[2025-10-26 19:13:49,064][dinov2][INFO] - using MLP layer as FFN
[2025-10-26 19:14:19,899][py.warnings][WARNING] - /opt/conda/envs/dcsplat/lib/python3.12/site-packages/torchvision/models/_utils.py:208: UserWarning: The parameter 'pretrained' is deprecated since 0.13 and may be removed in the future, please use 'weights' instead.
  warnings.warn(

[2025-10-26 19:14:19,899][py.warnings][WARNING] - /opt/conda/envs/dcsplat/lib/python3.12/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and may be removed in the future. The current behavior is equivalent to passing `weights=VGG16_Weights.IMAGENET1K_V1`. You can also use `weights=VGG16_Weights.DEFAULT` to get the most up-to-date weights.
  warnings.warn(msg)

[2025-10-26 19:19:10,336][dinov2][INFO] - using MLP layer as FFN
[2025-10-26 19:19:16,631][py.warnings][WARNING] - /opt/conda/envs/dcsplat/lib/python3.12/site-packages/torchvision/models/_utils.py:208: UserWarning: The parameter 'pretrained' is deprecated since 0.13 and may be removed in the future, please use 'weights' instead.
  warnings.warn(

[2025-10-26 19:19:16,631][py.warnings][WARNING] - /opt/conda/envs/dcsplat/lib/python3.12/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and may be removed in the future. The current behavior is equivalent to passing `weights=VGG16_Weights.IMAGENET1K_V1`. You can also use `weights=VGG16_Weights.DEFAULT` to get the most up-to-date weights.
  warnings.warn(msg)

[2025-10-26 19:22:38,182][dinov2][INFO] - using MLP layer as FFN
[2025-10-26 19:22:44,601][py.warnings][WARNING] - /opt/conda/envs/dcsplat/lib/python3.12/site-packages/torchvision/models/_utils.py:208: UserWarning: The parameter 'pretrained' is deprecated since 0.13 and may be removed in the future, please use 'weights' instead.
  warnings.warn(

[2025-10-26 19:22:44,601][py.warnings][WARNING] - /opt/conda/envs/dcsplat/lib/python3.12/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and may be removed in the future. The current behavior is equivalent to passing `weights=VGG16_Weights.IMAGENET1K_V1`. You can also use `weights=VGG16_Weights.DEFAULT` to get the most up-to-date weights.
  warnings.warn(msg)

[2025-10-26 19:22:48,867][py.warnings][WARNING] - /opt/conda/envs/dcsplat/lib/python3.12/site-packages/lightning/pytorch/trainer/connectors/data_connector.py:425: The 'val_dataloader' does not have many workers which may be a bottleneck. Consider increasing the value of the `num_workers` argument` to `num_workers=255` in the `DataLoader` to improve performance.

[2025-10-26 19:22:54,328][py.warnings][WARNING] - /opt/conda/envs/dcsplat/lib/python3.12/site-packages/lightning/pytorch/utilities/data.py:79: Trying to infer the `batch_size` from an ambiguous collection. The batch size we found is 1. To avoid any miscalculations, use `self.log(..., batch_size=batch_size)`.

[2025-10-26 19:22:54,329][py.warnings][WARNING] - /opt/conda/envs/dcsplat/lib/python3.12/site-packages/torchvision/models/_utils.py:208: UserWarning: The parameter 'pretrained' is deprecated since 0.13 and may be removed in the future, please use 'weights' instead.
  warnings.warn(

[2025-10-26 19:22:54,329][py.warnings][WARNING] - /opt/conda/envs/dcsplat/lib/python3.12/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and may be removed in the future. The current behavior is equivalent to passing `weights=VGG16_Weights.IMAGENET1K_V1`. You can also use `weights=VGG16_Weights.DEFAULT` to get the most up-to-date weights.
  warnings.warn(msg)

[2025-10-26 19:22:58,545][py.warnings][WARNING] - /opt/conda/envs/dcsplat/lib/python3.12/site-packages/torch/functional.py:554: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at /pytorch/aten/src/ATen/native/TensorShape.cpp:4314.)
  return _VF.meshgrid(tensors, **kwargs)  # type: ignore[attr-defined]

[2025-10-26 19:23:34,745][dinov2][INFO] - using MLP layer as FFN
[2025-10-26 19:23:41,698][py.warnings][WARNING] - /opt/conda/envs/dcsplat/lib/python3.12/site-packages/torchvision/models/_utils.py:208: UserWarning: The parameter 'pretrained' is deprecated since 0.13 and may be removed in the future, please use 'weights' instead.
  warnings.warn(

[2025-10-26 19:23:41,698][py.warnings][WARNING] - /opt/conda/envs/dcsplat/lib/python3.12/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and may be removed in the future. The current behavior is equivalent to passing `weights=VGG16_Weights.IMAGENET1K_V1`. You can also use `weights=VGG16_Weights.DEFAULT` to get the most up-to-date weights.
  warnings.warn(msg)

[2025-10-26 19:23:45,936][py.warnings][WARNING] - /opt/conda/envs/dcsplat/lib/python3.12/site-packages/lightning/pytorch/trainer/connectors/data_connector.py:425: The 'val_dataloader' does not have many workers which may be a bottleneck. Consider increasing the value of the `num_workers` argument` to `num_workers=255` in the `DataLoader` to improve performance.

[2025-10-26 19:23:49,495][py.warnings][WARNING] - /opt/conda/envs/dcsplat/lib/python3.12/site-packages/lightning/pytorch/utilities/data.py:79: Trying to infer the `batch_size` from an ambiguous collection. The batch size we found is 1. To avoid any miscalculations, use `self.log(..., batch_size=batch_size)`.

[2025-10-26 19:23:49,496][py.warnings][WARNING] - /opt/conda/envs/dcsplat/lib/python3.12/site-packages/torchvision/models/_utils.py:208: UserWarning: The parameter 'pretrained' is deprecated since 0.13 and may be removed in the future, please use 'weights' instead.
  warnings.warn(

[2025-10-26 19:23:49,496][py.warnings][WARNING] - /opt/conda/envs/dcsplat/lib/python3.12/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and may be removed in the future. The current behavior is equivalent to passing `weights=VGG16_Weights.IMAGENET1K_V1`. You can also use `weights=VGG16_Weights.DEFAULT` to get the most up-to-date weights.
  warnings.warn(msg)

[2025-10-26 19:23:53,646][py.warnings][WARNING] - /opt/conda/envs/dcsplat/lib/python3.12/site-packages/torch/functional.py:554: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at /pytorch/aten/src/ATen/native/TensorShape.cpp:4314.)
  return _VF.meshgrid(tensors, **kwargs)  # type: ignore[attr-defined]

[2025-10-26 19:24:35,723][dinov2][INFO] - using MLP layer as FFN
[2025-10-26 19:24:42,666][py.warnings][WARNING] - /opt/conda/envs/dcsplat/lib/python3.12/site-packages/torchvision/models/_utils.py:208: UserWarning: The parameter 'pretrained' is deprecated since 0.13 and may be removed in the future, please use 'weights' instead.
  warnings.warn(

[2025-10-26 19:24:42,666][py.warnings][WARNING] - /opt/conda/envs/dcsplat/lib/python3.12/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and may be removed in the future. The current behavior is equivalent to passing `weights=VGG16_Weights.IMAGENET1K_V1`. You can also use `weights=VGG16_Weights.DEFAULT` to get the most up-to-date weights.
  warnings.warn(msg)

[2025-10-26 19:24:46,880][py.warnings][WARNING] - /opt/conda/envs/dcsplat/lib/python3.12/site-packages/lightning/pytorch/trainer/connectors/data_connector.py:425: The 'val_dataloader' does not have many workers which may be a bottleneck. Consider increasing the value of the `num_workers` argument` to `num_workers=255` in the `DataLoader` to improve performance.

[2025-10-26 19:24:50,494][py.warnings][WARNING] - /opt/conda/envs/dcsplat/lib/python3.12/site-packages/lightning/pytorch/utilities/data.py:79: Trying to infer the `batch_size` from an ambiguous collection. The batch size we found is 1. To avoid any miscalculations, use `self.log(..., batch_size=batch_size)`.

[2025-10-26 19:24:50,495][py.warnings][WARNING] - /opt/conda/envs/dcsplat/lib/python3.12/site-packages/torchvision/models/_utils.py:208: UserWarning: The parameter 'pretrained' is deprecated since 0.13 and may be removed in the future, please use 'weights' instead.
  warnings.warn(

[2025-10-26 19:24:50,495][py.warnings][WARNING] - /opt/conda/envs/dcsplat/lib/python3.12/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and may be removed in the future. The current behavior is equivalent to passing `weights=VGG16_Weights.IMAGENET1K_V1`. You can also use `weights=VGG16_Weights.DEFAULT` to get the most up-to-date weights.
  warnings.warn(msg)

[2025-10-26 19:24:54,605][py.warnings][WARNING] - /opt/conda/envs/dcsplat/lib/python3.12/site-packages/torch/functional.py:554: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at /pytorch/aten/src/ATen/native/TensorShape.cpp:4314.)
  return _VF.meshgrid(tensors, **kwargs)  # type: ignore[attr-defined]

[2025-10-26 19:27:54,048][dinov2][INFO] - using MLP layer as FFN
[2025-10-26 19:28:00,911][py.warnings][WARNING] - /opt/conda/envs/dcsplat/lib/python3.12/site-packages/torchvision/models/_utils.py:208: UserWarning: The parameter 'pretrained' is deprecated since 0.13 and may be removed in the future, please use 'weights' instead.
  warnings.warn(

[2025-10-26 19:28:00,911][py.warnings][WARNING] - /opt/conda/envs/dcsplat/lib/python3.12/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and may be removed in the future. The current behavior is equivalent to passing `weights=VGG16_Weights.IMAGENET1K_V1`. You can also use `weights=VGG16_Weights.DEFAULT` to get the most up-to-date weights.
  warnings.warn(msg)

[2025-10-26 19:28:05,191][py.warnings][WARNING] - /opt/conda/envs/dcsplat/lib/python3.12/site-packages/lightning/pytorch/trainer/connectors/data_connector.py:425: The 'val_dataloader' does not have many workers which may be a bottleneck. Consider increasing the value of the `num_workers` argument` to `num_workers=255` in the `DataLoader` to improve performance.

[2025-10-26 19:28:08,758][py.warnings][WARNING] - /opt/conda/envs/dcsplat/lib/python3.12/site-packages/lightning/pytorch/utilities/data.py:79: Trying to infer the `batch_size` from an ambiguous collection. The batch size we found is 1. To avoid any miscalculations, use `self.log(..., batch_size=batch_size)`.

[2025-10-26 19:28:08,760][py.warnings][WARNING] - /opt/conda/envs/dcsplat/lib/python3.12/site-packages/torchvision/models/_utils.py:208: UserWarning: The parameter 'pretrained' is deprecated since 0.13 and may be removed in the future, please use 'weights' instead.
  warnings.warn(

[2025-10-26 19:28:08,760][py.warnings][WARNING] - /opt/conda/envs/dcsplat/lib/python3.12/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and may be removed in the future. The current behavior is equivalent to passing `weights=VGG16_Weights.IMAGENET1K_V1`. You can also use `weights=VGG16_Weights.DEFAULT` to get the most up-to-date weights.
  warnings.warn(msg)

[2025-10-26 19:28:12,962][py.warnings][WARNING] - /opt/conda/envs/dcsplat/lib/python3.12/site-packages/torch/functional.py:554: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at /pytorch/aten/src/ATen/native/TensorShape.cpp:4314.)
  return _VF.meshgrid(tensors, **kwargs)  # type: ignore[attr-defined]

[2025-10-26 19:29:11,320][py.warnings][WARNING] - /opt/conda/envs/dcsplat/lib/python3.12/site-packages/torch/optim/lr_scheduler.py:198: UserWarning: The epoch parameter in `scheduler.step()` was not necessary and is being deprecated where possible. Please use `scheduler.step()` to step the scheduler. During the deprecation, if epoch is different from None, the closed form is used instead of the new chainable form, where available. Please open an issue if you are unable to replicate your use case: https://github.com/pytorch/pytorch/issues/new/choose.
  warnings.warn(EPOCH_DEPRECATION_WARNING, UserWarning)

[2025-10-26 19:30:13,864][dinov2][INFO] - using MLP layer as FFN
[2025-10-26 19:30:21,215][py.warnings][WARNING] - /opt/conda/envs/dcsplat/lib/python3.12/site-packages/torchvision/models/_utils.py:208: UserWarning: The parameter 'pretrained' is deprecated since 0.13 and may be removed in the future, please use 'weights' instead.
  warnings.warn(

[2025-10-26 19:30:21,215][py.warnings][WARNING] - /opt/conda/envs/dcsplat/lib/python3.12/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and may be removed in the future. The current behavior is equivalent to passing `weights=VGG16_Weights.IMAGENET1K_V1`. You can also use `weights=VGG16_Weights.DEFAULT` to get the most up-to-date weights.
  warnings.warn(msg)

[2025-10-26 19:30:25,466][py.warnings][WARNING] - /opt/conda/envs/dcsplat/lib/python3.12/site-packages/lightning/pytorch/trainer/connectors/data_connector.py:425: The 'val_dataloader' does not have many workers which may be a bottleneck. Consider increasing the value of the `num_workers` argument` to `num_workers=255` in the `DataLoader` to improve performance.

[2025-10-26 19:30:29,259][py.warnings][WARNING] - /opt/conda/envs/dcsplat/lib/python3.12/site-packages/lightning/pytorch/utilities/data.py:79: Trying to infer the `batch_size` from an ambiguous collection. The batch size we found is 1. To avoid any miscalculations, use `self.log(..., batch_size=batch_size)`.

[2025-10-26 19:30:29,261][py.warnings][WARNING] - /opt/conda/envs/dcsplat/lib/python3.12/site-packages/torchvision/models/_utils.py:208: UserWarning: The parameter 'pretrained' is deprecated since 0.13 and may be removed in the future, please use 'weights' instead.
  warnings.warn(

[2025-10-26 19:30:29,261][py.warnings][WARNING] - /opt/conda/envs/dcsplat/lib/python3.12/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and may be removed in the future. The current behavior is equivalent to passing `weights=VGG16_Weights.IMAGENET1K_V1`. You can also use `weights=VGG16_Weights.DEFAULT` to get the most up-to-date weights.
  warnings.warn(msg)

[2025-10-26 19:30:33,394][py.warnings][WARNING] - /opt/conda/envs/dcsplat/lib/python3.12/site-packages/torch/functional.py:554: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at /pytorch/aten/src/ATen/native/TensorShape.cpp:4314.)
  return _VF.meshgrid(tensors, **kwargs)  # type: ignore[attr-defined]

[2025-10-26 19:33:09,720][py.warnings][WARNING] - /opt/conda/envs/dcsplat/lib/python3.12/site-packages/torch/optim/lr_scheduler.py:198: UserWarning: The epoch parameter in `scheduler.step()` was not necessary and is being deprecated where possible. Please use `scheduler.step()` to step the scheduler. During the deprecation, if epoch is different from None, the closed form is used instead of the new chainable form, where available. Please open an issue if you are unable to replicate your use case: https://github.com/pytorch/pytorch/issues/new/choose.
  warnings.warn(EPOCH_DEPRECATION_WARNING, UserWarning)

[2025-10-26 19:34:12,455][dinov2][INFO] - using MLP layer as FFN
[2025-10-26 19:34:19,263][py.warnings][WARNING] - /opt/conda/envs/dcsplat/lib/python3.12/site-packages/torchvision/models/_utils.py:208: UserWarning: The parameter 'pretrained' is deprecated since 0.13 and may be removed in the future, please use 'weights' instead.
  warnings.warn(

[2025-10-26 19:34:19,263][py.warnings][WARNING] - /opt/conda/envs/dcsplat/lib/python3.12/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and may be removed in the future. The current behavior is equivalent to passing `weights=VGG16_Weights.IMAGENET1K_V1`. You can also use `weights=VGG16_Weights.DEFAULT` to get the most up-to-date weights.
  warnings.warn(msg)

[2025-10-26 19:36:04,347][py.warnings][WARNING] - /opt/conda/envs/dcsplat/lib/python3.12/site-packages/lightning/pytorch/trainer/connectors/data_connector.py:425: The 'val_dataloader' does not have many workers which may be a bottleneck. Consider increasing the value of the `num_workers` argument` to `num_workers=31` in the `DataLoader` to improve performance.

[2025-10-26 19:36:04,351][py.warnings][WARNING] - /opt/conda/envs/dcsplat/lib/python3.12/site-packages/torch/distributed/distributed_c10d.py:4631: UserWarning: No device id is provided via `init_process_group` or `barrier `. Using the current device set by the user. 
  warnings.warn(  # warn only once

[2025-10-26 19:36:08,105][py.warnings][WARNING] - /opt/conda/envs/dcsplat/lib/python3.12/site-packages/lightning/pytorch/utilities/data.py:79: Trying to infer the `batch_size` from an ambiguous collection. The batch size we found is 1. To avoid any miscalculations, use `self.log(..., batch_size=batch_size)`.

[2025-10-26 19:36:08,107][py.warnings][WARNING] - /opt/conda/envs/dcsplat/lib/python3.12/site-packages/torchvision/models/_utils.py:208: UserWarning: The parameter 'pretrained' is deprecated since 0.13 and may be removed in the future, please use 'weights' instead.
  warnings.warn(

[2025-10-26 19:36:08,107][py.warnings][WARNING] - /opt/conda/envs/dcsplat/lib/python3.12/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and may be removed in the future. The current behavior is equivalent to passing `weights=VGG16_Weights.IMAGENET1K_V1`. You can also use `weights=VGG16_Weights.DEFAULT` to get the most up-to-date weights.
  warnings.warn(msg)

[2025-10-26 19:36:12,202][py.warnings][WARNING] - /opt/conda/envs/dcsplat/lib/python3.12/site-packages/torch/functional.py:554: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at /pytorch/aten/src/ATen/native/TensorShape.cpp:4314.)
  return _VF.meshgrid(tensors, **kwargs)  # type: ignore[attr-defined]

[2025-10-26 19:36:20,660][py.warnings][WARNING] - /opt/conda/envs/dcsplat/lib/python3.12/site-packages/lightning/pytorch/trainer/connectors/logger_connector/result.py:434: It is recommended to use `self.log('val/psnr', ..., sync_dist=True)` when logging on epoch level in distributed setting to accumulate the metric across devices.

[2025-10-26 19:36:20,662][py.warnings][WARNING] - /opt/conda/envs/dcsplat/lib/python3.12/site-packages/lightning/pytorch/trainer/connectors/logger_connector/result.py:434: It is recommended to use `self.log('val/lpips', ..., sync_dist=True)` when logging on epoch level in distributed setting to accumulate the metric across devices.

[2025-10-26 19:36:20,662][py.warnings][WARNING] - /opt/conda/envs/dcsplat/lib/python3.12/site-packages/lightning/pytorch/trainer/connectors/logger_connector/result.py:434: It is recommended to use `self.log('val/ssim', ..., sync_dist=True)` when logging on epoch level in distributed setting to accumulate the metric across devices.

[2025-10-26 19:36:20,663][py.warnings][WARNING] - /opt/conda/envs/dcsplat/lib/python3.12/site-packages/lightning/pytorch/trainer/connectors/logger_connector/result.py:434: It is recommended to use `self.log('val/gaussian_num_ratio', ..., sync_dist=True)` when logging on epoch level in distributed setting to accumulate the metric across devices.

[2025-10-26 19:36:20,663][py.warnings][WARNING] - /opt/conda/envs/dcsplat/lib/python3.12/site-packages/lightning/pytorch/trainer/connectors/logger_connector/result.py:434: It is recommended to use `self.log('val/uncertainty_weight_mean', ..., sync_dist=True)` when logging on epoch level in distributed setting to accumulate the metric across devices.

[2025-10-26 19:36:20,663][py.warnings][WARNING] - /opt/conda/envs/dcsplat/lib/python3.12/site-packages/lightning/pytorch/trainer/connectors/logger_connector/result.py:434: It is recommended to use `self.log('info/global_step', ..., sync_dist=True)` when logging on epoch level in distributed setting to accumulate the metric across devices.

[2025-10-26 19:38:49,451][py.warnings][WARNING] - /opt/conda/envs/dcsplat/lib/python3.12/site-packages/torch/distributed/distributed_c10d.py:4631: UserWarning: No device id is provided via `init_process_group` or `barrier `. Using the current device set by the user. 
  warnings.warn(  # warn only once

[2025-10-26 19:38:56,872][py.warnings][WARNING] - /opt/conda/envs/dcsplat/lib/python3.12/site-packages/torch/autograd/graph.py:824: UserWarning: Grad strides do not match bucket view strides. This may indicate grad was not created according to the gradient layout contract, or that the param's strides changed since DDP was constructed.  This is not an error, but may impair performance.
grad.sizes() = [1, 288, 1, 1], strides() = [288, 1, 288, 288]
bucket_view.sizes() = [1, 288, 1, 1], strides() = [288, 1, 1, 1] (Triggered internally at /pytorch/torch/csrc/distributed/c10d/reducer.cpp:328.)
  return Variable._execution_engine.run_backward(  # Calls into the C++ engine to run the backward pass

[2025-10-26 19:48:54,025][dinov2][INFO] - using MLP layer as FFN
[2025-10-26 19:49:00,901][py.warnings][WARNING] - /opt/conda/envs/dcsplat/lib/python3.12/site-packages/torchvision/models/_utils.py:208: UserWarning: The parameter 'pretrained' is deprecated since 0.13 and may be removed in the future, please use 'weights' instead.
  warnings.warn(

[2025-10-26 19:49:00,902][py.warnings][WARNING] - /opt/conda/envs/dcsplat/lib/python3.12/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and may be removed in the future. The current behavior is equivalent to passing `weights=VGG16_Weights.IMAGENET1K_V1`. You can also use `weights=VGG16_Weights.DEFAULT` to get the most up-to-date weights.
  warnings.warn(msg)

[2025-10-26 19:49:04,791][py.warnings][WARNING] - /opt/conda/envs/dcsplat/lib/python3.12/site-packages/lightning/pytorch/trainer/connectors/data_connector.py:425: The 'val_dataloader' does not have many workers which may be a bottleneck. Consider increasing the value of the `num_workers` argument` to `num_workers=255` in the `DataLoader` to improve performance.

[2025-10-26 19:49:08,489][py.warnings][WARNING] - /opt/conda/envs/dcsplat/lib/python3.12/site-packages/lightning/pytorch/utilities/data.py:79: Trying to infer the `batch_size` from an ambiguous collection. The batch size we found is 1. To avoid any miscalculations, use `self.log(..., batch_size=batch_size)`.

[2025-10-26 19:49:08,490][py.warnings][WARNING] - /opt/conda/envs/dcsplat/lib/python3.12/site-packages/torchvision/models/_utils.py:208: UserWarning: The parameter 'pretrained' is deprecated since 0.13 and may be removed in the future, please use 'weights' instead.
  warnings.warn(

[2025-10-26 19:49:08,490][py.warnings][WARNING] - /opt/conda/envs/dcsplat/lib/python3.12/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and may be removed in the future. The current behavior is equivalent to passing `weights=VGG16_Weights.IMAGENET1K_V1`. You can also use `weights=VGG16_Weights.DEFAULT` to get the most up-to-date weights.
  warnings.warn(msg)

[2025-10-26 19:49:12,665][py.warnings][WARNING] - /opt/conda/envs/dcsplat/lib/python3.12/site-packages/torch/functional.py:554: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at /pytorch/aten/src/ATen/native/TensorShape.cpp:4314.)
  return _VF.meshgrid(tensors, **kwargs)  # type: ignore[attr-defined]

[2025-10-26 19:57:42,595][dinov2][INFO] - using MLP layer as FFN
[2025-10-26 19:58:14,362][py.warnings][WARNING] - /opt/conda/envs/dcsplat/lib/python3.12/site-packages/torchvision/models/_utils.py:208: UserWarning: The parameter 'pretrained' is deprecated since 0.13 and may be removed in the future, please use 'weights' instead.
  warnings.warn(

[2025-10-26 19:58:14,363][py.warnings][WARNING] - /opt/conda/envs/dcsplat/lib/python3.12/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and may be removed in the future. The current behavior is equivalent to passing `weights=VGG16_Weights.IMAGENET1K_V1`. You can also use `weights=VGG16_Weights.DEFAULT` to get the most up-to-date weights.
  warnings.warn(msg)

[2025-10-26 20:06:16,400][dinov2][INFO] - using MLP layer as FFN
[2025-10-26 20:06:23,388][py.warnings][WARNING] - /opt/conda/envs/dcsplat/lib/python3.12/site-packages/torchvision/models/_utils.py:208: UserWarning: The parameter 'pretrained' is deprecated since 0.13 and may be removed in the future, please use 'weights' instead.
  warnings.warn(

[2025-10-26 20:06:23,389][py.warnings][WARNING] - /opt/conda/envs/dcsplat/lib/python3.12/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and may be removed in the future. The current behavior is equivalent to passing `weights=VGG16_Weights.IMAGENET1K_V1`. You can also use `weights=VGG16_Weights.DEFAULT` to get the most up-to-date weights.
  warnings.warn(msg)

[2025-10-26 20:06:49,706][dinov2][INFO] - using MLP layer as FFN
[2025-10-26 20:06:56,648][py.warnings][WARNING] - /opt/conda/envs/dcsplat/lib/python3.12/site-packages/torchvision/models/_utils.py:208: UserWarning: The parameter 'pretrained' is deprecated since 0.13 and may be removed in the future, please use 'weights' instead.
  warnings.warn(

[2025-10-26 20:06:56,648][py.warnings][WARNING] - /opt/conda/envs/dcsplat/lib/python3.12/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and may be removed in the future. The current behavior is equivalent to passing `weights=VGG16_Weights.IMAGENET1K_V1`. You can also use `weights=VGG16_Weights.DEFAULT` to get the most up-to-date weights.
  warnings.warn(msg)

[2025-10-26 20:09:54,570][py.warnings][WARNING] - /opt/conda/envs/dcsplat/lib/python3.12/site-packages/lightning/pytorch/trainer/connectors/data_connector.py:425: The 'val_dataloader' does not have many workers which may be a bottleneck. Consider increasing the value of the `num_workers` argument` to `num_workers=31` in the `DataLoader` to improve performance.

[2025-10-26 20:09:54,573][py.warnings][WARNING] - /opt/conda/envs/dcsplat/lib/python3.12/site-packages/torch/distributed/distributed_c10d.py:4631: UserWarning: No device id is provided via `init_process_group` or `barrier `. Using the current device set by the user. 
  warnings.warn(  # warn only once

[2025-10-26 20:14:49,566][dinov2][INFO] - using MLP layer as FFN
[2025-10-26 20:14:56,409][py.warnings][WARNING] - /opt/conda/envs/dcsplat/lib/python3.12/site-packages/torchvision/models/_utils.py:208: UserWarning: The parameter 'pretrained' is deprecated since 0.13 and may be removed in the future, please use 'weights' instead.
  warnings.warn(

[2025-10-26 20:14:56,409][py.warnings][WARNING] - /opt/conda/envs/dcsplat/lib/python3.12/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and may be removed in the future. The current behavior is equivalent to passing `weights=VGG16_Weights.IMAGENET1K_V1`. You can also use `weights=VGG16_Weights.DEFAULT` to get the most up-to-date weights.
  warnings.warn(msg)

[2025-10-26 20:16:49,478][py.warnings][WARNING] - /opt/conda/envs/dcsplat/lib/python3.12/site-packages/lightning/pytorch/trainer/connectors/data_connector.py:425: The 'val_dataloader' does not have many workers which may be a bottleneck. Consider increasing the value of the `num_workers` argument` to `num_workers=31` in the `DataLoader` to improve performance.

[2025-10-26 20:16:49,481][py.warnings][WARNING] - /opt/conda/envs/dcsplat/lib/python3.12/site-packages/torch/distributed/distributed_c10d.py:4631: UserWarning: No device id is provided via `init_process_group` or `barrier `. Using the current device set by the user. 
  warnings.warn(  # warn only once

[2025-10-26 20:16:54,700][py.warnings][WARNING] - /opt/conda/envs/dcsplat/lib/python3.12/site-packages/lightning/pytorch/utilities/data.py:79: Trying to infer the `batch_size` from an ambiguous collection. The batch size we found is 1. To avoid any miscalculations, use `self.log(..., batch_size=batch_size)`.

[2025-10-26 20:16:54,701][py.warnings][WARNING] - /opt/conda/envs/dcsplat/lib/python3.12/site-packages/torchvision/models/_utils.py:208: UserWarning: The parameter 'pretrained' is deprecated since 0.13 and may be removed in the future, please use 'weights' instead.
  warnings.warn(

[2025-10-26 20:16:54,702][py.warnings][WARNING] - /opt/conda/envs/dcsplat/lib/python3.12/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and may be removed in the future. The current behavior is equivalent to passing `weights=VGG16_Weights.IMAGENET1K_V1`. You can also use `weights=VGG16_Weights.DEFAULT` to get the most up-to-date weights.
  warnings.warn(msg)

[2025-10-26 20:16:59,158][py.warnings][WARNING] - /opt/conda/envs/dcsplat/lib/python3.12/site-packages/torch/functional.py:554: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at /pytorch/aten/src/ATen/native/TensorShape.cpp:4314.)
  return _VF.meshgrid(tensors, **kwargs)  # type: ignore[attr-defined]

[2025-10-26 20:17:07,778][py.warnings][WARNING] - /opt/conda/envs/dcsplat/lib/python3.12/site-packages/lightning/pytorch/trainer/connectors/logger_connector/result.py:434: It is recommended to use `self.log('val/psnr', ..., sync_dist=True)` when logging on epoch level in distributed setting to accumulate the metric across devices.

[2025-10-26 20:17:07,781][py.warnings][WARNING] - /opt/conda/envs/dcsplat/lib/python3.12/site-packages/lightning/pytorch/trainer/connectors/logger_connector/result.py:434: It is recommended to use `self.log('val/lpips', ..., sync_dist=True)` when logging on epoch level in distributed setting to accumulate the metric across devices.

[2025-10-26 20:17:07,782][py.warnings][WARNING] - /opt/conda/envs/dcsplat/lib/python3.12/site-packages/lightning/pytorch/trainer/connectors/logger_connector/result.py:434: It is recommended to use `self.log('val/ssim', ..., sync_dist=True)` when logging on epoch level in distributed setting to accumulate the metric across devices.

[2025-10-26 20:17:07,782][py.warnings][WARNING] - /opt/conda/envs/dcsplat/lib/python3.12/site-packages/lightning/pytorch/trainer/connectors/logger_connector/result.py:434: It is recommended to use `self.log('val/gaussian_num_ratio', ..., sync_dist=True)` when logging on epoch level in distributed setting to accumulate the metric across devices.

[2025-10-26 20:17:07,782][py.warnings][WARNING] - /opt/conda/envs/dcsplat/lib/python3.12/site-packages/lightning/pytorch/trainer/connectors/logger_connector/result.py:434: It is recommended to use `self.log('val/uncertainty_weight_mean', ..., sync_dist=True)` when logging on epoch level in distributed setting to accumulate the metric across devices.

[2025-10-26 20:17:07,782][py.warnings][WARNING] - /opt/conda/envs/dcsplat/lib/python3.12/site-packages/lightning/pytorch/trainer/connectors/logger_connector/result.py:434: It is recommended to use `self.log('info/global_step', ..., sync_dist=True)` when logging on epoch level in distributed setting to accumulate the metric across devices.

[2025-10-26 20:19:16,141][py.warnings][WARNING] - /opt/conda/envs/dcsplat/lib/python3.12/site-packages/torch/distributed/distributed_c10d.py:4631: UserWarning: No device id is provided via `init_process_group` or `barrier `. Using the current device set by the user. 
  warnings.warn(  # warn only once

[2025-10-26 20:19:25,207][py.warnings][WARNING] - /opt/conda/envs/dcsplat/lib/python3.12/site-packages/torch/autograd/graph.py:824: UserWarning: Grad strides do not match bucket view strides. This may indicate grad was not created according to the gradient layout contract, or that the param's strides changed since DDP was constructed.  This is not an error, but may impair performance.
grad.sizes() = [1, 288, 1, 1], strides() = [288, 1, 288, 288]
bucket_view.sizes() = [1, 288, 1, 1], strides() = [288, 1, 1, 1] (Triggered internally at /pytorch/torch/csrc/distributed/c10d/reducer.cpp:328.)
  return Variable._execution_engine.run_backward(  # Calls into the C++ engine to run the backward pass

[2025-10-26 20:23:29,369][py.warnings][WARNING] - /opt/conda/envs/dcsplat/lib/python3.12/site-packages/torch/optim/lr_scheduler.py:198: UserWarning: The epoch parameter in `scheduler.step()` was not necessary and is being deprecated where possible. Please use `scheduler.step()` to step the scheduler. During the deprecation, if epoch is different from None, the closed form is used instead of the new chainable form, where available. Please open an issue if you are unable to replicate your use case: https://github.com/pytorch/pytorch/issues/new/choose.
  warnings.warn(EPOCH_DEPRECATION_WARNING, UserWarning)

[2025-10-27 07:25:40,575][py.warnings][WARNING] - /opt/conda/envs/dcsplat/lib/python3.12/site-packages/torch/distributed/distributed_c10d.py:4631: UserWarning: No device id is provided via `init_process_group` or `barrier `. Using the current device set by the user. 
  warnings.warn(  # warn only once