# optimizer_G の設定
#================================
optimizer_G = optim.Adam(params=model_G.parameters(),
lr=args.lr,
betas=(args.beta1, args.beta2))
optimizer_D = optim.Adam(params=model_D.parameters(),
lr=args.lr,
betas=(args.beta1, args.beta2))
#================================
# loss 関数の設定
#================================
loss_l1_fn = nn.L1Loss()
loss_vgg_fn = VGGLoss(device, n_channels=3)
loss_feat_fn = FeatureMatchingLoss(device, n_dis=2, n_layers_D=3)
loss_adv_fn = LSGANLoss(device)
#================================
# モデルの学習
#================================
print("Starting Training Loop...")
n_print = 1
step = 0
for epoch in tqdm(range(args.n_epoches), desc="epoches"):
for iter, inputs in enumerate(
tqdm(dloader_train, desc="epoch={}".format(epoch))):
model_G.train()
model_D.train()
# 一番最後のミニバッチループで、バッチサイズに満たない場合は無視する（後の計算で、shape の不一致をおこすため）
if inputs["image_s"].shape[0] != args.batch_size:
#================================
# optimizer_G の設定
#================================
optimizer_G = optim.Adam(params=model_G.parameters(),
lr=args.lr,
betas=(args.beta1, args.beta2))
optimizer_D = optim.Adam(params=model_D.parameters(),
lr=args.lr,
betas=(args.beta1, args.beta2))
#================================
# loss 関数の設定
#================================
loss_l1_fn = nn.L1Loss()
loss_vgg_fn = VGGLoss(device, n_channels=3)
loss_adv_fn = LSGANLoss(device)
#================================
# モデルの学習
#================================
print("Starting Training Loop...")
n_print = 1
step = 0
for epoch in tqdm(range(args.n_epoches), desc="epoches"):
for iter, inputs in enumerate(
tqdm(dloader_train, desc="epoch={}".format(epoch))):
model_G.train()
model_D.train()
# 一番最後のミニバッチループで、バッチサイズに満たない場合は無視する（後の計算で、shape の不一致をおこすため）
if inputs["pose_parse_onehot"].shape[0] != args.batch_size:
#================================
# optimizer_G の設定
#================================
optimizer_G = optim.Adam(params=model_G.parameters(),
lr=args.lr,
betas=(args.beta1, args.beta2))
optimizer_D = optim.Adam(params=model_D.parameters(),
lr=args.lr,
betas=(args.beta1, args.beta2))
#================================
# loss 関数の設定
#================================
loss_l1_fn = nn.L1Loss()
loss_vgg_fn = VGGLoss(device, n_channels=3)
loss_adv_fn = LSGANLoss(device)
loss_const_fn = nn.MSELoss()
#================================
# モデルの学習
#================================
cutmix_fn = CutMix(prob=1.0)
seed_cutmix = random.randint(0, 10000)
print("Starting Training Loop...")
n_print = 1
step = 0
for epoch in tqdm(range(args.n_epoches), desc="epoches"):
for iter, inputs in enumerate(
tqdm(dloader_train, desc="epoch={}".format(epoch))):
model_G.train()