continue training

[elsobhano]

Hi my friends

I am training cycleGAN model But I cant train 200 epochs in one time. How can I continue my training operation from where I stopped the training?

[lll-hue]

[arrrrr3186]

is it working for anyone for you? I am using below command. which execute till web directory creations:

python3 train.py --dataroot ./Custom_data/v_2/urban/ --name Sar-Opt_CGAN --continue_train --n_epochs 70 --n_epochs_decay 70 --epoch_count 201 --direction BtoA /usr/lib/python3/dist-packages/requests/init.py:87: RequestsDependencyWarning: urllib3 (2.2.1) or chardet (4.0.0) doesn't match a supported version! warnings.warn("urllib3 ({}) or chardet ({}) doesn't match a supported " unaligned unaligned data.unaligned_dataset ----------------- Options --------------- batch_size: 1
beta1: 0.5
checkpoints_dir: ./checkpoints
continue_train: True [default: False] crop_size: 256
dataroot: ./Custom_data/v_2/urban/ [default: None] dataset_mode: unaligned
direction: BtoA [default: AtoB] display_env: main
display_freq: 400
display_id: 1
display_ncols: 4
display_port: 8097
display_server: http://localhost
display_winsize: 256
epoch: latest
epoch_count: 201 [default: 1] gan_mode: lsgan
gpu_ids: 0
init_gain: 0.02
init_type: normal
input_nc: 3
isTrain: True [default: None] lambda_A: 10.0
lambda_B: 10.0
lambda_identity: 0.5
load_iter: 0 [default: 0] load_size: 286
lr: 0.0002
lr_decay_iters: 50
lr_policy: linear
max_dataset_size: inf
model: cycle_gan
n_epochs: 70 [default: 100] n_epochs_decay: 70 [default: 100] n_layers_D: 3
name: Sar-Opt_CGAN [default: experiment_name] ndf: 64
netD: basic
netG: resnet_9blocks
ngf: 64
no_dropout: True
no_flip: False
no_html: False
norm: instance
num_threads: 4
output_nc: 3
phase: train
pool_size: 50
preprocess: resize_and_crop
print_freq: 100
save_by_iter: False
save_epoch_freq: 5
save_latest_freq: 5000
serial_batches: False
suffix:
update_html_freq: 1000
use_wandb: False
verbose: False
wandb_project_name: CycleGAN-and-pix2pix
----------------- End ------------------- unaligned data.unaligned_dataset dataset [UnalignedDataset] was created 500 The number of training images = 500 initialize network with normal initialize network with normal initialize network with normal initialize network with normal model [CycleGANModel] was created loading the model from ./checkpoints/Sar-Opt_CGAN/latest_net_G_A.pth loading the model from ./checkpoints/Sar-Opt_CGAN/latest_net_G_B.pth loading the model from ./checkpoints/Sar-Opt_CGAN/latest_net_D_A.pth loading the model from ./checkpoints/Sar-Opt_CGAN/latest_net_D_B.pth ---------- Networks initialized ------------- [Network G_A] Total number of parameters : 11.378 M [Network G_B] Total number of parameters : 11.378 M [Network D_A] Total number of parameters : 2.765 M [Network D_B] Total number of parameters : 2.765 M

Setting up a new session... create web directory ./checkpoints/Sar-Opt_CGAN/web...

---