ValueError: too many values to unpack (expected 2) when using multi_clip input

I used this script to generate multi clip input for my validation process

    class ActionDatasetMultiClips(ActionDataset):
    def __loading(self, path, frame_indices):
        clips = []
        for clip_frame_indices in frame_indices:
            
            valid_indices = [i for i in clip_frame_indices if i < len(path)]
            if not valid_indices:
                raise ValueError(f"No valid frame indices for clip: {clip_frame_indices}")
            clip = [Image.open(path[i]).convert('RGB') for i in valid_indices]
            if self.spatial_transform is not None:
                self.spatial_transform.randomize_parameters()
                clip = [self.spatial_transform(img) for img in clip]
            clips.append(torch.stack(clip, 0))
        return clips

    def __getitem__(self, idx):
      sequence_key = list(self.sequences.keys())[idx]
      sequence_data = self.sequences[sequence_key]

   
      frame_paths = [data['image_path'] for data in sequence_data]
    
   
      if self.temporal_transform:
        frame_indices = list(range(len(frame_paths))) 
        frame_indices = self.temporal_transform(frame_indices) 
        
        
        if isinstance(frame_indices[0], list):
            frame_indices = [i for sublist in frame_indices for i in sublist]
        

        frame_indices = [i for i in frame_indices if i < len(frame_paths)]
        if not frame_indices:
            raise ValueError(f"No valid frame indices for sequence {sequence_key}")
                
  
      clips = self.__loading(frame_paths, [frame_indices])


      action_name = sequence_data[0]['action_name']
      condition = sequence_data[0]['condition']
      action_name_id = self.action_name_to_id[action_name]
      condition_id = self.condition_name_to_id[condition]

     
      targets = [torch.tensor([action_name_id, condition_id], dtype=torch.long) for _ in range(len(clips))]
      print(f"Number of clips: {len(clips)}")
      print(f"Number of targets: {len(targets)}")

      return clips, targets

and this is the collate_fn to flatten the input


def collate_fn(batch):
    batch_clips, batch_targets = zip(*batch)
    
    print(f"Batch size: {len(batch)}")
    print(f"Number of clips in batch: {len(batch_clips)}")
    print(f"Number of targets in batch: {len(batch_targets)}")
    # Flatten the clips and targets
    batch_clips = [clip for multi_clips in batch_clips for clip in multi_clips]
    batch_targets = [target for multi_targets in batch_targets for target in multi_targets]
    
    print(f"Flattened clips: {len(batch_clips)}")
    print(f"Flattened targets: {len(batch_targets)}")
    # Stack clips into a single tensor
    batch_clips = torch.stack(batch_clips, 0)

    # Stack targets into a single tensor
    batch_targets = torch.stack(batch_targets, 0)

    return batch_clips, batch_targets

i tried to print the output of the dataloader
i got this

for batch_idx, (data, target) in enumerate(val_loader):
    print(f"\nBatch {batch_idx}: Data Shape: {data.shape}, Target: {target}")
    break  # Stop after one batch for debugging purposes

Number of clips: 1
Number of targets: 1
Number of clips: 1
Number of targets: 1
Batch size: 2
Number of clips in batch: 2
Number of targets in batch: 2
Flattened clips: 2
Flattened targets: 2

Batch 0: Data Shape: torch.Size([2, 32, 3, 224, 224]), Target: tensor([[0, 1],
        [1, 1]])

but when I perform the validation an error occures saying

Traceback (most recent call last):                       

  File ~\anaconda3\envs\cnnsvm\Lib\site-packages\spyder_kernels\customize\utils.py:209 in exec_encapsulate_locals
    exec_fun(compile(code_ast, filename, "exec"), globals)

  File d:\organized_files\transformer_exemple\train.py:164
    val_loss, val_action_acc, val_condition_acc = validate_one_epoch(

  File d:\organized_files\transformer_exemple\utils.py:85 in validate_one_epoch
    for frames, labels in tqdm(dataloader, desc="Validation", leave=False):

ValueError: too many values to unpack (expected 2)

I assume the training loop works fine?
If so, are you using the same Dataset and DataLoader (including the same collate_fn)?

yes the training loop works fine
but no i am not using the same dataset and dataloader for the training and validation
for the training i used a dataset that loads a sequence and then performed subsampling to get frames distributed accross all the sequence so for the input it’s just one sequence(clip)
and for the validation i used another dataset with a costum collate_fn to feed the model as input multiple clips not only one as for the training