Hello, I use gid data and use the FCEFModule model to train, but the following error is reported. Is it because of a version problem? thanks

[xjellyx]

there is my code

import torch
import torch.nn as nn
import pytorch_lightning as pl
from torchrs.datasets import GID15
from torchrs.train.modules import FCEFModule
from torchrs.train.datamodules import GID15DataModule
from torchrs.transforms import Compose, ToTensor


def collate_fn(batch):
    x = torch.stack([x["x"] for x in batch])
    y = torch.cat([x["mask"] for x in batch])
    x = x.to(torch.float32)
    y = y.to(torch.long)
    return x, y

transform = Compose([ToTensor()])

dm = GID15DataModule(
    root="./datasets/gid-15",
    transform=transform,
    batch_size=128,
    num_workers=1,
    prefetch_factor=1,
    collate_fn=collate_fn,
    test_collate_fn=collate_fn,
)


model = FCEFModule(channels=3, t=2, num_classes=15, lr=1E-3)


callbacks = [
    pl.callbacks.ModelCheckpoint(monitor="val_loss", mode="min", verbose=True, save_top_k=1),
    pl.callbacks.EarlyStopping(monitor="val_loss", mode="min", patience=10)
]

trainer = pl.Trainer(
    gpus=1,
    precision=16,
    accumulate_grad_batches=1,
    max_epochs=25,
    callbacks=callbacks,
    weights_summary="top"
)
#
trainer.fit(model, datamodule=dm)
trainer.test(datamodule=dm)

Error

[isaaccorley]

FCEF is a model for change detection. The GID-15 dataset is just a semantic segmentation dataset. I would recommend using the segmentation_models_pytorch U-Net model instead (smp.Unet).

[xjellyx]

thanks