TypeError: default_collate: batch must contain tensors, numpy arrays, numbers, dicts or lists; found <class 'PIL.Image.Image'>
The error states that the DataLoader receives a PIL image.
This is because there are no transforms made (transform=None) on the image.
You can add a transform that creates a tensor from the PIL image by adding transform:
from torchvision import transforms
transform = transforms.Compose([
# you can add other transformations in this list
transforms.ToTensor()
])
Are there any code examples left?
New code examples in category TypeScript
Relative searches
TypeError: default_collate: batch must contain tensors, numpy arrays, numbers, dicts or lists; found <class 'mmcv.parallel.data_container.DataContainer'>
pytorch mnist TypeError: default_collate: batch must contain tensors, numpy arrays, numbers, dicts or lists; found <class 'PIL.Image.Image'>
TypeError: default_collate: batch must contain tensors, numpy arrays, numbers, dicts or lists; found <class 'dataset.MICCDataset'>
TypeError: default_collate: batch must contain tensors, numpy arrays, numbers, dicts or lists; found object
TypeError: default_collate: batch must contain tensors, numpy arrays, numbers, dicts or lists; found <class 'PIL.Image.Image'> site:stackoverflow.com
TypeError: default_collate: batch must contain tensors, numpy arrays, numbers, dicts or lists; found <class 'PIL.JpegImagePlugin.JpegImageFile'>
default_collate: batch must contain tensors, numpy arrays, numbers, dicts or lists; found <class 'PIL.JpegImagePlugin.JpegImageFile'>
default_collate: batch must contain tensors, numpy arrays, numbers, dicts or lists; found <class 'pathlib.PosixPath'>
TypeError: default_collate: batch must contain tensors, numpy arrays, numbers, dicts or lists; found <class 'torchvision.transforms.transforms.Compose'>
pytorch batch must contain tensors, numpy arrays, numbers, dicts or lists; found <class 'PIL.Image.Image'>
default_collate: batch must contain tensors, numpy arrays, numbers, dicts or lists; found <class 'PIL.Image.Image'>
batch must contain tensors, numpy arrays, numbers, dicts or lists; found <class 'PIL.Image
TypeError: default_collate: batch must contain tensors, numpy arrays, numbers, dicts or lists; found <class 'pandas.core.series.Series'>
default_collate: batch must contain tensors, numpy arrays, numbers, dicts or lists; found <class 'torchvision.transforms.transforms.ToTensor'
default_collate: batch must contain tensors, numpy arrays, numbers, dicts or lists; found <class 'torchvision.transforms.transforms.ToTensor'>
TypeError: default_collate: batch must contain tensors, numpy arrays, numbers, dicts or lists; found <class 'NoneType'>
TypeError: default_collate: batch must contain tensors, numpy arrays, numbers, dicts or lists; found <U6
TypeError: default_collate: batch must contain tensors, numpy arrays, numbers, dicts or lists; found <class 'PIL.Image.Image'>
TypeError: batch must contain tensors, numbers, dicts or lists; found <class 'PIL.Image.Image'>
TypeError: default_collate: batch must contain tensors, numpy arrays, numbers, dicts or lists; found
