def predict_model(experiment, output_dir):
"""Writes the predictions of a given dataset file."""
saved_dir = "/home2/preetmhn/clms/ling_575_nlms/models/saved_{}".format(experiment)
model = torch.load('{}/hate_speech_model_trained.pt'.format(saved_dir))
settings = Settings(experiment, True)
# get gpu
device = get_gpu(settings)
# get data, split with the same random seed as in training
input_ids, labels, attention_masks = prepare_data(settings)
_, validation_inputs, _, validation_labels = train_test_split(input_ids, labels, random_state=2018, test_size=0.1)
_, validation_dataloader = split_data(settings, input_ids, labels, attention_masks)
# make predictions and write to file
settings.write_debug("Getting model predictions")
preds = predict(device, model, validation_dataloader)
# load tokenizer for the decoding
tokenizer = load_bert_tokenizer(settings, True)
# write to file
settings.write_debug("Writing model predictions")
output_file = os.path.join(output_dir, experiment + '_pred.txt')
out = csv.writer(open(output_file, 'w+', encoding='utf-8'), delimiter='\t')
out.writerow(['input', 'true', 'pred'])
for i in range(len(preds)):
tokens = tokenizer.decode(input_ids[i], skip_special_tokens=True)
out.writerow([tokens, labels[i], preds[i]])
# write scores
settings.write_debug("Getting test evaluation")
record_score_information(settings, validation_labels, preds)
def pred_label(f_pred, prepare_data, options, iterator, kb_dict):
labels = []
for x1, x2, x1_lemma, x2_lemma, y in iterator:
x1, x1_mask, x1_kb, x2, x2_mask, x2_kb, kb_att, y = prepare_data(x1, x2, x1_lemma, x2_lemma, y, options, kb_dict)
preds = f_pred(x1, x1_mask, x1_kb, x2, x2_mask, x2_kb, kb_att)
labels = labels + preds.tolist()
return labels
def pred_label(f_pred, prepare_data, iterator):
labels = []
for x1, x2, y in iterator:
x1, x1_mask, x2, x2_mask, y = prepare_data(x1, x2, y)
preds = f_pred(x1, x1_mask, x2, x2_mask)
labels = labels + preds.tolist()
return labels
def sanity_check_for_prepare_data():
"""Test function prepare_data and print out a sample."""
print("Running check for function prepare_data()...")
dataloader = prepare_data(batch_size=1)
print("Length of dataloader: ", len(dataloader))
sample = next(iter(dataloader))[0][0]
print("Shape of the sample image: ", sample.shape)
plt.figure()
plt.imshow(np.transpose(sample.detach(), (1, 2, 0)))
plt.show()
print("Passed!")
def sanity_check_for_train_hologan(use_gpu=True):
"""Test training discriminator."""
now = datetime.now()
subsample = None
if use_gpu and torch.cuda.is_available():
device = torch.device('cuda')
else:
device = torch.device('cpu')
print(use_gpu)
hologan = HoloGAN.Net(128, (3, 128, 128)).to(device)
init_layers_serious(hologan)
criterion = HoloGAN.compute_loss
dataloader = prepare_data(batch_size=8, subsample=subsample)
optim_G = optim.Adam(hologan.G.parameters())
optim_D = optim.Adam(hologan.D.parameters())
# Setup tensorboard
logdir = "logs/fit/" + now.strftime("%Y%m%d-%H%M%S")
writer = SummaryWriter(logdir)
it = iter(dataloader)
images, _ = it.next()
img_grid = make_grid(images)
writer.add_image("sample_batch", img_grid)
writer.close()
for epoch in range(3):
train_one_epoch(dataloader,
hologan,
criterion,
optim_G,
optim_D,
device,
writer,
epoch=epoch,
print_step=20)
def pred_label(f_prods, prepare_data, options, iterator, word_idict):
labels = []
valid_acc = 0
n_done = 0
for x1_, x2_, y_ in iterator:
n_done += len(x1_)
lengths_x1 = [len(s) for s in x1_]
lengths_x2 = [len(s) for s in x2_]
x1, x1_mask, char_x1, char_x1_mask, x2, x2_mask, char_x2, char_x2_mask, y = prepare_data(
x1_, x2_, y_, word_idict)
inps = [
x1, x1_mask, char_x1, char_x1_mask, x2, x2_mask, char_x2,
char_x2_mask
]
prods = f_prods(*inps)
preds = prods.argmax(axis=1)
valid_acc += (preds == y).sum()
labels = labels + preds.tolist()
valid_acc = 1.0 * valid_acc / n_done
print "total sampel", n_done
print "Acc", valid_acc
return labels
def forward(self, x):
"""Performs the forward pass."""
emb = self.embeddings(x)
recurrent_output, _ = self.recurrent_module(emb)
output = self.seq_modules(recurrent_output[-1])
return output
if __name__ == '__main__':
np.random.seed(SEED)
torch.manual_seed(SEED)
train_dataloader, valid_dataloader, \
test_dataloader, embeddings = prepare_data() # freeze=False
model = Recurrent(embeddings, nn.RNN)
# model = Recurrent(embeddings, nn.RNN, num_layers=3)
# model = Recurrent(embeddings, nn.RNN, num_layers=3, dropout=0.4)
# model = Recurrent(embeddings, nn.LSTM)
# model = Recurrent(embeddings, nn.LSTM, activation=nn.LeakyReLU)
# model = Recurrent(embeddings, nn.GRU)
# model = Recurrent(embeddings, nn.GRU, num_layers=1)
# model = Recurrent(embeddings, nn.GRU, hidden_size=200)
# model = Recurrent(embeddings, nn.GRU, bidirectional=True)
optimizer = torch.optim.Adam(model.parameters(), lr=1e-4)
# optimizer = torch.optim.SGD(model.parameters(), lr=1e-4)
main(model,
def sanity_check_for_train_discriminator(use_gpu=False):
"""Test training discriminator."""
now = datetime.now()
subsample = 80
if use_gpu and torch.cuda.is_available():
device = torch.device('cuda')
else:
device = torch.device('cpu')
print(use_gpu)
# z = torch.randn(128, device=device=None)
netD = Discriminator(128, (3, 128, 128),
spec_norm=spectral_norm,
norm_layer=nn.InstanceNorm2d).to(device)
criterion = nn.BCELoss()
real_label = 1
fake_label = 0
opt = optim.Adam(netD.parameters())
dataloader = prepare_data(batch_size=8, subsample=subsample)
# Setup tensorboard
logdir = "logs/fit/" + now.strftime("%Y%m%d-%H%M%S")
writer = SummaryWriter(logdir)
it = iter(dataloader)
images, _ = it.next()
img_grid = make_grid(images)
writer.add_image("sample_batch", img_grid)
writer.add_graph(netD, images.to(device))
writer.close()
running_loss = 0.0
for epoc in range(10):
print("\nEpoch: ", epoc + 1)
for i_batch, data in enumerate(Bar(dataloader)):
netD.zero_grad()
real_img = data[0].to(device)
bs = real_img.shape[0]
d_gan, d_id, d_style = netD(real_img)
label = torch.full(d_gan.shape,
real_label,
dtype=torch.float,
device=device)
errD_real = criterion(d_gan, label)
label = torch.full(d_style.shape,
real_label,
dtype=torch.float,
device=device)
errD_real += criterion(d_style, label)
errD_real.backward()
opt.step()
running_loss += errD_real.item()
if i_batch % 10 == 9:
writer.add_scalar("training loss", running_loss / 10,
epoc * subsample + i_batch)
writer.add_figure(
"predictions",
functional.plot_classes_preds(netD, real_img))
running_loss = 0.0
def test_prepare_data():
"""Dummy test function"""
assert prepare_data("location") is False
assert prepare_data("s3://mybucket/data/") is True
def test_count_chains():
adapters = prepare_data([16, 10, 15, 5, 1, 11, 7, 19, 6, 12, 4])
assert count_possible_chains(adapters, 0) == 8
from plotter import plot_two_class_classification, plot_regression_data, plot_multi_class_classification
if __name__ == '__main__':
path_to_test_data = str(sys.argv[1])
nol = int(sys.argv[2]) # number of lines of test data
type_of_problem = sys.argv[3]
radius_scale = float(sys.argv[4])
sys.argv[4] = sys.argv[3]
W = np.load("outputs/weights" + type_of_problem + ".npy")
V = np.load("outputs/V" + type_of_problem + ".npy")
gama = np.load("outputs/gama" + type_of_problem + ".npy")
type_of_problem = int(type_of_problem)
X, y, scales = prepare_data(number_of_lines=nol, path=path_to_test_data)
l, n = X.shape
c = 0
if type_of_problem == 2:
y = prepare_data_for_multi_class_classification(y)
_, c = y.shape
m, n_prime = V.shape
assert n == n_prime
G = generate_G_matrix(X, V, gama)
yhad = generate_yhad_matrix(G, W)
if type_of_problem == 0:
plot_regression_data(yhad)
elif type_of_problem == 1:
