Hi,
I am very new in the Deep learning and Pytorch platform. I have started a project related to image classification with CNN , for this reason I would like to load my custom data set( a folder which contain 4000 numpy files) In Pytorch. I used DatasetFolder as a reference. But I am unable to load my dataset.
Here is my code
import torch
import torchvision
from torch.utils.data import DataLoader, Sampler
from torchvision import datasets
from torchvision.transforms import transforms
import matplotlib.pyplot as plt
import numpy as np
DATA_TRAIN = '/home/mchow/Downloads/homework/data/pp'
def npy_loader(path):
sample = torch.from_numpy(np.load(path))
return sample
#
dataset = datasets.DatasetFolder(
root='DATA_TRAIN',
loader=npy_loader,
extensions=['.npy']
)
But I got the following errors.I could not solve this problem.
Traceback (most recent call last):
File "<input>", line 1, in <module>
File "/home/mchow/Downloads/pycharm-professional-2019.1.3/pycharm-2019.1.3/helpers/pydev/_pydev_bundle/pydev_umd.py", line 197, in runfile
pydev_imports.execfile(filename, global_vars, local_vars) # execute the script
File "/home/mchow/Downloads/pycharm-professional-2019.1.3/pycharm-2019.1.3/helpers/pydev/_pydev_imps/_pydev_execfile.py", line 18, in execfile
exec(compile(contents+"\n", file, 'exec'), glob, loc)
File "/home/mchow/Downloads/Assignment 3.py", line 29, in <module>
extensions=['.npy']
File "/home/mchow/miniconda3/lib/python3.6/site-packages/torchvision/datasets/folder.py", line 75, in __init__
classes, class_to_idx = find_classes(root)
File "/home/mchow/miniconda3/lib/python3.6/site-packages/torchvision/datasets/folder.py", line 23, in find_classes
classes = [d for d in os.listdir(dir) if os.path.isdir(os.path.join(dir, d))]
FileNotFoundError: [Errno 2] No such file or directory: 'DATA_TRAIN'
I will be very grateful,if any one help me out .