import argparse
import os





def parse_args():
    parser = argparse.ArgumentParser(description="Simple example of a training script.")
    parser.add_argument(
        "--dataset_name",
        type=str,
        default=None,
        help=(
            "The name of the Dataset (from the HuggingFace hub) to train on (could be your own, possibly private,"
            " dataset). It can also be a path pointing to a local copy of a dataset in your filesystem,"
            " or to a folder containing files that HF Datasets can understand."
        ),
    )
    parser.add_argument(
        "--dataset_config_name",
        type=str,
        default=None,
        help="The config of the Dataset, leave as None if there's only one config.",
    )
    parser.add_argument(
        "--model_config_name_or_path",
        type=str,
        default=None,
        help="The config of the UNet model to train, leave as None to use standard DDPM configuration.",
    )
    parser.add_argument(
        "--train_data_dir",
        type=str,
        default=None,
        help=(
            "A folder containing the training data. Folder contents must follow the structure described in"
            " https://huggingface.co/docs/datasets/image_dataset#imagefolder. In particular, a `metadata.jsonl` file"
            " must exist to provide the captions for the images. Ignored if `dataset_name` is specified."
        ),
    )
    parser.add_argument(
        "--output_dir",
        type=str,
        default="ddpm-model-64",
        help="The output directory where the model predictions and checkpoints will be written.",
    )
    parser.add_argument("--overwrite_output_dir", action="store_true")
    parser.add_argument(
        "--cache_dir",
        type=str,
        default=None,
        help="The directory where the downloaded models and datasets will be stored.",
    )
    parser.add_argument(
        "--resolution",
        type=int,
        default=64,
        help=(
            "The resolution for input images, all the images in the train/validation dataset will be resized to this"
            " resolution"
        ),
    )
    parser.add_argument(
        "--center_crop",
        default=False,
        action="store_true",
        help=(
            "Whether to center crop the input images to the resolution. If not set, the images will be randomly"
            " cropped. The images will be resized to the resolution first before cropping."
        ),
    )
    parser.add_argument(
        "--random_flip",
        default=False,
        action="store_true",
        help="whether to randomly flip images horizontally",
    )
    parser.add_argument(
        "--train_batch_size", type=int, default=64, help="Batch size (per device) for the training dataloader."
    )
    parser.add_argument(
        "--eval_batch_size", type=int, default=2, help="The number of images to generate for evaluation."
    )
    parser.add_argument(
        "--dataloader_num_workers",
        type=int,
        default=0,
        help=(
            "The number of subprocesses to use for data loading. 0 means that the data will be loaded in the main"
            " process."
        ),
    )
    parser.add_argument("--num_epochs", type=int, default=1000)
    parser.add_argument("--save_images_epochs", type=int, default=1000, help="How often to save images during training.")
    parser.add_argument(
        "--save_model_epochs", type=int, default=1, help="How often to save the model during training."
    )
    parser.add_argument(
        "--gradient_accumulation_steps",
        type=int,
        default=1,
        help="Number of updates steps to accumulate before performing a backward/update pass.",
    )
    parser.add_argument(
        "--learning_rate",
        type=float,
        default=1e-4,
        help="Initial learning rate (after the potential warmup period) to use.",
    )
    parser.add_argument(
        "--lr_scheduler",
        type=str,
        default="cosine",
        help=(
            'The scheduler type to use. Choose between ["linear", "cosine", "cosine_with_restarts", "polynomial",'
            ' "constant", "constant_with_warmup"]'
        ),
    )
    parser.add_argument(
        "--lr_warmup_steps", type=int, default=500, help="Number of steps for the warmup in the lr scheduler."
    )
    parser.add_argument("--adam_beta1", type=float, default=0.95, help="The beta1 parameter for the Adam optimizer.")
    parser.add_argument("--adam_beta2", type=float, default=0.999, help="The beta2 parameter for the Adam optimizer.")
    parser.add_argument(
        "--adam_weight_decay", type=float, default=1e-6, help="Weight decay magnitude for the Adam optimizer."
    )
    parser.add_argument("--adam_epsilon", type=float, default=1e-08, help="Epsilon value for the Adam optimizer.")
    parser.add_argument(
        "--use_ema",
        action="store_true",
        help="Whether to use Exponential Moving Average for the final model weights.",
    )
    parser.add_argument("--ema_inv_gamma", type=float, default=1.0, help="The inverse gamma value for the EMA decay.")
    parser.add_argument("--ema_power", type=float, default=3 / 4, help="The power value for the EMA decay.")
    parser.add_argument("--ema_max_decay", type=float, default=0.9999, help="The maximum decay magnitude for EMA.")
    parser.add_argument("--push_to_hub", action="store_true", help="Whether or not to push the model to the Hub.")
    parser.add_argument("--hub_token", type=str, default=None, help="The token to use to push to the Model Hub.")
    parser.add_argument(
        "--hub_model_id",
        type=str,
        default=None,
        help="The name of the repository to keep in sync with the local `output_dir`.",
    )
    parser.add_argument(
        "--hub_private_repo", action="store_true", help="Whether or not to create a private repository."
    )
    parser.add_argument(
        "--logger",
        type=str,
        default="tensorboard",
        choices=["tensorboard", "wandb"],
        help=(
            "Whether to use [tensorboard](https://www.tensorflow.org/tensorboard) or [wandb](https://www.wandb.ai)"
            " for experiment tracking and logging of model metrics and model checkpoints"
        ),
    )
    parser.add_argument(
        "--logging_dir",
        type=str,
        default="logs",
        help=(
            "[TensorBoard](https://www.tensorflow.org/tensorboard) log directory. Will default to"
            " *output_dir/runs/**CURRENT_DATETIME_HOSTNAME***."
        ),
    )
    parser.add_argument("--local_rank", type=int, default=-1, help="For distributed training: local_rank")
    parser.add_argument(
        "--mixed_precision",
        type=str,
        default="no",
        choices=["no", "fp16", "bf16"],
        help=(
            "Whether to use mixed precision. Choose"
            "between fp16 and bf16 (bfloat16). Bf16 requires PyTorch >= 1.10."
            "and an Nvidia Ampere GPU."
        ),
    )
    parser.add_argument(
        "--prediction_type",
        type=str,
        default="epsilon",
        choices=["epsilon", "sample"],
        help="Whether the model should predict the 'epsilon'/noise error or directly the reconstructed image 'x0'.",
    )
    parser.add_argument("--ddpm_num_steps", type=int, default=1000)
    parser.add_argument("--ddpm_num_inference_steps", type=int, default=250)
    parser.add_argument("--ddpm_beta_schedule", type=str, default="linear")
    parser.add_argument(
        "--checkpointing_steps",
        type=int,
        default=500,
        help=(
            "Save a checkpoint of the training state every X updates. These checkpoints are only suitable for resuming"
            " training using `--resume_from_checkpoint`."
        ),
    )
    parser.add_argument(
        "--checkpoints_total_limit",
        type=int,
        default=None,
        help=("Max number of checkpoints to store."),
    )
    parser.add_argument(
        "--resume_from_checkpoint",
        type=str,
        default=None,
        help=(
            "Whether training should be resumed from a previous checkpoint. Use a path saved by"
            ' `--checkpointing_steps`, or `"latest"` to automatically select the last available checkpoint.'
        ),
    )
    parser.add_argument(
        "--enable_xformers_memory_efficient_attention", action="store_true", help="Whether or not to use xformers."
    )

    parser.add_argument("--train_or_test", type=str, default='train', help="train or test")
    parser.add_argument("--test_samples", type=int, default=1, help="test_samples")
    parser.add_argument("--seed", type=int, default=0, help="seed")
    parser.add_argument("--noise_type", type=str, default='gaussian', help="gaussian, gaussianBN, gaussianRN")
    parser.add_argument("--out_channels", type=int, default=3, help="out_channels")
    parser.add_argument("--use_vae", action="store_true", help="Whether or not to use vae for latent diffusion")


    parser.add_argument("--optimize_scheduler_param", action="store_true", help="whether to optimize scheduler_param")
    parser.add_argument("--scheduler_gamma", type=str, default='linear', help="scheduler type")
    parser.add_argument('--scheduler_param', type=float, default=0.02, help='scheduler parameter for scheduler_gamma')
    parser.add_argument('--scheduler_param_s', type=float, default=0, help='scheduler parameter for scheduler_gamma')
    parser.add_argument('--scheduler_param_e', type=float, default=3, help='scheduler parameter for scheduler_gamma')

    
    args = parser.parse_args()
    env_local_rank = int(os.environ.get("LOCAL_RANK", -1))
    if env_local_rank != -1 and env_local_rank != args.local_rank:
        args.local_rank = env_local_rank

    if args.dataset_name is None and args.train_data_dir is None:
        raise ValueError("You must specify either a dataset name from the hub or a train data directory.")

    return args