Open wr0124 opened 2 months ago
add G_prompt for cut_turbo for unaligned dataset and works for batch_size larger than 1
The training works with the following command line
python3 train.py \ --dataroot /data1/juliew/dataset/horse2zebra \ --checkpoints_dir /data1/juliew/checkpoints \ --name horse2zebra_turbo \ --config_json examples/example_cut_turbo_horse2zebra.json \ --train_batch_size 2 \ --output_print_freq 10 \ --data_crop_size 64 \ --data_load_size 64 \ --G_prompt zebra (this option is mandatory if there is no prompt file in the dataset)
The inference works with the following command line
cd scripts python3 gen_single_image.py \ --model_in_file /data1/juliew/checkpoints/horse2zebra_turbo/latest_net_G_A.pth \ --img_in /data1/juliew/dataset/horse2zebra/testA/n02381460_1000.jpg \ --img_out /data1/juliew/target.jpg \ --prompt zebra \ --gpuid 0 \
add G_prompt for cut_turbo for unaligned dataset and works for batch_size larger than 1
The training works with the following command line
The inference works with the following command line