Last active
October 11, 2019 09:26
-
-
Save gwerbin/2a214298bcf2fc50bf2539818cb79b6d to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import sys | |
from time import perf_counter | |
import numpy as np | |
import torch | |
import torch.nn.functional as F | |
from sklearn.datasets import make_classification | |
from sklearn.model_selection import train_test_split | |
from sklearn.preprocessing import LabelBinarizer | |
from tqdm import tqdm | |
rs = np.random.RandomState(4890702) | |
x, y = make_classification( | |
n_samples=5000, | |
n_classes=8, | |
n_features=200, | |
n_informative=100, | |
random_state=rs | |
) | |
x = x.astype(np.float32) | |
y = y.astype(np.int64) | |
x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.25, stratify=y) | |
y_trans = LabelBinarizer() | |
def array_islice(data, batch_size): | |
bounds = np.arange(0, data.shape[0]+batch_size, batch_size) | |
for i0, i1 in zip(bounds[:-1], bounds[1:]): | |
if isinstance(data, (pd.Series, pd.DataFrame)): | |
yield data.iloc[i0 : i1] | |
else: | |
yield data[i0 : i1] | |
x_train_t = x_train | |
y_train_t = y_trans.fit_transform(y_train) | |
x_test_t = x_test | |
y_test_t = y_trans.transform(y_test) | |
n_epoch = 25 | |
batch_size = x_train_t.shape[0] // 25 | |
model = torch.nn.Linear(x_train_t.shape[1], y_train_t.shape[1]) | |
criterion = torch.nn.MultiLabelSoftMarginLoss(reduction='mean') | |
optimizer = torch.optim.Adam(model.parameters(), lr=0.001, weight_decay=0.01) | |
t0 = perf_counter() | |
loss_train_seq = [] | |
loss_test_seq = [] | |
acc_train_seq = [] | |
acc_test_seq = [] | |
with tqdm(desc='epochs', total=n_epoch) as progress: | |
progress.set_postfix({'loss': None}) | |
for epoch in range(n_epoch): | |
data_gen = zip( | |
array_islice(x_train_t, batch_size), | |
array_islice(y_train_t, batch_size) | |
) | |
loss_epoch_seq = [] | |
epoch_n_correct = 0 | |
epoch_n_total = 0 | |
for batch_x, batch_y in data_gen: | |
x_in = torch.autograd.Variable(torch.Tensor(batch_x)) | |
y_in = torch.autograd.Variable(torch.Tensor(batch_y)) | |
y_out = model(x_in) | |
loss = criterion(y_out, y_in) | |
loss_epoch_seq.append(float(loss)) | |
epoch_n_correct += (y_out.argmax(dim=1) == y_in.argmax(dim=1)).sum() | |
epoch_n_total += y_in.shape[0] | |
optimizer.zero_grad() | |
loss.backward() | |
optimizer.step() | |
loss_epoch = np.mean(loss_epoch_seq) | |
loss_train_seq.append(loss_epoch) | |
acc_epoch = float(epoch_n_correct) / float(epoch_n_total) | |
acc_train_seq.append(acc_epoch) | |
x_test_in = torch.autograd.Variable(torch.Tensor(x_test_t)) | |
y_test_in = torch.autograd.Variable(torch.Tensor(y_test_t)) | |
y_test_out = model(x_test_in) | |
loss_test = float(criterion(y_test_out, y_test_in)) | |
loss_test_seq.append(loss_test) | |
acc_test = float((y_test_out.argmax(dim=1) == y_test_in.argmax(dim=1)).sum()) / y_test_in.shape[0] | |
acc_test_seq.append(acc_test) | |
progress.set_postfix({'loss_train': loss_epoch, 'acc_train': acc_epoch, 'loss_test': loss_test, 'acc_test': acc_test}) | |
progress.update(1) | |
t1 = perf_counter() | |
print(end='', flush=True, file=sys.stderr) | |
print(t1-t0) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment