error when using ghm loss

Describe the bug when using ghm loss,error occured.

Reproduction

script

fp16 = dict(loss_scale=512.)
# model settings
model = dict(
type='CascadeRCNN',
num_stages=3,
pretrained=None,
backbone=dict(
    type='ResNeXt',
    depth=101,
    groups=64,
    base_width=4,
    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],
    loss_cls=dict(
        type='GHMC',
        bins=30,
        momentum=0.75,
        use_sigmoid=True,
        loss_weight=1.0),
    loss_bbox=dict(
        type='GHMR',
        mu=0.02,
        bins=10,
        momentum=0.7,
        loss_weight=10.0)),
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=5,
        target_means=[0., 0., 0., 0.],
        target_stds=[0.1, 0.1, 0.2, 0.2],
        reg_class_agnostic=True,
        loss_cls=dict(
            type='GHMC',
            bins=30,
            momentum=0.75,
            use_sigmoid=True,
            loss_weight=1.0),
        loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0)),
    dict(
        type='SharedFCBBoxHead',
        num_fcs=2,
        in_channels=256,
        fc_out_channels=1024,
        roi_feat_size=7,
        num_classes=5,
        target_means=[0., 0., 0., 0.],
        target_stds=[0.05, 0.05, 0.1, 0.1],
        reg_class_agnostic=True,
        loss_cls=dict(
            type='GHMC',
            bins=30,
            momentum=0.75,
            use_sigmoid=True,
            loss_weight=1.0),
        loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0)),
    dict(
        type='SharedFCBBoxHead',
        num_fcs=2,
        in_channels=256,
        fc_out_channels=1024,
        roi_feat_size=7,
        num_classes=5,
        target_means=[0., 0., 0., 0.],
        target_stds=[0.033, 0.033, 0.067, 0.067],
        reg_class_agnostic=True,
        loss_cls=dict(
            type='GHMC',
            bins=30,
            momentum=0.75,
            use_sigmoid=True,
            loss_weight=1.0),
        loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0))
])
# model training and testing settings
train_cfg = dict(
rpn=dict(
    assigner=dict(
        type='MaxIoUAssigner',
        pos_iou_thr=0.7,
        neg_iou_thr=0.3,
        min_pos_iou=0.3,
        ignore_iof_thr=-1),
    sampler=dict(
        type='RandomSampler',
        num=256,
        pos_fraction=0.5,
        neg_pos_ub=-1,
        add_gt_as_proposals=False),
    allowed_border=0,
    pos_weight=-1,
    debug=False),
rpn_proposal=dict(
    nms_across_levels=False,
    nms_pre=2000,
    nms_post=2000,
    max_num=2000,
    nms_thr=0.7,
    min_bbox_size=0),
rcnn=[
    dict(
        assigner=dict(
            type='MaxIoUAssigner',
            pos_iou_thr=0.5,
            neg_iou_thr=0.5,
            min_pos_iou=0.5,
            ignore_iof_thr=-1),
        sampler=dict(
            type='RandomSampler',
            num=512,
            pos_fraction=0.25,
            neg_pos_ub=-1,
            add_gt_as_proposals=True),
        pos_weight=-1,
        debug=False),
    dict(
        assigner=dict(
            type='MaxIoUAssigner',
            pos_iou_thr=0.6,
            neg_iou_thr=0.6,
            min_pos_iou=0.6,
            ignore_iof_thr=-1),
        sampler=dict(
            type='RandomSampler',
            num=512,
            pos_fraction=0.25,
            neg_pos_ub=-1,
            add_gt_as_proposals=True),
        pos_weight=-1,
        debug=False),
    dict(
        assigner=dict(
            type='MaxIoUAssigner',
            pos_iou_thr=0.7,
            neg_iou_thr=0.7,
            min_pos_iou=0.7,
            ignore_iof_thr=-1),
        sampler=dict(
            type='RandomSampler',
            num=512,
            pos_fraction=0.25,
            neg_pos_ub=-1,
            add_gt_as_proposals=True),
        pos_weight=-1,
        debug=False)
],
stage_loss_weights=[1, 0.5, 0.25])
test_cfg = dict(
rpn=dict(
    nms_across_levels=False,
    nms_pre=1000,
    nms_post=1000,
    max_num=1000,
    nms_thr=0.7,
    min_bbox_size=0),
rcnn=dict(
    score_thr=0.0001, nms=dict(type='soft_nms', iou_thr=0.5, min_score=0.0001), max_per_img=50))
# dataset settings
dataset_type = 'CocoDataset'
data_root = 'data/'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='LoadAnnotations', with_bbox=True),
dict(type='Resize', img_scale=[(4096, 600), (4096, 1000)],
     multiscale_mode='range', keep_ratio=True),
dict(type='RandomFlip', flip_ratio=0.5),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=32),
dict(type='DefaultFormatBundle'),
dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
]
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(
    type='MultiScaleFlipAug',
    img_scale=[(4096, 600), (4096, 800), (4096, 1000)],
    flip=True,
    transforms=[
        dict(type='Resize', keep_ratio=True),
        dict(type='RandomFlip'),
        dict(type='Normalize', **img_norm_cfg),
        dict(type='Pad', size_divisor=32),
        dict(type='ImageToTensor', keys=['img']),
        dict(type='Collect', keys=['img']),
    ])
]
data = dict(
imgs_per_gpu=1,
workers_per_gpu=2,
train=dict(
    type=dataset_type,
    ann_file=data_root + 'train_annotations_coco_style.json',
    img_prefix=data_root + 'train/',
    pipeline=train_pipeline),
val=dict(
    type=dataset_type,
    ann_file=data_root + 'val_annotations_coco_style.json',
    img_prefix=data_root + 'val/',
    pipeline=test_pipeline),
test=dict(
    type=dataset_type,
    ann_file= data_root+'val_annotations_coco_style_crop.json',
    img_prefix=data_root + 'val_crop/',
    pipeline=test_pipeline))
# optimizer
optimizer = dict(type='SGD', lr=0.005, 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_x101_64x4d_fpn_ghm'
load_from = 'data/pretrained/cascade_rcnn_x101_64x4d_fpn_1x_20181218-e2dc376a.pth'
resume_from = None
workflow = [('train', 1)]

Error traceback

Traceback (most recent call last):
  File "./tools/train.py", line 142, in <module>
    main()
  File "./tools/train.py", line 138, in main
    meta=meta)
  File "/home/mmdetection/mmdet/apis/train.py", line 102, in train_detector
    meta=meta)
  File "/home/mmdetection/mmdet/apis/train.py", line 181, in _dist_train
    runner.run(data_loaders, cfg.workflow, cfg.total_epochs)
  File "/root/anaconda3/envs/python367/lib/python3.6/site-packages/mmcv-0.4.2-py3.6-linux-x86_64.egg/mmcv/runner/runner.py", line 359, in run
    epoch_runner(data_loaders[i], **kwargs)
  File "/root/anaconda3/envs/python367/lib/python3.6/site-packages/mmcv-0.4.2-py3.6-linux-x86_64.egg/mmcv/runner/runner.py", line 263, in train
    self.model, data_batch, train_mode=True, **kwargs)
  File "/home/mmdetection/mmdet/apis/train.py", line 75, in batch_processor
    losses = model(**data)
  File "/root/anaconda3/envs/python367/lib/python3.6/site-packages/torch/nn/modules/module.py", line 547, in __call__
    result = self.forward(*input, **kwargs)
  File "/root/anaconda3/envs/python367/lib/python3.6/site-packages/torch/nn/parallel/distributed.py", line 442, in forward
    output = self.module(*inputs[0], **kwargs[0])
  File "/root/anaconda3/envs/python367/lib/python3.6/site-packages/torch/nn/modules/module.py", line 547, in __call__
    result = self.forward(*input, **kwargs)
  File "/home/mmdetection/mmdet/core/fp16/decorators.py", line 75, in new_func
    output = old_func(*new_args, **new_kwargs)
  File "/home/mmdetection/mmdet/models/detectors/base.py", line 147, in forward
    return self.forward_train(img, img_metas, **kwargs)
  File "/home/mmdetection/mmdet/models/detectors/cascade_rcnn.py", line 197, in forward_train
    *rpn_loss_inputs, gt_bboxes_ignore=gt_bboxes_ignore)
  File "/home/mmdetection/mmdet/models/anchor_heads/rpn_head.py", line 51, in loss
    gt_bboxes_ignore=gt_bboxes_ignore)
  File "/home/mmdetection/mmdet/core/fp16/decorators.py", line 152, in new_func
    output = old_func(*new_args, **new_kwargs)
  File "/home/mmdetection/mmdet/models/anchor_heads/anchor_head.py", line 205, in loss
    cfg=cfg)
  File "/home/mmdetection/mmdet/core/utils/misc.py", line 24, in multi_apply
    return tuple(map(list, zip(*map_results)))
  File "/home/mmdetection/mmdet/models/anchor_heads/anchor_head.py", line 149, in loss_single
    cls_score, labels, label_weights, avg_factor=num_total_samples)
  File "/root/anaconda3/envs/python367/lib/python3.6/site-packages/torch/nn/modules/module.py", line 547, in __call__
    result = self.forward(*input, **kwargs)
  File "/home/mmdetection/mmdet/models/losses/ghm_loss.py", line 78, in forward
    inds = (g >= edges[i]) & (g < edges[i + 1]) & valid
RuntimeError: Expected object of scalar type Float but got scalar type Half for argument #2 'other'

open-mmlab / mmdetection

error when using ghm loss #2398