How should I apply the transform_train to my train_loader or train_dataset here?
rgb_mean = (97.13, 97.15, 97.15)
rgb_std = (28.74, 28.79, 28.8)
transform_train = transforms.Compose([
transforms.RandomHorizontalFlip(),
transforms.ToTensor(),
transforms.Normalize(rgb_mean, rgb_std),
])
class MothLandmarksDataset(Dataset):
"""Face Landmarks dataset."""
def __init__(self, csv_file, root_dir, transform=None):
"""
Args:
csv_file (string): Path to the csv file with annotations.
root_dir (string): Directory with all the images.
transform (callable, optional): Optional transform to be applied
on a sample.
"""
self.landmarks_frame = pd.read_csv(csv_file)
self.root_dir = root_dir
self.transform = transform
def __len__(self):
return len(self.landmarks_frame)
def __getitem__(self, idx):
if torch.is_tensor(idx):
idx = idx.tolist()
img_name = os.path.join(self.root_dir, self.landmarks_frame.iloc[idx, 0])
image = io.imread(img_name)
landmarks = self.landmarks_frame.iloc[idx, 1:]
landmarks = np.array([landmarks])
landmarks = landmarks.astype('float').reshape(-1, 2)
sample = {'image': image, 'landmarks': landmarks}
if self.transform:
sample = self.transform(sample)
return sample
dataset = MothLandmarksDataset('moth_gt.csv', '.', transform=transform_train)
# Device configuration
device = torch.device('cuda:0' if torch.cuda.is_available() else 'cpu')
seed = 42
np.random.seed(seed)
torch.manual_seed(seed)
# split the dataset into validation and test sets
len_valid_set = int(0.1*len(dataset))
len_train_set = len(dataset) - len_valid_set
train_dataset , valid_dataset, = torch.utils.data.random_split(dataset , [len_train_set, len_valid_set])
# shuffle and batch the datasets
train_loader = torch.utils.data.DataLoader(train_dataset, batch_size=8, shuffle=True, num_workers=4)
test_loader = torch.utils.data.DataLoader(valid_dataset, batch_size=8, shuffle=True, num_workers=4)
The main problem with above code is I cannot segregate the transform_train and transform_test. How can I differentiate them in MothLandmarksDataset? Mainly I think the problem happens because MothLandmarksDataset is instantiated on the whole dataset
not train_dataset or test_dataset. Any help is really appreciated.