evaluate.sh

export PYTHONWARNINGS="ignore"
export CUDA_VISIBLE_DEVICES=4,5,6,7

# export NCCL_DEBUG=INFO
# export TORCH_NCCL_ASYNC_ERROR_HANDLING=1
# export TORCH_DISTRIBUTED_DEBUG=DETAIL
# export NCCL_DEBUG_SUBSYS=COLL
# # Optional but very helpful while debugging (slower):
# export TORCH_NCCL_BLOCKING_WAIT=1
export NCCL_TIMEOUT=7200
export NCCL_P2P_DISABLE=1
export HYDRA_FULL_ERROR=1

wandb offline
python -m main +name=infer \
    experiment.tasks=[test] \
    dataset.validation_multiplier=1 \
    +dataset.seed=42 \
    +diffusion_model_path=/share_1/users/bonan_ding/worldmem_ckpt/diffusion_only.ckpt \
    +vae_path=/share_1/users/bonan_ding/worldmem_ckpt/vae_only.ckpt \
    +customized_load=true \
    +seperate_load=true \
    dataset.n_frames=8 \
    dataset.save_dir=/share_1/users/bonan_ding/worldmem_data/minecraft \
    +dataset.n_frames_valid=700 \
    algorithm.diffusion.sampling_timesteps=20 \
    +algorithm.memory_condition_length=8 \
    +algorithm.lpips_batch_size=16 \
    +algorithm.log_video=true \
    +algorithm.save_local=true \
    +dataset.customized_validation=true \
    +algorithm.n_tokens=8 \
    algorithm.context_frames=600 \
    experiment.test.batch_size=1 \
    experiment.test.limit_batch=160 \