i got this error when training cbnetv2, but It's normal when I train other models
wzr0108 opened this issue · 11 comments
Traceback (most recent call last):
File "./tools/train.py", line 234, in
main()
File "./tools/train.py", line 221, in main
meta=meta)
File "/disk/sde/wzr/mmm/mmdet/apis/train.py", line 208, in train_detector
runner.run(data_loaders, cfg.workflow)
File "/disk/sdb/wzr/.conda/envs/wzr_env2/lib/python3.7/site-packages/mmcv/runner/epoch_based_runner.py", line 127, in run
epoch_runner(data_loaders[i], **kwargs)
File "/disk/sdb/wzr/.conda/envs/wzr_env2/lib/python3.7/site-packages/mmcv/runner/epoch_based_runner.py", line 50, in train
self.run_iter(data_batch, train_mode=True, **kwargs)
File "/disk/sdb/wzr/.conda/envs/wzr_env2/lib/python3.7/site-packages/mmcv/runner/epoch_based_runner.py", line 30, in run_iter
**kwargs)
File "/disk/sdb/wzr/.conda/envs/wzr_env2/lib/python3.7/site-packages/mmcv/parallel/distributed.py", line 59, in train_step
output = self.module.train_step(*inputs[0], **kwargs[0])
File "/disk/sde/wzr/mmm/mmdet/models/detectors/base.py", line 248, in train_step
losses = self(**data)
File "/disk/sdb/wzr/.conda/envs/wzr_env2/lib/python3.7/site-packages/torch/nn/modules/module.py", line 727, in _call_impl
result = self.forward(*input, **kwargs)
File "/disk/sdb/wzr/.conda/envs/wzr_env2/lib/python3.7/site-packages/mmcv/runner/fp16_utils.py", line 140, in new_func
output = old_func(*new_args, **new_kwargs)
File "/disk/sde/wzr/mmm/mmdet/models/detectors/base.py", line 172, in forward
return self.forward_train(img, img_metas, **kwargs)
File "/disk/sde/wzr/mmm/mmdet/models/detectors/two_stage.py", line 142, in forward_train
**kwargs)
File "/disk/sde/wzr/mmm/mmdet/models/dense_heads/base_dense_head.py", line 330, in forward_train
outs = self(x)
File "/disk/sdb/wzr/.conda/envs/wzr_env2/lib/python3.7/site-packages/torch/nn/modules/module.py", line 727, in _call_impl
result = self.forward(*input, **kwargs)
File "/disk/sde/wzr/mmm/mmdet/models/dense_heads/anchor_head.py", line 169, in forward
return multi_apply(self.forward_single, feats)
File "/disk/sde/wzr/mmm/mmdet/core/utils/misc.py", line 30, in multi_apply
return tuple(map(list, zip(*map_results)))
File "/disk/sde/wzr/mmm/mmdet/models/dense_heads/rpn_head.py", line 64, in forward_single
x = self.rpn_conv(x)
File "/disk/sdb/wzr/.conda/envs/wzr_env2/lib/python3.7/site-packages/torch/nn/modules/module.py", line 727, in _call_impl
result = self.forward(*input, **kwargs)
File "/disk/sdb/wzr/.conda/envs/wzr_env2/lib/python3.7/site-packages/torch/nn/modules/conv.py", line 423, in forward
return self._conv_forward(input, self.weight)
File "/disk/sdb/wzr/.conda/envs/wzr_env2/lib/python3.7/site-packages/torch/nn/modules/conv.py", line 420, in _conv_forward
self.padding, self.dilation, self.groups)
TypeError: conv2d(): argument 'input' (position 1) must be Tensor, not tuple
the config is as follows
model = dict(
type='CascadeRCNN',
init_cfg=dict(
type='Pretrained',
checkpoint="checkpoints/htc_cbv2_swin_base22k_patch4_window7_mstrain_400-1400_adamw_20e_coco_swa.pth"
),
backbone=dict(
type='CBSwinTransformer',
embed_dim=128,
depths=[2, 2, 18, 2],
num_heads=[4, 8, 16, 32],
window_size=7,
mlp_ratio=4,
qkv_bias=True,
qk_scale=None,
drop_rate=0.0,
attn_drop_rate=0.0,
drop_path_rate=0.3,
patch_norm=True,
out_indices=(0, 1, 2, 3),
),
neck=dict(
type='CBFPN',
in_channels=[128, 256, 512, 1024],
out_channels=256,
num_outs=5,
),
rpn_head=dict(
type='RPNHead',
in_channels=256,
feat_channels=256,
anchor_generator=dict(
type='AnchorGenerator',
scales=[8], # 8
ratios=[0.25, 0.5, 1.0, 2.0, 4.0], # 增加到7个
strides=[4, 8, 16, 32, 64]),
bbox_coder=dict(
type='DeltaXYWHBBoxCoder',
target_means=[0.0, 0.0, 0.0, 0.0],
target_stds=[1.0, 1.0, 1.0, 1.0]),
loss_cls=dict(
type='CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0),
loss_bbox=dict(
type='SmoothL1Loss', beta=0.1111111111111111, loss_weight=1.0)
),
roi_head=dict(
type='CascadeRoIHead',
num_stages=3, # 3->4
stage_loss_weights=[1, 0.5, 0.25],
bbox_roi_extractor=dict(
type='SingleRoIExtractor',
roi_layer=dict(type='RoIAlign', output_size=7, sampling_ratio=0),
out_channels=256,
gc_context=True,
featmap_strides=[4, 8, 16, 32]),
bbox_head=[
dict(
type='ConvFCBBoxHead',
num_shared_convs=4,
num_shared_fcs=1,
in_channels=256,
conv_out_channels=256,
fc_out_channels=1024,
roi_feat_size=7,
num_classes=8,
bbox_coder=dict(
type='DeltaXYWHBBoxCoder',
target_means=[0., 0., 0., 0.],
target_stds=[0.1, 0.1, 0.2, 0.2]),
reg_class_agnostic=False,
reg_decoded_bbox=True,
norm_cfg=dict(type='SyncBN', requires_grad=True),
loss_cls=dict(type='EQLv2'),
loss_bbox=dict(type='CIoULoss', loss_weight=10.0)),
dict(
type='ConvFCBBoxHead',
num_shared_convs=4,
num_shared_fcs=1,
in_channels=256,
conv_out_channels=256,
fc_out_channels=1024,
roi_feat_size=7,
num_classes=8,
bbox_coder=dict(
type='DeltaXYWHBBoxCoder',
target_means=[0., 0., 0., 0.],
target_stds=[0.05, 0.05, 0.1, 0.1]),
reg_class_agnostic=False,
reg_decoded_bbox=True,
norm_cfg=dict(type='SyncBN', requires_grad=True),
loss_cls=dict(type='EQLv2'),
loss_bbox=dict(type='CIoULoss', loss_weight=10.0)),
dict(
type='ConvFCBBoxHead',
num_shared_convs=4,
num_shared_fcs=1,
in_channels=256,
conv_out_channels=256,
fc_out_channels=1024,
roi_feat_size=7,
num_classes=8,
bbox_coder=dict(
type='DeltaXYWHBBoxCoder',
target_means=[0., 0., 0., 0.],
target_stds=[0.033, 0.033, 0.067, 0.067]),
reg_class_agnostic=False,
reg_decoded_bbox=True,
norm_cfg=dict(type='SyncBN', requires_grad=True),
loss_cls=dict(type='EQLv2'),
loss_bbox=dict(type='CIoULoss', loss_weight=10.0))
]),
train_cfg=dict(
rpn=dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.5, # 0.7->0.5
neg_iou_thr=0.3,
min_pos_iou=0.3,
match_low_quality=True,
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_per_img=2000,
nms=dict(type='nms', iou_threshold=0.7),
min_bbox_size=0),
rcnn=[
dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.6, # 0.5->0.3
neg_iou_thr=0.6,
min_pos_iou=0.6,
match_low_quality=False,
ignore_iof_thr=-1),
sampler=dict(
# type='OHEMSampler',
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, # 0.6->0.4
neg_iou_thr=0.7,
min_pos_iou=0.7,
match_low_quality=False,
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=0.8, # 0.7->0.5
neg_iou_thr=0.8,
min_pos_iou=0.8,
match_low_quality=False,
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)
]),
test_cfg=dict(
rpn=dict(
nms_across_levels=False,
nms_pre=5000,
nms_post=5000,
max_per_img=5000,
nms=dict(type='nms', iou_threshold=0.7),
min_bbox_size=0),
rcnn=dict(
score_thr=0.1, # 0.0001
nms=dict(type='soft_nms', iou_threshold=0.5, min_score=0.0001),
# nms=dict(type='nms', iou_threshold=0.99),
max_per_img=300)))
Hello,have you solved this problem？i meet this problem too.
Hello,have you solved this problem？i meet this problem too.
直接替换mmdet的models文件夹，应该是这里的文件和我安装的mmdet有点不同，直接替换环境中的mmdet/models就好了
Hello,have you solved this problem？i meet this problem too.
直接替换mmdet的models文件夹，应该是这里的文件和我安装的mmdet有点不同，直接替换环境中的mmdet/models就好了
太感谢了老哥，困扰了许久终于解决了！
请问您使用的pytorch和cuda 的版本是什么呢
torch 1.9.1 cuda 11.1
可以再问一下您使用的mmcv-full是什么版本不
1.6.1
谢谢！！我刚才用了跟您一样的环境跑了一遍 遇到了loss为NaN的情况 请问您有遇到过吗
调一下学习率，或者debug看一下哪里nan
好的好的 谢谢！