from __future__ import print_function, division
import torch
import numpy as np
import torch.nn as nn
import os
import shutil
from sklearn.metrics.pairwise import euclidean_distances
import torch.nn.functional as F
import Options
config = Options.Config()
def to_np(x):
return x.data.cpu().numpy()
def save_checkpoint(state,
epoch,
is_best,
filename=config.name + '_checkpoint.pth.tar'):
if not os.path.exists(config.checkpoints_dir):
os.mkdir(config.checkpoints_dir)
torch.save(
state, os.path.join(config.checkpoints_dir,
str(epoch) + "_" + filename))
if is_best:
shutil.copyfile(
os.path.join(config.checkpoints_dir,
str(epoch) + "_" + filename),
config.name + '_model_best.pth.tar')
from __future__ import print_function, division
import torch
import torch.nn as nn
import embedding_utils
from torch.autograd import Variable
import random
import Options
opt = Options.Config()
class GANLoss(nn.Module):
def __init__(self,
use_lsgan=False,
target_real_label=1.0,
target_fake_label=0.0,
tensor=torch.FloatTensor,
softlabel=False):
super(GANLoss, self).__init__()
self.real_label = target_real_label
self.fake_label = target_fake_label
self.real_label_var = None
self.fake_label_var = None
self.Tensor = tensor
self.softlabel = softlabel
if use_lsgan:
self.loss = nn.MSELoss()
else:
self.loss = nn.BCELoss()
def get_target_tensor(self, input, target_is_real):
