nohup: ignoring input Global seed set to 231 /usr/local/lib/python3.9/site-packages/torch/functional.py:504: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at /data/jenkins_workspace/workspace/pytorch_23.04_abi@4/aten/src/ATen/native/TensorShape.cpp:3191.) return _VF.meshgrid(tensors, **kwargs) # type: ignore[attr-defined] /usr/local/lib/python3.9/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( /usr/local/lib/python3.9/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=AlexNet_Weights.IMAGENET1K_V1`. You can also use `weights=AlexNet_Weights.DEFAULT` to get the most up-to-date weights. warnings.warn(msg) GPU available: True, used: True TPU available: False, using: 0 TPU cores IPU available: False, using: 0 IPUs Global seed set to 231 initializing ddp: GLOBAL_RANK: 0, MEMBER: 1/3 Global seed set to 231 Global seed set to 231 /usr/local/lib/python3.9/site-packages/torch/functional.py:504: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at /data/jenkins_workspace/workspace/pytorch_23.04_abi@4/aten/src/ATen/native/TensorShape.cpp:3191.) return _VF.meshgrid(tensors, **kwargs) # type: ignore[attr-defined] /usr/local/lib/python3.9/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( /usr/local/lib/python3.9/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=AlexNet_Weights.IMAGENET1K_V1`. You can also use `weights=AlexNet_Weights.DEFAULT` to get the most up-to-date weights. warnings.warn(msg) /usr/local/lib/python3.9/site-packages/torch/functional.py:504: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at /data/jenkins_workspace/workspace/pytorch_23.04_abi@4/aten/src/ATen/native/TensorShape.cpp:3191.) return _VF.meshgrid(tensors, **kwargs) # type: ignore[attr-defined] /usr/local/lib/python3.9/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( /usr/local/lib/python3.9/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=AlexNet_Weights.IMAGENET1K_V1`. You can also use `weights=AlexNet_Weights.DEFAULT` to get the most up-to-date weights. warnings.warn(msg) Global seed set to 231 initializing ddp: GLOBAL_RANK: 1, MEMBER: 2/3 WARNING: Logging before InitGoogleLogging() is written to STDERR I1103 04:22:32.982725 4113395 ProcessGroupNCCL.cpp:669] [Rank 1] ProcessGroupNCCL initialized with following options: NCCL_ASYNC_ERROR_HANDLING: 0 NCCL_DESYNC_DEBUG: 0 NCCL_BLOCKING_WAIT: 0 TIMEOUT(ms): 1800000 USE_HIGH_PRIORITY_STREAM: 0 I1103 04:22:32.982746 4119599 ProcessGroupNCCL.cpp:835] [Rank 1] NCCL watchdog thread started! Global seed set to 231 initializing ddp: GLOBAL_RANK: 2, MEMBER: 3/3 WARNING: Logging before InitGoogleLogging() is written to STDERR I1103 04:22:42.253474 4113753 ProcessGroupNCCL.cpp:669] [Rank 2] ProcessGroupNCCL initialized with following options: NCCL_ASYNC_ERROR_HANDLING: 0 NCCL_DESYNC_DEBUG: 0 NCCL_BLOCKING_WAIT: 0 TIMEOUT(ms): 1800000 USE_HIGH_PRIORITY_STREAM: 0 I1103 04:22:42.253731 4120039 ProcessGroupNCCL.cpp:835] [Rank 2] NCCL watchdog thread started! WARNING: Logging before InitGoogleLogging() is written to STDERR I1103 04:22:42.256446 4120041 ProcessGroupNCCL.cpp:835] [Rank 0] NCCL watchdog thread started! I1103 04:22:42.256433 4109126 ProcessGroupNCCL.cpp:669] [Rank 0] ProcessGroupNCCL initialized with following options: NCCL_ASYNC_ERROR_HANDLING: 0 NCCL_DESYNC_DEBUG: 0 NCCL_BLOCKING_WAIT: 0 TIMEOUT(ms): 1800000 USE_HIGH_PRIORITY_STREAM: 0 ---------------------------------------------------------------------------------------------------- distributed_backend=nccl All DDP processes registered. Starting ddp with 3 processes ---------------------------------------------------------------------------------------------------- I1103 04:22:43.273196 4109126 ProcessGroupNCCL.cpp:1274] NCCL_DEBUG: N/A LOCAL_RANK: 0 - CUDA_VISIBLE_DEVICES: [0,1,2,3,4,5,6,7] LOCAL_RANK: 2 - CUDA_VISIBLE_DEVICES: [0,1,2,3,4,5,6,7] LOCAL_RANK: 1 - CUDA_VISIBLE_DEVICES: [0,1,2,3,4,5,6,7] | Name | Type | Params ------------------------------------------------------------- 0 | model | DiffusionWrapper | 865 M 1 | first_stage_model | AutoencoderKL | 83.7 M 2 | cond_stage_model | FrozenOpenCLIPEmbedder | 354 M 3 | control_model | ControlNet | 363 M 4 | preprocess_model | SwinIR | 15.8 M 5 | cond_encoder | Sequential | 34.2 M ------------------------------------------------------------- 1.2 B Trainable params 487 M Non-trainable params 1.7 B Total params 6,866.827 Total estimated model params size (MB) No module 'xformers'. Proceeding without it. ControlLDM: Running in eps-prediction mode DiffusionWrapper has 865.91 M params. making attention of type 'vanilla' with 512 in_channels Working with z of shape (1, 4, 32, 32) = 4096 dimensions. making attention of type 'vanilla' with 512 in_channels /home/modelzoo/DiffBIR/weights/open_clip_pytorch_model.bin Setting up [LPIPS] perceptual loss: trunk [alex], v[0.1], spatial [off] Loading model from: /usr/local/lib/python3.9/site-packages/lpips/weights/v0.1/alex.pth Validation sanity check: 0it [00:00, ?it/s]/usr/local/lib/python3.9/site-packages/pytorch_lightning/trainer/data_loading.py:105: UserWarning: The dataloader, val dataloader 0, does not have many workers which may be a bottleneck. Consider increasing the value of the `num_workers` argument` (try 128 which is the number of cpus on this machine) in the `DataLoader` init to improve performance. rank_zero_warn( Validation sanity check: 0%| | 0/2 [00:00