RuntimeError: The size of tensor a (1025) must match the size of tensor b (257) at non-singleton dimension 1

[ArnabPurk]

I am using the library to run Semi supervised models on my dataset i used the custom dataset code given in google colab and converted my dataset images to csv when i run the code to train the dataset i get RuntimeError: The size of tensor a (1025) must match the size of tensor b (257) at non-singleton dimension 1 error i am giving the code below please give me possible solutions `config = { 'algorithm': 'fixmatch', 'net': 'vit_tiny_patch2_32', 'use_pretrain': True, 'pretrain_path': 'https://github.com/microsoft/Semi-supervised-learning/releases/download/v.0.0.0/vit_tiny_patch2_32_mlp_im_1k_32.pth',

# Optimization configs
'epoch': 50,
'num_train_iter': 5000,
'num_eval_iter': 1000,
'num_log_iter': 50,
'optim': 'AdamW',
'lr': 5e-4,
'layer_decay': 0.5,
'batch_size': 16,
'eval_batch_size': 16,

# Dataset configs
'dataset': 'custom',
'num_labels': 3500,
'num_classes': 7,
'img_size': 64,
'crop_ratio': 0.875,
'data_dir': '/kaggle/input/augmented-balanced/augmented_balanced_splitted',  # Change this to your main folder path

# Algorithm specific configs
'hard_label': True,
'uratio': 2,
'ulb_loss_ratio': 1.0,

# Device configs
'gpu': 0,
'world_size': 1,
'num_workers': 2,
'distributed': False,

} config = get_config(config)

create model and specify algorithm

algorithm = get_algorithm(config, get_net_builder(config.net, from_name=False), tb_log=None, logger=None) image_data = df.drop("label", axis=1).values data = image_data.reshape((-1, 64, 64, 3)) data = np.uint8(data) target = df["label"] lb_data, lb_target, ulb_data, ulb_target = split_ssl_data(config, data, target, 7, config.num_labels, include_lb_to_ulb=False) train_transform = transforms.Compose([transforms.ToTensor(), transforms.Normalize([0.5, 0.5, 0.5], [0.5, 0.5, 0.5])])

train_strong_transform = transforms.Compose([transforms.ToTensor(), transforms.Normalize([0.5, 0.5, 0.5], [0.5, 0.5, 0.5])])

lb_dataset = BasicDataset(config.algorithm, lb_data, lb_target, config.num_classes, train_transform, is_ulb=False) ulb_dataset = BasicDataset(config.algorithm, lb_data, lb_target, config.num_classes, train_transform, is_ulb=True, strong_transform=train_strong_transform) df2=pd.read_csv("/kaggle/input/unnormalized-64x64/image_data_64x64_validation.csv") df2['label'] = df2['label'].astype(int) image_data2 = df2.drop("label", axis=1).values eval_data = image_data2.reshape((-1, 64, 64, 3)) data = np.uint8(data) eval_target = df2["label"] eval_transform = transforms.Compose([transforms.ToTensor(), transforms.Normalize([0.5, 0.5, 0.5], [0.5, 0.5, 0.5])])

eval_dataset = BasicDataset(config.algorithm, eval_data, eval_target, config.num_classes, eval_transform, is_ulb=False)

define data loaders

train_lb_loader = get_data_loader(config, lb_dataset, config.batch_size) train_ulb_loader = get_data_loader(config, ulb_dataset, int(config.batch_size * config.uratio)) eval_loader = get_data_loader(config, eval_dataset, config.eval_batch_size)

training and evaluation

trainer = Trainer(config, algorithm) trainer.fit(train_lb_loader, train_ulb_loader, eval_loader)`