data = ImageItemList
.from_df(df, path, folder=“train”, cols=0, suffix=".png")
.label_from_df(cols=1, sep=" ")
How to set shuffle=False of train and val?
The validation dataset always uses shuffle=False. If you want the training dataloader to use shuffle=False, there’s no direct argument but you can type
data.train_dl = data.train_dl.new(shuffle=False) after creating the DataBunch.
Hi @sgugger and @Bohdan ,
I am using Databunch.create() using the following lines of code:
ds_train = PyTorchDataset('fld/training/', batch_size = 8)
ds_val = PyTorchDataset('fld/alidation/', batch_size = 8)
from torch.nn.modules.loss import CrossEntropyLoss
model = BaseCNN(n_channels = 1, n_classes = 2)
loss_func = CrossEntropyLoss(weight = torch.Tensor([0.1,0.9]))
data = DataBunch.create(ds_train,ds_val,collate_fn=cnn_collate,path="fld/")
The create function raised the following error:
ValueError: DataLoader with IterableDataset: expected unspecified shuffle option, but got shuffle=True
I don’t know what I am missing out. Can you please help me with that. Thanks in advance.
v1 will not support
IterableDataset, only regular datasets with a length and getitem. You can still create your dataloaders by hand then pass them to the init of
Not sure of your error since you only give part of the stack trace but you should try to add
fix_dl=train_dl in your call to
DataBunch. It’s trying to create it for internal purposes by using our monkey-patch of the PyTorch
DataLoader, but that monkey-patch isn’t compatible with your dataloader class.
@sgugger, Just saw this after posting the trace, would try with that
Thanks it works . Appreciate the help.
Can you guys send the code where you achieved shuffle= true for fastai v1.
And does the shuffling work while training or before the training the imagedatabunch is created by shuffling the data it takes , which is the way , I’m using Fastaiv1.