Я работаю над набором данных Food-101, и, как вы, возможно, знаете, набор данных включает в себя как составные, так и испытательные части. Поскольку набор данных больше не может быть найден в ссылке ETH Zurich, мне пришлось разделить их на разделы <1 ГБ каждый и клонировать их в Colab и собрать заново. Это очень утомительная работа, но у меня все получилось. Я опущу код Python, но структура файла выглядит следующим образом: </p>
Food-101
images
train
...75750 train images
test
...25250 test images
meta
classes.txt
labes.txt
test.json
test.txt
train.json
train.txt
README.txt
license_agreement.txt
Следующий код показывает, что выдает ошибку времени выполнения
train_image_path = Path('images/train/')
test_image_path = Path('images/test/')
path = Path('../Food-101')
food_names = get_image_files(train_image_path)
file_parse = r'/([^/]+)_\d+\.(png|jpg|jpeg)'
data = ImageDataBunch.from_folder(train_image_path, test_image_path, valid_pct=0.2, ds_tfms=get_transforms(), size=224)
data.normalize(imagenet_stats)
Я предполагаю, что ImageDataBunch.from_folder() это то, что выдает ошибку, но я не знаю, почему она попадает в типы данных, так как (я не думаю) я предоставляю ей любые данные, которые имеют тип c.
/usr/local/lib/python3.6/dist-packages/torch/nn/functional.py:2854: UserWarning: The default behavior for interpolate/upsample with float scale_factor will change in 1.6.0 to align with other frameworks/libraries, and use scale_factor directly, instead of relying on the computed output size. If you wish to keep the old behavior, please set recompute_scale_factor=True. See the documentation of nn.Upsample for details.
warnings.warn("The default behavior for interpolate/upsample with float scale_factor will change "
/usr/local/lib/python3.6/dist-packages/torch/nn/functional.py:2854: UserWarning: The default behavior for interpolate/upsample with float scale_factor will change in 1.6.0 to align with other frameworks/libraries, and use scale_factor directly, instead of relying on the computed output size. If you wish to keep the old behavior, please set recompute_scale_factor=True. See the documentation of nn.Upsample for details.
warnings.warn("The default behavior for interpolate/upsample with float scale_factor will change "
/usr/local/lib/python3.6/dist-packages/torch/nn/functional.py:2854: UserWarning: The default behavior for interpolate/upsample with float scale_factor will change in 1.6.0 to align with other frameworks/libraries, and use scale_factor directly, instead of relying on the computed output size. If you wish to keep the old behavior, please set recompute_scale_factor=True. See the documentation of nn.Upsample for details.
warnings.warn("The default behavior for interpolate/upsample with float scale_factor will change "
/usr/local/lib/python3.6/dist-packages/torch/nn/functional.py:2854: UserWarning: The default behavior for interpolate/upsample with float scale_factor will change in 1.6.0 to align with other frameworks/libraries, and use scale_factor directly, instead of relying on the computed output size. If you wish to keep the old behavior, please set recompute_scale_factor=True. See the documentation of nn.Upsample for details.
warnings.warn("The default behavior for interpolate/upsample with float scale_factor will change "
/usr/local/lib/python3.6/dist-packages/torch/nn/functional.py:2854: UserWarning: The default behavior for interpolate/upsample with float scale_factor will change in 1.6.0 to align with other frameworks/libraries, and use scale_factor directly, instead of relying on the computed output size. If you wish to keep the old behavior, please set recompute_scale_factor=True. See the documentation of nn.Upsample for details.
warnings.warn("The default behavior for interpolate/upsample with float scale_factor will change "
/usr/local/lib/python3.6/dist-packages/torch/nn/functional.py:2854: UserWarning: The default behavior for interpolate/upsample with float scale_factor will change in 1.6.0 to align with other frameworks/libraries, and use scale_factor directly, instead of relying on the computed output size. If you wish to keep the old behavior, please set recompute_scale_factor=True. See the documentation of nn.Upsample for details.
warnings.warn("The default behavior for interpolate/upsample with float scale_factor will change "
/usr/local/lib/python3.6/dist-packages/torch/nn/functional.py:2854: UserWarning: The default behavior for interpolate/upsample with float scale_factor will change in 1.6.0 to align with other frameworks/libraries, and use scale_factor directly, instead of relying on the computed output size. If you wish to keep the old behavior, please set recompute_scale_factor=True. See the documentation of nn.Upsample for details.
warnings.warn("The default behavior for interpolate/upsample with float scale_factor will change "
You can deactivate this warning by passing `no_check=True`.
/usr/local/lib/python3.6/dist-packages/fastai/basic_data.py:262: UserWarning: There seems to be something wrong with your dataset, for example, in the first batch can't access these elements in self.train_ds: 9600,37233,16116,38249,1826...
warn(warn_msg)
---------------------------------------------------------------------------
RuntimeError Traceback (most recent call last)
/usr/local/lib/python3.6/dist-packages/IPython/core/formatters.py in __call__(self, obj)
697 type_pprinters=self.type_printers,
698 deferred_pprinters=self.deferred_printers)
--> 699 printer.pretty(obj)
700 printer.flush()
701 return stream.getvalue()
11 frames
/usr/local/lib/python3.6/dist-packages/fastai/vision/image.py in affine(self, func, *args, **kwargs)
181 "Equivalent to `image.affine_mat = image.affine_mat @ func()`."
182 m = tensor(func(*args, **kwargs)).to(self.device)
--> 183 self.affine_mat = self.affine_mat @ m
184 return self
185
RuntimeError: Expected object of scalar type Float but got scalar type Double for argument #3 'mat2' in call to _th_addmm_out