Ejemplos de identity_loss_fn en Python

Ejemplo n.º 1

# how many times we send stats to tensorboard
n_stats_to_tensorboard = args.crayon_send_stats_iters
logger.info(f"Sending stats to tensorboard every {n_stats_to_tensorboard} iterations")

# how many times we save model
n_save: int = round(args.n_train / args.n_models_saved)
logger.info(f"Save models every {n_save} iterations, for a total of {args.n_models_saved}")

# initialize potentials to 0
for iteration, data_dict in enumerate(dataloader_init):
    X = data_dict["X"].squeeze(dim=0)
    Y = data_dict["Y"].squeeze(dim=0)

    torch_losses = {
        "potential_u_initialization_loss": identity_loss_fn(0.0, potential_u(X)),
        "potential_v_initialization_loss": identity_loss_fn(0.0, potential_v(Y))
    }

    torch_losses_take_step(loss_dict=torch_losses,
                           optimizer=opt_potential,
                           loss_names=["potential_u_initialization_loss",
                                       "potential_v_initialization_loss"])
    
    roll_average(loss_dict=torch_losses, mets_dict=mets,
                 metrics=["potential_u_initialization_loss",
                          "potential_v_initialization_loss"],
                 iteration=iteration)

    if (iteration + 1) % n_stats_to_tensorboard == 0:
        crayon_ship_metrics(ccexp, mets, ["identity_loss"],

Ejemplo n.º 2

n_stats_to_tensorboard = args.crayon_send_stats_iters
logger.info(
    f"Sending stats to tensorboard every {n_stats_to_tensorboard} iterations")

# how many times we save model
n_save: int = round(args.n_train / args.n_models_saved)
logger.info(
    f"Save models every {n_save} iterations, for a total of {args.n_models_saved}"
)

# initialize network to the identity
for iteration, data_dict in enumerate(dataloader_init):
    X = data_dict["X"].squeeze(dim=0)
    TX = neural_map(X)

    torch_losses = {"identity_loss": identity_loss_fn(X, TX)}

    torch_losses_take_step(loss_dict=torch_losses,
                           optimizer=opt_tm,
                           loss_names=["identity_loss"])

    roll_average(loss_dict=torch_losses,
                 mets_dict=mets,
                 metrics=["identity_loss"],
                 iteration=iteration)

    if (iteration + 1) % n_stats_to_tensorboard == 0:
        crayon_ship_metrics(ccexp, mets, ["identity_loss"], iteration)

# iterations to evaluate on
eval_iters: List[int] = []

Ejemplo n.º 3

Archivo: heuristic_discr_w_tpreg_flow.py Proyecto: salayatana66/learn_to_transport_code

# how many times we send stats to tensorboard
n_stats_to_tensorboard = args.crayon_send_stats_iters
logger.info(f"Sending stats to tensorboard every {n_stats_to_tensorboard} iterations")

# how many times we save model
n_save: int = round(args.n_train / args.n_models_saved)
logger.info(f"Save models every {n_save} iterations, for a total of {args.n_models_saved}")

# initialize network to the identity
for iteration, data_dict in enumerate(dataloader_init):
    X = data_dict["X"].squeeze(dim=0)
    TX = neural_map(X)

    torch_losses = {
        "identity_loss" : identity_loss_fn(X, TX)
        }

    torch_losses_take_step(loss_dict=torch_losses,
                           optimizer=opt_tm,
                           loss_names=["identity_loss"])
    
    roll_average(loss_dict=torch_losses, mets_dict=mets,
                 metrics=["identity_loss"],
                 iteration=iteration)

    if (iteration + 1) % n_stats_to_tensorboard == 0:
        crayon_ship_metrics(ccexp, mets, ["identity_loss"],
                            iteration)

# iterations to evaluate on