diff --git a/unitree_z1_stackbox/case1/run_world_model_interaction.sh b/unitree_z1_stackbox/case1/run_world_model_interaction.sh new file mode 100644 index 0000000..73d9132 --- /dev/null +++ b/unitree_z1_stackbox/case1/run_world_model_interaction.sh @@ -0,0 +1,24 @@ +res_dir="unitree_z1_stackbox/case1" +dataset="unitree_z1_stackbox" + +{ + time CUDA_VISIBLE_DEVICES=0 python3 scripts/evaluation/world_model_interaction.py \ + --seed 123 \ + --ckpt_path ckpts/unifolm_wma_dual.ckpt \ + --config configs/inference/world_model_interaction.yaml \ + --savedir "${res_dir}/output" \ + --bs 1 --height 320 --width 512 \ + --unconditional_guidance_scale 1.0 \ + --ddim_steps 50 \ + --ddim_eta 1.0 \ + --prompt_dir "unitree_z1_stackbox/case1/world_model_interaction_prompts" \ + --dataset ${dataset} \ + --video_length 16 \ + --frame_stride 4 \ + --n_action_steps 16 \ + --exe_steps 16 \ + --n_iter 12 \ + --timestep_spacing 'uniform_trailing' \ + --guidance_rescale 0.7 \ + --perframe_ae +} 2>&1 | tee "${res_dir}/output.log" diff --git a/unitree_z1_stackbox/case1/unitree_z1_stackbox_case1.mp4 b/unitree_z1_stackbox/case1/unitree_z1_stackbox_case1.mp4 new file mode 100644 index 0000000..b999ddf Binary files /dev/null and b/unitree_z1_stackbox/case1/unitree_z1_stackbox_case1.mp4 differ diff --git a/unitree_z1_stackbox/case1/world_model_interaction_prompts/images/unitree_z1_stackbox/5.png b/unitree_z1_stackbox/case1/world_model_interaction_prompts/images/unitree_z1_stackbox/5.png new file mode 100644 index 0000000..8e265c0 Binary files /dev/null and b/unitree_z1_stackbox/case1/world_model_interaction_prompts/images/unitree_z1_stackbox/5.png differ diff --git a/unitree_z1_stackbox/case1/world_model_interaction_prompts/transitions/unitree_z1_stackbox/5.h5 b/unitree_z1_stackbox/case1/world_model_interaction_prompts/transitions/unitree_z1_stackbox/5.h5 new file mode 100644 index 0000000..fa647f1 Binary files /dev/null and b/unitree_z1_stackbox/case1/world_model_interaction_prompts/transitions/unitree_z1_stackbox/5.h5 differ diff --git a/unitree_z1_stackbox/case1/world_model_interaction_prompts/transitions/unitree_z1_stackbox/meta_data/stats.safetensors b/unitree_z1_stackbox/case1/world_model_interaction_prompts/transitions/unitree_z1_stackbox/meta_data/stats.safetensors new file mode 100644 index 0000000..1918ea0 Binary files /dev/null and b/unitree_z1_stackbox/case1/world_model_interaction_prompts/transitions/unitree_z1_stackbox/meta_data/stats.safetensors differ diff --git a/unitree_z1_stackbox/case1/world_model_interaction_prompts/unitree_z1_stackbox.csv b/unitree_z1_stackbox/case1/world_model_interaction_prompts/unitree_z1_stackbox.csv new file mode 100644 index 0000000..8f55185 --- /dev/null +++ b/unitree_z1_stackbox/case1/world_model_interaction_prompts/unitree_z1_stackbox.csv @@ -0,0 +1,2 @@ +videoid,contentUrl,duration,data_dir,instruction,dynamic_confidence,dynamic_wording,dynamic_source_category,embodiment,fps +5,x,x,unitree_z1_stackbox,"Pick up the red cup on the table.",x,x,x,Unitree Z1 Robot Arm,30 diff --git a/unitree_z1_stackbox/case2/run_world_model_interaction.sh b/unitree_z1_stackbox/case2/run_world_model_interaction.sh new file mode 100644 index 0000000..95fb33b --- /dev/null +++ b/unitree_z1_stackbox/case2/run_world_model_interaction.sh @@ -0,0 +1,24 @@ +res_dir="unitree_z1_stackbox/case2" +dataset="unitree_z1_stackbox" + +{ + time CUDA_VISIBLE_DEVICES=0 python3 scripts/evaluation/world_model_interaction.py \ + --seed 123 \ + --ckpt_path ckpts/unifolm_wma_dual.ckpt \ + --config configs/inference/world_model_interaction.yaml \ + --savedir "${res_dir}/output" \ + --bs 1 --height 320 --width 512 \ + --unconditional_guidance_scale 1.0 \ + --ddim_steps 50 \ + --ddim_eta 1.0 \ + --prompt_dir "unitree_z1_stackbox/case2/world_model_interaction_prompts" \ + --dataset ${dataset} \ + --video_length 16 \ + --frame_stride 4 \ + --n_action_steps 16 \ + --exe_steps 16 \ + --n_iter 12 \ + --timestep_spacing 'uniform_trailing' \ + --guidance_rescale 0.7 \ + --perframe_ae +} 2>&1 | tee "${res_dir}/output.log" diff --git a/unitree_z1_stackbox/case2/unitree_z1_stackbox_case2.mp4 b/unitree_z1_stackbox/case2/unitree_z1_stackbox_case2.mp4 new file mode 100644 index 0000000..cfd27eb Binary files /dev/null and b/unitree_z1_stackbox/case2/unitree_z1_stackbox_case2.mp4 differ diff --git a/unitree_z1_stackbox/case2/world_model_interaction_prompts/images/unitree_z1_stackbox/15.png b/unitree_z1_stackbox/case2/world_model_interaction_prompts/images/unitree_z1_stackbox/15.png new file mode 100644 index 0000000..2b7be22 Binary files /dev/null and b/unitree_z1_stackbox/case2/world_model_interaction_prompts/images/unitree_z1_stackbox/15.png differ diff --git a/unitree_z1_stackbox/case2/world_model_interaction_prompts/transitions/unitree_z1_stackbox/15.h5 b/unitree_z1_stackbox/case2/world_model_interaction_prompts/transitions/unitree_z1_stackbox/15.h5 new file mode 100644 index 0000000..4a71e9f Binary files /dev/null and b/unitree_z1_stackbox/case2/world_model_interaction_prompts/transitions/unitree_z1_stackbox/15.h5 differ diff --git a/unitree_z1_stackbox/case2/world_model_interaction_prompts/transitions/unitree_z1_stackbox/meta_data/stats.safetensors b/unitree_z1_stackbox/case2/world_model_interaction_prompts/transitions/unitree_z1_stackbox/meta_data/stats.safetensors new file mode 100644 index 0000000..1918ea0 Binary files /dev/null and b/unitree_z1_stackbox/case2/world_model_interaction_prompts/transitions/unitree_z1_stackbox/meta_data/stats.safetensors differ diff --git a/unitree_z1_stackbox/case2/world_model_interaction_prompts/unitree_z1_stackbox.csv b/unitree_z1_stackbox/case2/world_model_interaction_prompts/unitree_z1_stackbox.csv new file mode 100644 index 0000000..bde4468 --- /dev/null +++ b/unitree_z1_stackbox/case2/world_model_interaction_prompts/unitree_z1_stackbox.csv @@ -0,0 +1,2 @@ +videoid,contentUrl,duration,data_dir,instruction,dynamic_confidence,dynamic_wording,dynamic_source_category,embodiment,fps +15,x,x,unitree_z1_stackbox,"Pick up the red cup on the table.",x,x,x,Unitree Z1 Robot Arm,30 diff --git a/unitree_z1_stackbox/case3/run_world_model_interaction.sh b/unitree_z1_stackbox/case3/run_world_model_interaction.sh new file mode 100644 index 0000000..d92501c --- /dev/null +++ b/unitree_z1_stackbox/case3/run_world_model_interaction.sh @@ -0,0 +1,24 @@ +res_dir="unitree_z1_stackbox/case3" +dataset="unitree_z1_stackbox" + +{ + time CUDA_VISIBLE_DEVICES=0 python3 scripts/evaluation/world_model_interaction.py \ + --seed 123 \ + --ckpt_path ckpts/unifolm_wma_dual.ckpt \ + --config configs/inference/world_model_interaction.yaml \ + --savedir "${res_dir}/output" \ + --bs 1 --height 320 --width 512 \ + --unconditional_guidance_scale 1.0 \ + --ddim_steps 50 \ + --ddim_eta 1.0 \ + --prompt_dir "unitree_z1_stackbox/case3/world_model_interaction_prompts" \ + --dataset ${dataset} \ + --video_length 16 \ + --frame_stride 4 \ + --n_action_steps 16 \ + --exe_steps 16 \ + --n_iter 12 \ + --timestep_spacing 'uniform_trailing' \ + --guidance_rescale 0.7 \ + --perframe_ae +} 2>&1 | tee "${res_dir}/output.log" diff --git a/unitree_z1_stackbox/case3/unitree_z1_stackbox_case3.mp4 b/unitree_z1_stackbox/case3/unitree_z1_stackbox_case3.mp4 new file mode 100644 index 0000000..b256f3a Binary files /dev/null and b/unitree_z1_stackbox/case3/unitree_z1_stackbox_case3.mp4 differ diff --git a/unitree_z1_stackbox/case3/world_model_interaction_prompts/images/unitree_z1_stackbox/25.png b/unitree_z1_stackbox/case3/world_model_interaction_prompts/images/unitree_z1_stackbox/25.png new file mode 100644 index 0000000..1365fd5 Binary files /dev/null and b/unitree_z1_stackbox/case3/world_model_interaction_prompts/images/unitree_z1_stackbox/25.png differ diff --git a/unitree_z1_stackbox/case3/world_model_interaction_prompts/transitions/unitree_z1_stackbox/25.h5 b/unitree_z1_stackbox/case3/world_model_interaction_prompts/transitions/unitree_z1_stackbox/25.h5 new file mode 100644 index 0000000..27c0773 Binary files /dev/null and b/unitree_z1_stackbox/case3/world_model_interaction_prompts/transitions/unitree_z1_stackbox/25.h5 differ diff --git a/unitree_z1_stackbox/case3/world_model_interaction_prompts/transitions/unitree_z1_stackbox/meta_data/stats.safetensors b/unitree_z1_stackbox/case3/world_model_interaction_prompts/transitions/unitree_z1_stackbox/meta_data/stats.safetensors new file mode 100644 index 0000000..1918ea0 Binary files /dev/null and b/unitree_z1_stackbox/case3/world_model_interaction_prompts/transitions/unitree_z1_stackbox/meta_data/stats.safetensors differ diff --git a/unitree_z1_stackbox/case3/world_model_interaction_prompts/unitree_z1_stackbox.csv b/unitree_z1_stackbox/case3/world_model_interaction_prompts/unitree_z1_stackbox.csv new file mode 100644 index 0000000..a32f631 --- /dev/null +++ b/unitree_z1_stackbox/case3/world_model_interaction_prompts/unitree_z1_stackbox.csv @@ -0,0 +1,2 @@ +videoid,contentUrl,duration,data_dir,instruction,dynamic_confidence,dynamic_wording,dynamic_source_category,embodiment,fps +25,x,x,unitree_z1_stackbox,"Pick up the red cup on the table.",x,x,x,Unitree Z1 Robot Arm,30 diff --git a/unitree_z1_stackbox/case4/run_world_model_interaction.sh b/unitree_z1_stackbox/case4/run_world_model_interaction.sh new file mode 100644 index 0000000..054b175 --- /dev/null +++ b/unitree_z1_stackbox/case4/run_world_model_interaction.sh @@ -0,0 +1,24 @@ +res_dir="unitree_z1_stackbox/case4" +dataset="unitree_z1_stackbox" + +{ + time CUDA_VISIBLE_DEVICES=0 python3 scripts/evaluation/world_model_interaction.py \ + --seed 123 \ + --ckpt_path ckpts/unifolm_wma_dual.ckpt \ + --config configs/inference/world_model_interaction.yaml \ + --savedir "${res_dir}/output" \ + --bs 1 --height 320 --width 512 \ + --unconditional_guidance_scale 1.0 \ + --ddim_steps 50 \ + --ddim_eta 1.0 \ + --prompt_dir "unitree_z1_stackbox/case4/world_model_interaction_prompts" \ + --dataset ${dataset} \ + --video_length 16 \ + --frame_stride 4 \ + --n_action_steps 16 \ + --exe_steps 16 \ + --n_iter 12 \ + --timestep_spacing 'uniform_trailing' \ + --guidance_rescale 0.7 \ + --perframe_ae +} 2>&1 | tee "${res_dir}/output.log" diff --git a/unitree_z1_stackbox/case4/unitree_z1_stackbox_case4.mp4 b/unitree_z1_stackbox/case4/unitree_z1_stackbox_case4.mp4 new file mode 100644 index 0000000..f0beb01 Binary files /dev/null and b/unitree_z1_stackbox/case4/unitree_z1_stackbox_case4.mp4 differ diff --git a/unitree_z1_stackbox/case4/world_model_interaction_prompts/images/unitree_z1_stackbox/35.png b/unitree_z1_stackbox/case4/world_model_interaction_prompts/images/unitree_z1_stackbox/35.png new file mode 100644 index 0000000..67736af Binary files /dev/null and b/unitree_z1_stackbox/case4/world_model_interaction_prompts/images/unitree_z1_stackbox/35.png differ diff --git a/unitree_z1_stackbox/case4/world_model_interaction_prompts/transitions/unitree_z1_stackbox/35.h5 b/unitree_z1_stackbox/case4/world_model_interaction_prompts/transitions/unitree_z1_stackbox/35.h5 new file mode 100644 index 0000000..94322f7 Binary files /dev/null and b/unitree_z1_stackbox/case4/world_model_interaction_prompts/transitions/unitree_z1_stackbox/35.h5 differ diff --git a/unitree_z1_stackbox/case4/world_model_interaction_prompts/transitions/unitree_z1_stackbox/meta_data/stats.safetensors b/unitree_z1_stackbox/case4/world_model_interaction_prompts/transitions/unitree_z1_stackbox/meta_data/stats.safetensors new file mode 100644 index 0000000..1918ea0 Binary files /dev/null and b/unitree_z1_stackbox/case4/world_model_interaction_prompts/transitions/unitree_z1_stackbox/meta_data/stats.safetensors differ diff --git a/unitree_z1_stackbox/case4/world_model_interaction_prompts/unitree_z1_stackbox.csv b/unitree_z1_stackbox/case4/world_model_interaction_prompts/unitree_z1_stackbox.csv new file mode 100644 index 0000000..2f0bbc0 --- /dev/null +++ b/unitree_z1_stackbox/case4/world_model_interaction_prompts/unitree_z1_stackbox.csv @@ -0,0 +1,2 @@ +videoid,contentUrl,duration,data_dir,instruction,dynamic_confidence,dynamic_wording,dynamic_source_category,embodiment,fps +35,x,x,unitree_z1_stackbox,"Pick up the red cup on the table.",x,x,x,Unitree Z1 Robot Arm,30