def eval(fold_ix=1):
test_data = data.Data(
fold=fold_ix, is_test_data=True
) # the dataset merges self.real_U_file and self.fake_U_file
test_data_loader = DataLoader(test_data,
batch_size=50,
shuffle=True,
num_workers=8)
# self.discriminator(validation_data_loader)
X_trn, Y_trn, Y_trn_o, X_tst, Y_tst, Y_tst_o, vocabulary, vocabulary_inv = data_helpers.load_data(
fold=fold_ix)
X_trn = X_trn.astype(np.int32)
X_tst = X_tst.astype(np.int32)
Y_trn = Y_trn.astype(np.int32)
Y_tst = Y_tst.astype(np.int32)
args.num_classes = Y_trn.shape[1]
embedding_weights = load_word2vec('glove',
vocabulary_inv,
num_features=300)
capsule_net = CapsNet_Text(args, embedding_weights)
path = 'save/model/fold' + str(fold_ix) + '/nlp-capsule50.pth'
capsule_net.load_state_dict(torch.load(path))
# discriminator.eval()
with torch.no_grad():
for _, (input, labels) in enumerate(test_data_loader):
# input, labels = input, labels
_, preds = capsule_net(
input, labels) # (None, vocab_size, sequence_len+1)
# print('preds without round: ' , preds.squeeze(2))
preds = preds.round().squeeze(2)
# print('input : ', input)
# print('preds squeeze 2 : ', preds)
# print('labels: ', labels)
# print('preds 0: ' , preds.shape[0])
# print('preds 1: ' , preds.shape[1])
# print('labels 0: ', labels.shape[0])
# print('labels 1: ', labels.shape[1])
report = metrics.classification_report(labels, preds)
print('report on fold ' + str(fold_ix) + ': ')
print(report)
df = pd.DataFrame(Loss_data, columns = ['Epochs', 'Loss'])
df.to_csv(path)
X_trn, Y_trn, X_tst, Y_tst, vocabulary, vocabulary_inv = datasets.get_cross_domain_doctor_doctor()
X_trn = X_trn.astype(np.int32)
X_tst = X_tst.astype(np.int32)
Y_trn = Y_trn.astype(np.int32)
Y_tst = Y_tst.astype(np.int32)
args.num_classes = Y_trn.shape[1]
embedding_weights = load_word2vec('glove', vocabulary_inv, num_features=300)
capsule_net = CapsNet_Text(args, embedding_weights)
current_lr = args.learning_rate
optimizer = Adam(capsule_net.parameters(), lr=current_lr)
# capsule_net = nn.DataParallel(capsule_net).cuda()
losses = []
for epoch in range(args.num_epochs):
# torch.cuda.empty_cache()
nr_trn_num = X_trn.shape[0]
nr_batches = int(np.ceil(nr_trn_num / float(args.tr_batch_size)))
if epoch > args.learning_rate_decay_start and args.learning_rate_decay_start >= 0:
frac = (epoch - args.learning_rate_decay_start) // args.learning_rate_decay_every
decay_factor = args.learning_rate_decay_rate ** frac
print(json.dumps(params, indent=2))
X_trn, Y_trn, Y_trn_o, X_tst, Y_tst, Y_tst_o, vocabulary, vocabulary_inv = data_helpers.load_data(
args.dataset, max_length=args.sequence_length, vocab_size=args.vocab_size)
Y_trn = Y_trn.toarray()
Y_tst = Y_tst.toarray()
X_trn = X_trn.astype(np.int32)
X_tst = X_tst.astype(np.int32)
Y_trn = Y_trn.astype(np.int32)
Y_tst = Y_tst.astype(np.int32)
embedding_weights = load_word2vec('glove', vocabulary_inv, args.vec_size)
args.num_classes = Y_trn.shape[1]
capsule_net = CapsNet_Text(args, embedding_weights)
capsule_net = nn.DataParallel(capsule_net).cuda()
model_name = 'model-eur-akde-29.pth'
capsule_net.load_state_dict(
torch.load(os.path.join(args.start_from, model_name)))
print(model_name + ' loaded')
model_name = 'model-EUR-CNN-40.pth'
baseline = CNN_KIM(args, embedding_weights)
baseline.load_state_dict(torch.load(os.path.join(args.start_from, model_name)))
baseline = nn.DataParallel(baseline).cuda()
print(model_name + ' loaded')
nr_tst_num = X_tst.shape[0]
nr_batches = int(np.ceil(nr_tst_num / float(args.ts_batch_size)))
X_trn, Y_trn, Y_trn_o, X_tst, Y_tst, Y_tst_o, vocabulary, vocabulary_inv = data_helpers.load_data(args.dataset,
max_length=args.sequence_length,
vocab_size=args.vocab_size)
Y_trn = Y_trn.toarray()
Y_tst = Y_tst.toarray()
X_trn = X_trn.astype(np.int32)
X_tst = X_tst.astype(np.int32)
Y_trn = Y_trn.astype(np.int32)
Y_tst = Y_tst.astype(np.int32)
embedding_weights = load_word2vec('glove', vocabulary_inv, args.vec_size)
args.num_classes = Y_trn.shape[1]
capsule_net = CapsNet_Text(args, embedding_weights)
capsule_net = nn.DataParallel(capsule_net).cuda()
model_name = 'model-EUR-CNN-40.pth'
baseline = CNN_KIM(args, embedding_weights)
baseline.load_state_dict(torch.load(os.path.join('save_new', model_name)))
baseline = nn.DataParallel(baseline).cuda()
print(model_name + ' loaded')
def transformLabels(labels, total_labels):
label_index = list(set([l for _ in total_labels for l in _]))
label_index.sort()
variable_num_classes = len(label_index)
target = []
for _ in labels: