Thank you for your response
This is the code for the dataset
class SLD_Labeled(Dataset):
def __init__(self):
self.root = "/home/ubuntu/workdir/data/real_stuff/"
self.image_dir = os.listdir(self.root+'images/')
self.bands = ['B02', 'B03', 'B04']
def __len__(self):
return len(self.image_dir)
def __getitem__(self, index):
subf = os.path.join(self.root, f'images/'+self.image_dir[index])
multiband = []
b = Image.open(subf).convert('RGB')
label_file = os.path.join(self.root, f'labels/{self.image_dir[index]}').replace('.jpg', '.tif')
label = np.array(Image.open(label_file).convert('P'))
if ':' in label_file:
#print('original image')
pass
else:
#print('In generated image')
label= np.where(label<128, 0, label)
label= np.where(label>127, 1, label)
bgr_images = np.array(b)
data_tensor = torch.from_numpy(np.transpose(bgr_images,(2, 1, 0))).float()
label_tensor = torch.from_numpy(label).long()
return data_tensor, label_tensor,str(self.image_dir[index])
The same dataset was used for Both the validation_data and supervised_data
I am trying to remove the validation_data indices that exist in the supervised data so I can have a subset that doesn’t contain the validation_data