How to convert pixel value numpy array of images into ImageDataBunch object

[srinivas365 (Mannem Srinivas)]

I have a csv file which contains pixel values of images along the columns. I want to convert those into ImageDataBunch object for training. As I am beginner I didn’t find the solution yet.

Thanks in advance

[stewshka]

Data_Block_API to read numpy Arrays

I’m not sure if you are looking for something like this, but i managed to load image data previously saved as Tensor (could be numpy array / txt) class CustomImageItemList(ImageItemList): def open(self, fn): return Image(torch.load(fn)) lst = CustomImageItemList.from_folder(Path('clean_pt'), '.pt')

[srinivas365 (Mannem Srinivas)]

I have a .csv file with labels as first column and image pixels values along the columns in Out[3] .I want to transform this into ImageDataBunch object for training

Thanks in advance