================
# dataset
# =============================================================================
transform = RandomTransform(10.0)
data_path = osp.join(args.exp_dir, 'test_list')
assert osp.isfile(data_path), "No test list file found at {}".format(data_path)
test_dataset, path_list = load_dataset(data_path, transform)
test_loader = DataLoader(test_dataset,
batch_size=1,
shuffle=False,
num_workers=1)
logging.info('{} testing data'.format(len(test_dataset)))
# =============================================================================
# model
# =============================================================================
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
model = net.Net(params.nClassesTotal).to(device)
load_checkpoint(osp.join(args.exp_dir, 'best.pth.tar'), model)
acc, iou = test(test_loader)
logging.info('Acc: {:.4f}, IoU: {:.4f}'.format(acc, iou))
return epoch_loss / len(iterator)
print("Initializing model...")
device = torch.device(torch_device if torch.cuda.is_available() else 'cpu')
print("Using device", device)
model = config['model'](dropout_rate=dropout_rate,
linear_layer_size=config['linear_layer_size'],
filter_sizes=config['filter_sizes'])
model.set_device(device)
torch_utils.count_parameters(model)
model.apply(torch_utils.init_weights)
optimizer = optim.Adam(model.parameters())
if os.path.exists(checkpoint_dir):
torch_utils.load_checkpoint(checkpoint_dir + '/last.pth.tar', model,
optimizer)
else:
print("Saving checkpoints to ", checkpoint_dir)
print("Beginning training...")
writer = SummaryWriter(checkpoint_dir)
if augment_fn is not None:
print("Loading background noise files...")
noise_signals = load_noise_files()
augment_fn = partial(augment_fn, noise_signals=noise_signals)
print("Loading impulse responses...")
impulse_responses = load_impulse_responses()
augment_fn = partial(augment_fn, impulse_responses=impulse_responses)
if supervised_augment:
