jolibrain / joliGEN

Generative AI Image Toolset with GANs and Diffusion for Real-World Applications
https://www.joligen.com
Other
243 stars 32 forks source link

option for max_sequence_length of video generation #699

Closed wr0124 closed 4 weeks ago

wr0124 commented 1 month ago

Create an option for the maximum sequence length for video generation, --vid_max_sequence_length. The data_temporal_number_frames value should not exceed --vid_max_sequence_length

Example of execution. It works with:

python3 -W ignore::UserWarning  train.py \
--dataroot /path/to/online_mario2sonic_full_mario  \
--checkpoints_dir  /path/to/checkpoints \
--name  mario_vid   \
--gpu_ids 0    \
--model_type palette \
--output_print_freq 1   \
--output_display_freq 1   \
--data_dataset_mode  self_supervised_temporal_labeled_mask_online  \
--train_batch_size 1  \
--train_iter_size 1  \
--model_input_nc 3 \
--model_output_nc 3 \
--data_relative_paths \
--train_G_ema \
--train_optim adamw \
--G_netG unet_vid   \
--data_online_creation_crop_size_A 32  \
--data_online_creation_crop_size_B 32 \
--data_crop_size 32 \
--data_load_size 32  \
--data_online_creation_rand_mask_A \
--train_G_lr 0.0001 \
--dataaug_no_rotate \
--G_diff_n_timestep_train  6  \
--G_diff_n_timestep_test  3  \
--data_temporal_number_frames 8  \
--data_temporal_frame_step 1 \
--data_online_creation_mask_delta_A_ratio 0.12 0.12 \
--alg_diffusion_cond_image_creation    computed_sketch  \
--alg_diffusion_cond_computed_sketch_list canny \
--alg_diffusion_vid_canny_dropout 0.1 0.8  \
--alg_diffusion_cond_sketch_canny_range  500 1000  \
--vid_max_sequence_length 24 
wr0124 commented 1 month ago

code works with python3 -W ignore::UserWarning train.py \ --dataroot /data1/juliew/dataset/online_mario2sonic_full_mario \ --checkpoints_dir /data1/juliew/checkpoints \ --name mario_vid \ --gpu_ids 0 \ --model_type palette \ --output_print_freq 1 \ --output_display_freq 1 \ --data_dataset_mode self_supervised_temporal_labeled_mask_online \ --train_batch_size 1 \ --train_iter_size 1 \ --model_input_nc 3 \ --model_output_nc 3 \ --data_relative_paths \ --train_G_ema \ --train_optim adamw \ --G_netG unet_vid \ --data_online_creation_crop_size_A 32 \ --data_online_creation_crop_size_B 32 \ --data_crop_size 32 \ --data_load_size 32 \ --data_online_creation_rand_mask_A \ --train_G_lr 0.0001 \ --dataaug_no_rotate \ --G_diff_n_timestep_train 6 \ --G_diff_n_timestep_test 3 \ --data_temporal_number_frames 8 \ --data_temporal_frame_step 1 \ --data_online_creation_mask_delta_A_ratio 0.12 0.12 \ --alg_diffusion_cond_image_creation computed_sketch \ --alg_diffusion_cond_computed_sketch_list canny \ --alg_diffusion_vid_canny_dropout 0.1 0.8 \ --alg_diffusion_cond_sketch_canny_range 500 1000 \ --G_unet_vid_max_sequence_length 15 \ ~