Help me about 01_intro - cuda runtime error (801)

I run ‘intro lesson’ code in windows env.

I run underline code very well ( dls input num_workers=0):

from fastai.vision.all import *
path = untar_data(URLs.PETS)/‘images’

def is_cat(x): return x[0].isupper()
dls = ImageDataLoaders.from_name_func(
path, get_image_files(path), valid_pct=0.2, seed=42,
label_func=is_cat, item_tfms=Resize(224),num_workers=0)

learn = cnn_learner(dls, resnet34, metrics=error_rate)
learn.fine_tune(1)


but i run under code wrong( RuntimeError: cuda runtime error (801) : operation not supported at …\torch/csrc/generic/StorageSharing.cpp:247):
path = untar_data(URLs.CAMVID_TINY)
dls = SegmentationDataLoaders.from_label_func(
path, bs=8, fnames = get_image_files(path/“images”),
label_func = lambda o: path/‘labels’/f’{o.stem}_P{o.suffix}’,
codes = np.loadtxt(path/‘codes.txt’, dtype=str)
)

learn = unet_learner(dls, resnet34)
learn.fine_tune(8)

Somebody can help me !

somebody can help?

I’m not sure I can help but you need to put the full stack trace so we can know which line and function is causing the error.

First case is a data loader for image classification with normal CNN while second case is of a data loader for semantic segmentation with autoencoder like CNN. So data loading, model and the learners are different so it’s not possible to figure out what’s wrong from the info you have given.