when training, epochxx_weight.jpg are totally black in checkpoints？
jiangzhubo opened this issue · comments
hi, i am training my own dataset, my input is real image and output is a mask. and i found a situation, during the training,, the epochxx_weigh.jpg is always black, do you know the reasons and what is epochxx_weight.jpg means?
following are my settings:
------------ Options -------------
TTUR: False
add_face_disc: False
basic_point_only: False
batchSize: 1
beta1: 0.5
checkpoints_dir: ./checkpoints
continue_train: False
dataroot: datasets/plax2
dataset_mode: temporal
debug: False
densepose_only: False
display_freq: 100
display_id: 0
display_winsize: 512
feat_num: 3
fg: False
fg_labels: [255]
fineSize: 256
fp16: False
gan_mode: ls
gpu_ids: [0]
input_nc: 3
isTrain: True
label_feat: False
label_nc: 0
lambda_F: 10.0
lambda_T: 10.0
lambda_feat: 10.0
loadSize: 256
load_features: False
load_pretrain:
local_rank: 0
lr: 0.0002
max_dataset_size: inf
max_frames_backpropagate: 2
max_frames_per_gpu: 8
max_t_step: 1
model: vid2vid
nThreads: 2
n_blocks: 9
n_blocks_local: 3
n_downsample_E: 3
n_downsample_G: 3
n_frames_D: 3
n_frames_G: 3
n_frames_total: 3
n_gpus_gen: 1
n_layers_D: 3
n_local_enhancers: 1
n_scales_spatial: 1
n_scales_temporal: 2
name: plaxs6
ndf: 64
nef: 32
netE: simple
netG: composite
ngf: 128
niter: 20
niter_decay: 25
niter_fix_global: 0
niter_step: 8
no_canny_edge: False
no_dist_map: False
no_first_img: True
no_flip: True
no_flow: False
no_ganFeat: False
no_html: False
no_vgg: False
norm: batch
num_D: 1
openpose_only: False
output_nc: 3
phase: train
pool_size: 1
print_freq: 100
random_drop_prob: 0.05
random_scale_points: False
remove_face_labels: False
resize_or_crop: scaleWidth
save_epoch_freq: 1
save_latest_freq: 1000
serial_batches: False
sparse_D: False
tf_log: False
use_instance: False
use_single_G: False
which_epoch: latest
-------------- End ----------------
Hello, I have the same issue. Did you find a way to solve it ?