Why are my training and test results all gray pictures

[potaosking]

I am using the default dataset This is my option ----------------- Options --------------- aspect_ratio: 1.0 batch_size: 1 checkpoints_dir: ./checkpoints crop_size: 256 dataroot: ./datasets/summer2winter_yosemite [default: None] dataset_mode: unaligned direction: AtoB display_winsize: 256 epoch: latest eval: False gpu_ids: 0 init_gain: 0.02 init_type: normal input_nc: 3 isTrain: False [default: None] load_iter: 0 [default: 0] load_size: 256 max_dataset_size: inf model: cycle_gan [default: test] n_layers_D: 3 name: summer2winter_pretrained [default: experiment_name] ndf: 64 netD: basic netG: resnet_9blocks ngf: 64 no_dropout: True no_flip: False norm: instance num_test: 50 num_threads: 4 output_nc: 3 phase: test preprocess: resize_and_crop results_dir: ./results/ serial_batches: False suffix: use_wandb: False verbose: False ----------------- End -------------------

Even the images I generated using the pretrained model are gray

[junyanz]

Could you share with us the training script and debugging information (loss plots)?