error_details.txt

(pytorch1.7.0) root@milton-LabPC:/data/code13/SETR# python tools/train.py configs/SETR/SETR_PUP_768x768_40k_cityscapes_bs_8.py
2021-04-07 10:26:16,450 - mmseg - INFO - Environment info:
------------------------------------------------------------
sys.platform: linux
Python: 3.8.8 (default, Feb 24 2021, 21:46:12) [GCC 7.3.0]
CUDA available: True
GPU 0: GeForce RTX 3090
CUDA_HOME: /usr/local/cuda-11.0
NVCC: Build cuda_11.0_bu.TC445_37.28540450_0
GCC: gcc (Ubuntu 5.4.0-6ubuntu1~16.04.12) 5.4.0 20160609
PyTorch: 1.7.0
PyTorch compiling details: PyTorch built with:
  - GCC 7.3
  - C++ Version: 201402
  - Intel(R) Math Kernel Library Version 2020.0.2 Product Build 20200624 for Intel(R) 64 architecture applications
  - Intel(R) MKL-DNN v1.6.0 (Git Hash 5ef631a030a6f73131c77892041042805a06064f)
  - OpenMP 201511 (a.k.a. OpenMP 4.5)
  - NNPACK is enabled
  - CPU capability usage: AVX2
  - CUDA Runtime 11.0
  - NVCC architecture flags: -gencode;arch=compute_37,code=sm_37;-gencode;arch=compute_50,code=sm_50;-gencode;arch=compute_60,code=sm_60;-gencode;arch=compute_61,code=sm_61;-gencode;arch=compute_70,code=sm_70;-gencode;arch=compute_75,code=sm_75;-gencode;arch=compute_80,code=sm_80;-gencode;arch=compute_37,code=compute_37
  - CuDNN 8.0.3
  - Magma 2.5.2
  - Build settings: BLAS=MKL, BUILD_TYPE=Release, CXX_FLAGS= -Wno-deprecated -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -fopenmp -DNDEBUG -DUSE_FBGEMM -DUSE_QNNPACK -DUSE_PYTORCH_QNNPACK -DUSE_XNNPACK -DUSE_VULKAN_WRAPPER -O2 -fPIC -Wno-narrowing -Wall -Wextra -Werror=return-type -Wno-missing-field-initializers -Wno-type-limits -Wno-array-bounds -Wno-unknown-pragmas -Wno-sign-compare -Wno-unused-parameter -Wno-unused-variable -Wno-unused-function -Wno-unused-result -Wno-unused-local-typedefs -Wno-strict-overflow -Wno-strict-aliasing -Wno-error=deprecated-declarations -Wno-stringop-overflow -Wno-psabi -Wno-error=pedantic -Wno-error=redundant-decls -Wno-error=old-style-cast -fdiagnostics-color=always -faligned-new -Wno-unused-but-set-variable -Wno-maybe-uninitialized -fno-math-errno -fno-trapping-math -Werror=format -Wno-stringop-overflow, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, USE_CUDA=ON, USE_EXCEPTION_PTR=1, USE_GFLAGS=OFF, USE_GLOG=OFF, USE_MKL=ON, USE_MKLDNN=ON, USE_MPI=OFF, USE_NCCL=ON, USE_NNPACK=ON, USE_OPENMP=ON, 

TorchVision: 0.8.0
OpenCV: 4.5.1
MMCV: 1.3.0
MMCV Compiler: GCC 7.3
MMCV CUDA Compiler: 11.0
MMSegmentation: 0.12.0+0504a4c
------------------------------------------------------------

2021-04-07 10:26:16,451 - mmseg - INFO - Distributed training: False
2021-04-07 10:26:16,776 - mmseg - INFO - Config:
norm_cfg = dict(type='SyncBN', requires_grad=True)
model = dict(
    type='EncoderDecoder',
    backbone=dict(
        type='VisionTransformer',
        model_name='vit_large_patch16_384',
        img_size=768,
        patch_size=16,
        in_chans=3,
        embed_dim=1024,
        depth=24,
        num_heads=16,
        num_classes=19,
        drop_rate=0.0,
        norm_cfg=dict(type='SyncBN', requires_grad=True),
        pos_embed_interp=True,
        align_corners=False),
    decode_head=dict(
        type='VisionTransformerUpHead',
        in_channels=1024,
        channels=512,
        in_index=23,
        img_size=768,
        embed_dim=1024,
        num_classes=19,
        norm_cfg=dict(type='SyncBN', requires_grad=True),
        num_conv=4,
        upsampling_method='bilinear',
        align_corners=False,
        loss_decode=dict(
            type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
        num_upsampe_layer=4),
    auxiliary_head=[
        dict(
            type='VisionTransformerUpHead',
            in_channels=1024,
            channels=512,
            in_index=9,
            img_size=768,
            embed_dim=1024,
            num_classes=19,
            norm_cfg=dict(type='SyncBN', requires_grad=True),
            num_conv=2,
            upsampling_method='bilinear',
            num_upsampe_layer=2,
            align_corners=False,
            loss_decode=dict(
                type='CrossEntropyLoss', use_sigmoid=False, loss_weight=0.4)),
        dict(
            type='VisionTransformerUpHead',
            in_channels=1024,
            channels=512,
            in_index=14,
            img_size=768,
            embed_dim=1024,
            num_classes=19,
            norm_cfg=dict(type='SyncBN', requires_grad=True),
            num_conv=2,
            upsampling_method='bilinear',
            num_upsampe_layer=2,
            align_corners=False,
            loss_decode=dict(
                type='CrossEntropyLoss', use_sigmoid=False, loss_weight=0.4)),
        dict(
            type='VisionTransformerUpHead',
            in_channels=1024,
            channels=512,
            in_index=19,
            img_size=768,
            embed_dim=1024,
            num_classes=19,
            norm_cfg=dict(type='SyncBN', requires_grad=True),
            num_conv=2,
            upsampling_method='bilinear',
            num_upsampe_layer=2,
            align_corners=False,
            loss_decode=dict(
                type='CrossEntropyLoss', use_sigmoid=False, loss_weight=0.4)),
        dict(
            type='VisionTransformerUpHead',
            in_channels=1024,
            channels=512,
            in_index=23,
            img_size=768,
            embed_dim=1024,
            num_classes=19,
            norm_cfg=dict(type='SyncBN', requires_grad=True),
            num_conv=2,
            upsampling_method='bilinear',
            num_upsampe_layer=2,
            align_corners=False,
            loss_decode=dict(
                type='CrossEntropyLoss', use_sigmoid=False, loss_weight=0.4))
    ])
train_cfg = dict()
test_cfg = dict(mode='slide', crop_size=(768, 768), stride=(512, 512))
dataset_type = 'CityscapesDataset'
data_root = 'data/cityscapes/'
img_norm_cfg = dict(
    mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
crop_size = (768, 768)
train_pipeline = [
    dict(type='LoadImageFromFile'),
    dict(type='LoadAnnotations'),
    dict(type='Resize', img_scale=(2049, 1025), ratio_range=(0.5, 2.0)),
    dict(type='RandomCrop', crop_size=(768, 768), cat_max_ratio=0.75),
    dict(type='RandomFlip', flip_ratio=0.5),
    dict(type='PhotoMetricDistortion'),
    dict(
        type='Normalize',
        mean=[123.675, 116.28, 103.53],
        std=[58.395, 57.12, 57.375],
        to_rgb=True),
    dict(type='Pad', size=(768, 768), pad_val=0, seg_pad_val=255),
    dict(type='DefaultFormatBundle'),
    dict(type='Collect', keys=['img', 'gt_semantic_seg'])
]
test_pipeline = [
    dict(type='LoadImageFromFile'),
    dict(
        type='MultiScaleFlipAug',
        img_scale=(2049, 1025),
        flip=False,
        transforms=[
            dict(type='Resize', keep_ratio=True),
            dict(type='RandomFlip'),
            dict(
                type='Normalize',
                mean=[123.675, 116.28, 103.53],
                std=[58.395, 57.12, 57.375],
                to_rgb=True),
            dict(type='ImageToTensor', keys=['img']),
            dict(type='Collect', keys=['img'])
        ])
]
data = dict(
    samples_per_gpu=1,
    workers_per_gpu=2,
    train=dict(
        type='CityscapesDataset',
        data_root='data/cityscapes/',
        img_dir='leftImg8bit/train',
        ann_dir='gtFine/train',
        pipeline=[
            dict(type='LoadImageFromFile'),
            dict(type='LoadAnnotations'),
            dict(
                type='Resize', img_scale=(2049, 1025), ratio_range=(0.5, 2.0)),
            dict(type='RandomCrop', crop_size=(768, 768), cat_max_ratio=0.75),
            dict(type='RandomFlip', flip_ratio=0.5),
            dict(type='PhotoMetricDistortion'),
            dict(
                type='Normalize',
                mean=[123.675, 116.28, 103.53],
                std=[58.395, 57.12, 57.375],
                to_rgb=True),
            dict(type='Pad', size=(768, 768), pad_val=0, seg_pad_val=255),
            dict(type='DefaultFormatBundle'),
            dict(type='Collect', keys=['img', 'gt_semantic_seg'])
        ]),
    val=dict(
        type='CityscapesDataset',
        data_root='data/cityscapes/',
        img_dir='leftImg8bit/val',
        ann_dir='gtFine/val',
        pipeline=[
            dict(type='LoadImageFromFile'),
            dict(
                type='MultiScaleFlipAug',
                img_scale=(2049, 1025),
                flip=False,
                transforms=[
                    dict(type='Resize', keep_ratio=True),
                    dict(type='RandomFlip'),
                    dict(
                        type='Normalize',
                        mean=[123.675, 116.28, 103.53],
                        std=[58.395, 57.12, 57.375],
                        to_rgb=True),
                    dict(type='ImageToTensor', keys=['img']),
                    dict(type='Collect', keys=['img'])
                ])
        ]),
    test=dict(
        type='CityscapesDataset',
        data_root='data/cityscapes/',
        img_dir='leftImg8bit/val',
        ann_dir='gtFine/val',
        pipeline=[
            dict(type='LoadImageFromFile'),
            dict(
                type='MultiScaleFlipAug',
                img_scale=(2049, 1025),
                flip=False,
                transforms=[
                    dict(type='Resize', keep_ratio=True),
                    dict(type='RandomFlip'),
                    dict(
                        type='Normalize',
                        mean=[123.675, 116.28, 103.53],
                        std=[58.395, 57.12, 57.375],
                        to_rgb=True),
                    dict(type='ImageToTensor', keys=['img']),
                    dict(type='Collect', keys=['img'])
                ])
        ]))
log_config = dict(
    interval=50, hooks=[dict(type='TextLoggerHook', by_epoch=False)])
dist_params = dict(backend='nccl')
log_level = 'INFO'
load_from = None
resume_from = None
workflow = [('train', 1)]
cudnn_benchmark = True
optimizer = dict(
    type='SGD',
    lr=0.01,
    momentum=0.9,
    weight_decay=0.0,
    paramwise_cfg=dict(custom_keys=dict(head=dict(lr_mult=10.0))))
optimizer_config = dict()
lr_config = dict(policy='poly', power=0.9, min_lr=0.0001, by_epoch=False)
total_iters = 40000
checkpoint_config = dict(by_epoch=False, interval=4000)
evaluation = dict(interval=4000, metric='mIoU')
find_unused_parameters = True
work_dir = './work_dirs/SETR_PUP_768x768_40k_cityscapes_bs_8'
gpu_ids = range(0, 1)

/media/root/mdata/data/code13/mmsegmentation/mmseg/models/builder.py:59: UserWarning: train_cfg and test_cfg is deprecated, please specify them in model
  warnings.warn(
Traceback (most recent call last):
  File "/root/anaconda3/envs/pytorch1.7.0/lib/python3.8/site-packages/mmcv/utils/registry.py", line 179, in build_from_cfg
    return obj_cls(**args)
  File "/media/root/mdata/data/code13/mmsegmentation/mmseg/models/segmentors/encoder_decoder.py", line 30, in __init__
    self.backbone = builder.build_backbone(backbone)
  File "/media/root/mdata/data/code13/mmsegmentation/mmseg/models/builder.py", line 38, in build_backbone
    return build(cfg, BACKBONES)
  File "/media/root/mdata/data/code13/mmsegmentation/mmseg/models/builder.py", line 33, in build
    return build_from_cfg(cfg, registry, default_args)
  File "/root/anaconda3/envs/pytorch1.7.0/lib/python3.8/site-packages/mmcv/utils/registry.py", line 171, in build_from_cfg
    raise KeyError(
KeyError: 'VisionTransformer is not in the backbone registry'

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "tools/train.py", line 161, in <module>
    main()
  File "tools/train.py", line 130, in main
    model = build_segmentor(
  File "/media/root/mdata/data/code13/mmsegmentation/mmseg/models/builder.py", line 66, in build_segmentor
    return build(cfg, SEGMENTORS, dict(train_cfg=train_cfg, test_cfg=test_cfg))
  File "/media/root/mdata/data/code13/mmsegmentation/mmseg/models/builder.py", line 33, in build
    return build_from_cfg(cfg, registry, default_args)
  File "/root/anaconda3/envs/pytorch1.7.0/lib/python3.8/site-packages/mmcv/utils/registry.py", line 182, in build_from_cfg
    raise type(e)(f'{obj_cls.__name__}: {e}')
KeyError: "EncoderDecoder: 'VisionTransformer is not in the backbone registry'"
(pytorch1.7.0) root@milton-LabPC:/data/code13/SETR#