search

open-mmlab / mmdetection

OpenMMLab Detection Toolbox and Benchmark
https://mmdetection.readthedocs.io
Apache License 2.0
29.61k stars 9.47k forks source link

Error when training: module 'torch.distributed' has no attribute '_initialized' #132

Closed adityaarun1 closed 5 years ago

adityaarun1 commented 5 years ago

Hi,

When I am running the training script ./tools/dist_train.sh configs/cascade_rcnn_r50_fpn_1x.py 1 on a single GPU for PASCAL VOC 2007 dataset, I get the following error:

Traceback (most recent call last):
  File "./tools/train.py", line 81, in <module>
    main()
  File "./tools/train.py", line 60, in main
    logger = get_root_logger(cfg.log_level)
  File "/ssd_scratch/cvit/aditya/mmdetection/mmdet/apis/env.py", line 54, in get_root_logger
    rank, _ = get_dist_info()
  File "/home/aditya.a/Libraries/anaconda3/lib/python3.7/site-packages/mmcv/runner/utils.py", line 16, in get_dist_info
    if dist._initialized:
AttributeError: module 'torch.distributed' has no attribute '_initialized'

I get the same error when I run python tools/train.py configs/cascade_rcnn_r50_fpn_1x.py --gpus 1 --validate

I am not sure what the issue is. Following are the additional details:

Pytorch: 1.0.0.dev20181129

I have used pascal_voc.py to convert PASCAL VOC annotations to CustomDataset annotatios.The annotations are kept in data/voc2007/Annotations folder, and the images are symlinked at data/voc2007/Images.

Here is the config file I am using:

# model settings
model = dict(
    type='CascadeRCNN',
    num_stages=3,
    pretrained='modelzoo://resnet50',
    backbone=dict(
        type='ResNet',
        depth=50,
        num_stages=4,
        out_indices=(0, 1, 2, 3),
        frozen_stages=1,
        style='pytorch'),
    neck=dict(
        type='FPN',
        in_channels=[256, 512, 1024, 2048],
        out_channels=256,
        num_outs=5),
    rpn_head=dict(
        type='RPNHead',
        in_channels=256,
        feat_channels=256,
        anchor_scales=[8],
        anchor_ratios=[0.5, 1.0, 2.0],
        anchor_strides=[4, 8, 16, 32, 64],
        target_means=[.0, .0, .0, .0],
        target_stds=[1.0, 1.0, 1.0, 1.0],
        use_sigmoid_cls=True),
    bbox_roi_extractor=dict(
        type='SingleRoIExtractor',
        roi_layer=dict(type='RoIAlign', out_size=7, sample_num=2),
        out_channels=256,
        featmap_strides=[4, 8, 16, 32]),
    bbox_head=[
        dict(
            type='SharedFCBBoxHead',
            num_fcs=2,
            in_channels=256,
            fc_out_channels=1024,
            roi_feat_size=7,
            num_classes=81,
            target_means=[0., 0., 0., 0.],
            target_stds=[0.1, 0.1, 0.2, 0.2],
            reg_class_agnostic=True),
        dict(
            type='SharedFCBBoxHead',
            num_fcs=2,
            in_channels=256,
            fc_out_channels=1024,
            roi_feat_size=7,
            num_classes=81,
            target_means=[0., 0., 0., 0.],
            target_stds=[0.05, 0.05, 0.1, 0.1],
            reg_class_agnostic=True),
        dict(
            type='SharedFCBBoxHead',
            num_fcs=2,
            in_channels=256,
            fc_out_channels=1024,
            roi_feat_size=7,
            num_classes=81,
            target_means=[0., 0., 0., 0.],
            target_stds=[0.033, 0.033, 0.067, 0.067],
            reg_class_agnostic=True)
    ])
# model training and testing settings
train_cfg = dict(
    rpn=dict(
        assigner=dict(
            pos_iou_thr=0.7,
            neg_iou_thr=0.3,
            min_pos_iou=0.3,
            ignore_iof_thr=-1),
        sampler=dict(
            num=256,
            pos_fraction=0.5,
            neg_pos_ub=-1,
            add_gt_as_proposals=False,
            pos_balance_sampling=False,
            neg_balance_thr=0),
        allowed_border=0,
        pos_weight=-1,
        smoothl1_beta=1 / 9.0,
        debug=False),
    rcnn=[
        dict(
            assigner=dict(
                pos_iou_thr=0.5,
                neg_iou_thr=0.5,
                min_pos_iou=0.5,
                ignore_iof_thr=-1),
            sampler=dict(
                num=512,
                pos_fraction=0.25,
                neg_pos_ub=-1,
                add_gt_as_proposals=True,
                pos_balance_sampling=False,
                neg_balance_thr=0),
            pos_weight=-1,
            debug=False),
        dict(
            assigner=dict(
                pos_iou_thr=0.6,
                neg_iou_thr=0.6,
                min_pos_iou=0.6,
                ignore_iof_thr=-1),
            sampler=dict(
                num=512,
                pos_fraction=0.25,
                neg_pos_ub=-1,
                add_gt_as_proposals=True,
                pos_balance_sampling=False,
                neg_balance_thr=0),
            pos_weight=-1,
            debug=False),
        dict(
            assigner=dict(
                pos_iou_thr=0.7,
                neg_iou_thr=0.7,
                min_pos_iou=0.7,
                ignore_iof_thr=-1),
            sampler=dict(
                num=512,
                pos_fraction=0.25,
                neg_pos_ub=-1,
                add_gt_as_proposals=True,
                pos_balance_sampling=False,
                neg_balance_thr=0),
            pos_weight=-1,
            debug=False)
    ],
    stage_loss_weights=[1, 0.5, 0.25])
test_cfg = dict(
    rpn=dict(
        nms_across_levels=False,
        nms_pre=2000,
        nms_post=2000,
        max_num=2000,
        nms_thr=0.7,
        min_bbox_size=0),
    rcnn=dict(
        score_thr=0.05, nms=dict(type='nms', iou_thr=0.5), max_per_img=100),
    keep_all_stages=False)
# dataset settings
dataset_type = 'CocoDataset'
data_root = 'data/voc2007/'
img_norm_cfg = dict(
    mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
data = dict(
    imgs_per_gpu=2,
    workers_per_gpu=2,
    train=dict(
        type=dataset_type,
        ann_file=data_root + 'Annotations/voc07_train.pkl',
        img_prefix=data_root + 'Images/',
        img_scale=(1333, 800),
        img_norm_cfg=img_norm_cfg,
        size_divisor=32,
        flip_ratio=0.5,
        with_mask=False,
        with_crowd=True,
        with_label=True),
    val=dict(
        type=dataset_type,
        ann_file=data_root + 'Annotations/voc07_val.pkl',
        img_prefix=data_root + 'Images/',
        img_scale=(1333, 800),
        img_norm_cfg=img_norm_cfg,
        size_divisor=32,
        flip_ratio=0,
        with_mask=False,
        with_crowd=True,
        with_label=True),
    test=dict(
        type=dataset_type,
        ann_file=data_root + 'Annotations/voc07_test.pkl',
        img_prefix=data_root + 'Images/',
        img_scale=(1333, 800),
        img_norm_cfg=img_norm_cfg,
        size_divisor=32,
        flip_ratio=0,
        with_mask=False,
        with_label=False,
        test_mode=True))
# optimizer
optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
# learning policy
lr_config = dict(
    policy='step',
    warmup='linear',
    warmup_iters=500,
    warmup_ratio=1.0 / 3,
    step=[8, 11])
checkpoint_config = dict(interval=1)
# yapf:disable
log_config = dict(
    interval=50,
    hooks=[
        dict(type='TextLoggerHook'),
        # dict(type='TensorboardLoggerHook')
    ])
# yapf:enable
# runtime settings
total_epochs = 12
dist_params = dict(backend='nccl')
log_level = 'INFO'
work_dir = './work_dirs/cascade_rcnn_r50_fpn_1x'
load_from = None
resume_from = None
workflow = [('train', 1)]
hellock commented 5 years ago

Currently we only support the latest stable version of PyTorch (0.4.1). You need to reinstall PyTorch.

adityaarun1 commented 5 years ago

I see. thanks.