Skip to content

Wrong example in ReadMe - train_LDM? #2

@Cerann

Description

@Cerann

Hi,

Shouldn't the execution path of training of the LDM be:

python -m src.python.training.train_ldm
--training_ids=../Data_Preprocessed/train.csv
--validation_ids=../Data_Preprocessed/validation.csv
--output_dir=/FARM/3D_CT_Synthesis/output
--run_dir=LDM_v1_py310
--batch_size=1
--eval_freq=10
--n_epochs=500
--num_workers=2
--config_vqvae=/FARM/3D_CT_Synthesis/medlord/configs/stage1/vqgan_ds4.yaml
--config_file=/FARM/3D_CT_Synthesis/medlord/configs/diffusion/ddpm.yaml
--vqvae_ckpt=/FARM/3D_CT_Synthesis/output/VQGAN_v1_py310/checkpoint.pth
--scale_factor=1.0

instead of what is given in the ReadMe?

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type
    No fields configured for issues without a type.

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions