RuWANG

@luoxiaoliaolan hi, just read your post, how long time does it take to run this segmentation? it is the part segmentation or sematic segmentation?

the same problem here Missing key(s) in state_dict: "G.attns.0.0.fn.g", "G.attns.0.0.fn.fn.to_q.weight", "G.attns.0.0.fn.fn.to_q.bias", "G.attns.0.0.fn.fn.to_k.weight", "G.attns.0.0.fn.fn.to_k.bias", "G.attns.0.0.fn.fn.to_v.weight", "G.attns.0.0.fn.fn.to_v.bias", "G.attns.0.0.fn.fn.to_out.weight", "G.attns.0.0.fn.fn.to_out.bias", "G.attns.0.1.fn.g", "G.attns.0.1.fn.fn.0.weight", "G.attns.0.1.fn.fn.0.bias", "G.attns.0.1.fn.fn.2.weight", "G.attns.0.1.fn.fn.2.bias", "G.attns.1.0.fn.g", "G.attns.1.0.fn.fn.to_q.weight", "G.attns.1.0.fn.fn.to_q.bias", "G.attns.1.0.fn.fn.to_k.weight", "G.attns.1.0.fn.fn.to_k.bias", "G.attns.1.0.fn.fn.to_v.weight", "G.attns.1.0.fn.fn.to_v.bias", "G.attns.1.0.fn.fn.to_out.weight",...

Same issue here.

same here 'GCVAgent' object has no attribute '_client'

UNet=((ResBlock+Attention )*2)*4 for input_blocks python3 -W ignore::UserWarning train.py \ --dataroot /data1/juliew/mini_dataset/online_mario2sonic_lite \ --checkpoints_dir /data1/juliew/checkpoints \ --name mario \ --config_json examples/example_ddpm_mario.json \ --gpu_ids 1 \ --output_display_env test_mario_unet \ --output_display_freq 1 \...

Since joliGEN DDPM temporal use_temporal, it creates tensor in the shape(b,f,c,h,w), which differs from the priginal paper's formate of (b,c,f,h,w). So, in this version, all tensor flow is the formate...

python3 -W ignore::UserWarning train.py \ --dataroot /data1/juliew/dataset/online_mario2sonic_full_mario \ --checkpoints_dir /data1/juliew/checkpoints \ --name mario_temporal \ --config_json examples/example_ddpm_mario.json \ --gpu_ids 2 \ --output_display_env test_mario_temporal \ --output_print_freq 1 \ --output_display_freq 1 \ --data_dataset_mode...

works with command line python3 -W ignore::UserWarning train.py \ --dataroot /data1/juliew/dataset/online_mario2sonic_full_mario \ --checkpoints_dir /data1/juliew/checkpoints \ --name mario_antoine \ --gpu_ids 2 \ --output_display_env test_mario_antoine \ --model_type palette \ --output_print_freq 1 \...

python3 -W ignore::UserWarning train.py \ --dataroot /data1/juliew/dataset/online_mario2sonic_full_mario \ --checkpoints_dir /data1/juliew/checkpoints \ --name mario_vid_bs1 \ --gpu_ids 2 \ --model_type palette \ --output_print_freq 1 \ --output_display_freq 1 \ --data_dataset_mode self_supervised_temporal_labeled_mask_online \ --train_batch_size...

lanch inference cd scripts/ python3 gen_vid_diffusion.py \ --model_in_file /data1/juliew/checkpoints/mario_vid_bs1/latest_net_G_A.pth \ --img_in /data1/juliew/mini_dataset/online_mario2sonic_video/trainA/paths_part.txt \ --paths_file /data1/juliew/mini_dataset/online_mario2sonic_video/trainA/paths_part.txt \ --mask_in /data1/juliew/mini_dataset/online_mario2sonic_video/trainA/paths_part.txt \ --data_root /data1/juliew/mini_dataset/online_mario2sonic_video/ \ --dir_out ../inference_mario \ --img_width 128 \ --img_height 128...