Fine_tune_RT_DETR_on_a_custom_dataset:

[msaqib17]

---

RuntimeError Traceback (most recent call last)
Cell In[17], line 13
1 from transformers import Trainer
3 trainer = Trainer(
4 model=model,
5 args=training_args,
(...)
10 compute_metrics=eval_compute_metrics_fn,
11 )
---> 13 trainer.train()

File ~/anaconda3/envs/dvc_detr/lib/python3.12/site-packages/transformers/trainer.py:2052, in Trainer.train(self, resume_from_checkpoint, trial, ignore_keys_for_eval, **kwargs)
2050 hf_hub_utils.enable_progress_bars()
2051 else:
-> 2052 return inner_training_loop(
2053 args=args,
2054 resume_from_checkpoint=resume_from_checkpoint,
2055 trial=trial,
2056 ignore_keys_for_eval=ignore_keys_for_eval,
2057 )

File ~/anaconda3/envs/dvc_detr/lib/python3.12/site-packages/transformers/trainer.py:2388, in Trainer._inner_training_loop(self, batch_size, args, resume_from_checkpoint, trial, ignore_keys_for_eval)
2385 self.control = self.callback_handler.on_step_begin(args, self.state, self.control)
2387 with self.accelerator.accumulate(model):
-> 2388 tr_loss_step = self.training_step(model, inputs)
2390 if (
2391 args.logging_nan_inf_filter
2392 and not is_torch_xla_available()
2393 and (torch.isnan(tr_loss_step) or torch.isinf(tr_loss_step))
2394 ):
2395 # if loss is nan or inf simply add the average of previous logged losses
2396 tr_loss = tr_loss + tr_loss / (1 + self.state.global_step - self._globalstep_last_logged)

File ~/anaconda3/envs/dvc_detr/lib/python3.12/site-packages/transformers/trainer.py:3485, in Trainer.training_step(self, model, inputs)
3482 return loss_mb.reduce_mean().detach().to(self.args.device)
3484 with self.compute_loss_context_manager():
-> 3485 loss = self.compute_loss(model, inputs)
3487 del inputs
3488 if (
3489 self.args.torch_empty_cache_steps is not None
3490 and self.state.global_step % self.args.torch_empty_cache_steps == 0
3491 ):

File ~/anaconda3/envs/dvc_detr/lib/python3.12/site-packages/transformers/trainer.py:3532, in Trainer.compute_loss(self, model, inputs, return_outputs)
3530 else:
3531 labels = None
-> 3532 outputs = model(**inputs)
3533 # Save past state if it exists
3534 # TODO: this needs to be fixed and made cleaner later.
3535 if self.args.past_index >= 0:

File ~/anaconda3/envs/dvc_detr/lib/python3.12/site-packages/torch/nn/modules/module.py:1553, in Module._wrapped_call_impl(self, *args, **kwargs)
1551 return self._compiled_call_impl(*args, **kwargs) # type: ignore[misc]
1552 else:
-> 1553 return self._call_impl(*args, **kwargs)

File ~/anaconda3/envs/dvc_detr/lib/python3.12/site-packages/torch/nn/modules/module.py:1562, in Module._call_impl(self, *args, **kwargs)
1557 # If we don't have any hooks, we want to skip the rest of the logic in
1558 # this function, and just call forward.
1559 if not (self._backward_hooks or self._backward_pre_hooks or self._forward_hooks or self._forward_pre_hooks
1560 or _global_backward_pre_hooks or _global_backward_hooks
1561 or _global_forward_hooks or _global_forward_pre_hooks):
-> 1562 return forward_call(*args, **kwargs)
1564 try:
1565 result = None

File ~/anaconda3/envs/dvc_detr/lib/python3.12/site-packages/torch/nn/parallel/data_parallel.py:186, in DataParallel.forward(self, *inputs, **kwargs)
184 return self.module(*inputs[0], **module_kwargs[0])
185 replicas = self.replicate(self.module, self.device_ids[:len(inputs)])
--> 186 outputs = self.parallel_apply(replicas, inputs, module_kwargs)
187 return self.gather(outputs, self.output_device)

File ~/anaconda3/envs/dvc_detr/lib/python3.12/site-packages/torch/nn/parallel/data_parallel.py:201, in DataParallel.parallel_apply(self, replicas, inputs, kwargs)
200 def parallel_apply(self, replicas: Sequence[T], inputs: Sequence[Any], kwargs: Any) -> List[Any]:
--> 201 return parallel_apply(replicas, inputs, kwargs, self.device_ids[:len(replicas)])

File ~/anaconda3/envs/dvc_detr/lib/python3.12/site-packages/torch/nn/parallel/parallel_apply.py:109, in parallel_apply(modules, inputs, kwargs_tup, devices)
107 output = results[i]
108 if isinstance(output, ExceptionWrapper):
--> 109 output.reraise()
110 outputs.append(output)
111 return outputs

File ~/anaconda3/envs/dvc_detr/lib/python3.12/site-packages/torch/_utils.py:706, in ExceptionWrapper.reraise(self)
702 except TypeError:
703 # If the exception takes multiple arguments, don't try to
704 # instantiate since we don't know how to
705 raise RuntimeError(msg) from None
--> 706 raise exception

RuntimeError: Caught RuntimeError in replica 0 on device 0.
Original Traceback (most recent call last):
File "/home/xyz/anaconda3/envs/dvc_detr/lib/python3.12/site-packages/torch/nn/parallel/parallel_apply.py", line 84, in _worker
output = module(*input, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/xyz/anaconda3/envs/dvc_detr/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/xyz/anaconda3/envs/dvc_detr/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1562, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/xyz/anaconda3/envs/dvc_detr/lib/python3.12/site-packages/transformers/models/rt_detr/modeling_rt_detr.py", line 2659, in forward
outputs = self.model(
^^^^^^^^^^^
File "/home/xyz/anaconda3/envs/dvc_detr/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/xyz/anaconda3/envs/dvc_detr/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1562, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/xyz/anaconda3/envs/dvc_detr/lib/python3.12/site-packages/transformers/models/rt_detr/modeling_rt_detr.py", line 1892, in forward
reference_points_unact = torch.concat([denoising_bbox_unact, reference_points_unact], 1)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
RuntimeError: Sizes of tensors must match except in dimension 1. Expected size 16 but got size 8 for tensor number 1 in the list.