No such file or directory lvis_v0.5_val_cocofied.json

[bosslv]

您好，我想问下，我使用类似coco数据集格式的时候，在验证的时候，为什么会提示我找不到lvis_v0.5_val_cocofied.json？
Traceback (most recent call last):
File "tools/train.py", line 153, in
main()
File "tools/train.py", line 142, in main
train_detector(
File "/home/lvshuzhou/RefineMask-main/mmdet/apis/train.py", line 143, in train_detector
runner.run(data_loaders, cfg.workflow, cfg.total_epochs)
File "/home/lvshuzhou/RefineMask-main/mmcv-1.0.5/mmcv/runner/epoch_based_runner.py", line 122, in run
epoch_runner(data_loaders[i], **kwargs)
File "/home/lvshuzhou/RefineMask-main/mmcv-1.0.5/mmcv/runner/epoch_based_runner.py", line 46, in train
self.call_hook('after_train_epoch')
File "/home/lvshuzhou/RefineMask-main/mmcv-1.0.5/mmcv/runner/base_runner.py", line 298, in call_hook
getattr(hook, fn_name)(self)
File "/home/lvshuzhou/RefineMask-main/mmdet/core/evaluation/eval_hooks.py", line 28, in after_train_epoch
self.evaluate(runner, results)
File "/home/lvshuzhou/RefineMask-main/mmdet/core/evaluation/eval_hooks.py", line 31, in evaluate
eval_res = self.dataloader.dataset.evaluate(
File "/home/lvshuzhou/RefineMask-main/mmdet/datasets/coco.py", line 575, in evaluate
self.eval_cocofied_lvis_result(
File "/home/lvshuzhou/RefineMask-main/mmdet/datasets/coco.py", line 673, in eval_cocofied_lvis_result
lvis_gt = LVIS(gt_file)
File "/home/lvshuzhou/anaconda3/envs/refinemask/lib/python3.8/site-packages/lvis/lvis.py", line 27, in init
self.dataset = self._load_json(annotation_path)
File "/home/lvshuzhou/anaconda3/envs/refinemask/lib/python3.8/site-packages/lvis/lvis.py", line 35, in _load_json
with open(path, 'r') as f:
FileNotFoundError: [Errno 2] No such file or directory: '/home/data/lsz/dataset/instance_version/annotations/lvis_v0.5_val_cocofied.json'

这是我的配置文件
model = dict(
type='MaskRCNN',
pretrained='torchvision://resnet50',
backbone=dict(
type='ResNet',
depth=50,
num_stages=4,
out_indices=(0, 1, 2, 3),
frozen_stages=1,
norm_cfg=dict(type='BN', requires_grad=True),
norm_eval=True,
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_generator=dict(
type='AnchorGenerator',
scales=[8],
ratios=[0.5, 1.0, 2.0],
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='L1Loss', loss_weight=1.0)),
roi_head=dict(
type='RefineRoIHead',
bbox_roi_extractor=dict(
type='SingleRoIExtractor',
roi_layer=dict(type='RoIAlign', output_size=7, sampling_ratio=0),
out_channels=256,
featmap_strides=[4, 8, 16, 32]),
bbox_head=dict(
type='Shared2FCBBoxHead',
in_channels=256,
fc_out_channels=1024,
roi_feat_size=7,
num_classes=22,
bbox_coder=dict(
type='DeltaXYWHBBoxCoder',
target_means=[0.0, 0.0, 0.0, 0.0],
target_stds=[0.1, 0.1, 0.2, 0.2]),
reg_class_agnostic=False,
loss_cls=dict(
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=2.0),
loss_bbox=dict(type='L1Loss', loss_weight=2.0)),
mask_roi_extractor=dict(
type='SingleRoIExtractor',
roi_layer=dict(type='RoIAlign', output_size=14, sampling_ratio=0),
out_channels=256,
featmap_strides=[4, 8, 16, 32]),
mask_head=dict(
type='RefineMaskHead',
num_convs_instance=2,
num_convs_semantic=4,
conv_in_channels_instance=256,
conv_in_channels_semantic=256,
conv_kernel_size_instance=3,
conv_kernel_size_semantic=3,
conv_out_channels_instance=256,
conv_out_channels_semantic=256,
conv_cfg=None,
norm_cfg=None,
dilations=[1, 3, 5],
semantic_out_stride=4,
mask_use_sigmoid=True,
stage_num_classes=[22, 22, 22, 22],
stage_sup_size=[14, 28, 56, 112],
upsample_cfg=dict(type='bilinear', scale_factor=2),
loss_cfg=dict(
type='RefineCrossEntropyLoss',
stage_instance_loss_weight=[0.25, 0.5, 0.75, 1.0],
semantic_loss_weight=1.0,
boundary_width=2,
start_stage=1))))

train_cfg = dict(
rpn=dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.7,
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=-1,
pos_weight=-1,
debug=False),
rpn_proposal=dict(
nms_across_levels=False,
nms_pre=2000,
nms_post=1000,
max_num=1000,
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,
match_low_quality=True,
ignore_iof_thr=-1),
sampler=dict(
type='RandomSampler',
num=512,
pos_fraction=0.25,
neg_pos_ub=-1,
add_gt_as_proposals=True),
mask_size=28,
pos_weight=-1,
debug=False))

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=0.05,
nms=dict(type='nms', iou_threshold=0.5),
max_per_img=100,
mask_thr_binary=0.5))

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,
with_mask=True,
poly2mask=False),
dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
dict(type='RandomFlip', flip_ratio=0.5),
dict(
type='Normalize',
mean=[123.675, 116.28, 103.53],
std=[58.395, 57.12, 57.375],
to_rgb=True),
dict(type='Pad', size_divisor=32),
dict(type='DefaultFormatBundle'),
dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks'])
]

test_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug',
img_scale=(1333, 800),
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='Pad', size_divisor=32),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img'])
])
]

data_root = '/home/data/lsz/dataset/instance_version' # change this to your own path
data = dict(
samples_per_gpu=2,
workers_per_gpu=1,
train=dict(
type='CocoDataset',
ann_file='instances_train_trashcan.json',
img_prefix='train/',
pipeline=[
dict(type='LoadImageFromFile'),
dict(
type='LoadAnnotations',
with_bbox=True,
with_mask=True,
poly2mask=False),
dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
dict(type='RandomFlip', flip_ratio=0.5),
dict(
type='Normalize',
mean=[123.675, 116.28, 103.53],
std=[58.395, 57.12, 57.375],
to_rgb=True),
dict(type='Pad', size_divisor=32),
dict(type='DefaultFormatBundle'),
dict(
type='Collect',
keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks'])
],
data_root=data_root),
val=dict(
type='CocoDataset',
ann_file='instances_val_trashcan.json',
img_prefix='val/',
pipeline=[
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug',
img_scale=(1333, 800),
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='Pad', size_divisor=32),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img'])
])
],
data_root=data_root),
test=dict(
type='CocoDataset',
ann_file='instances_val_trashcan.json',
img_prefix='val/',
pipeline=[
dict(type='LoadImageFromFile'),
dict(
type='MultiScaleFlipAug',
img_scale=(1333, 800),
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='Pad', size_divisor=32),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img'])
])
],
data_root=data_root))

evaluation = dict(metric=['bbox', 'segm'], classwise=True, interval=1)
optimizer = dict(type='SGD', lr=0.001, momentum=0.9, weight_decay=0.0001)

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))
total_epochs = 12
lr_config = dict(
policy='step',
warmup='linear',
warmup_iters=500,
warmup_ratio=0.0001,
step=[8, 11])
checkpoint_config = dict(interval=1)
log_config = dict(interval=50, hooks=[dict(type='TextLoggerHook')])
dist_params = dict(backend='nccl')
log_level = 'INFO'
workflow = [('train', 1)]
gpu_ids = range(0, 1)

work_dir = None
load_from = None
resume_from = None

[zhanggang001]

您好，我想问下，我使用类似coco数据集格式的时候，在验证的时候，为什么会提示我找不到lvis_v0.5_val_cocofied.json？ Traceback (most recent call last): File "tools/train.py", line 153, in main() File "tools/train.py", line 142, in main train_detector( File "/home/lvshuzhou/RefineMask-main/mmdet/apis/train.py", line 143, in train_detector runner.run(data_loaders, cfg.workflow, cfg.total_epochs) File "/home/lvshuzhou/RefineMask-main/mmcv-1.0.5/mmcv/runner/epoch_based_runner.py", line 122, in run epoch_runner(data_loaders[i], **kwargs) File "/home/lvshuzhou/RefineMask-main/mmcv-1.0.5/mmcv/runner/epoch_based_runner.py", line 46, in train self.call_hook('after_train_epoch') File "/home/lvshuzhou/RefineMask-main/mmcv-1.0.5/mmcv/runner/base_runner.py", line 298, in call_hook getattr(hook, fn_name)(self) File "/home/lvshuzhou/RefineMask-main/mmdet/core/evaluation/eval_hooks.py", line 28, in after_train_epoch self.evaluate(runner, results) File "/home/lvshuzhou/RefineMask-main/mmdet/core/evaluation/eval_hooks.py", line 31, in evaluate eval_res = self.dataloader.dataset.evaluate( File "/home/lvshuzhou/RefineMask-main/mmdet/datasets/coco.py", line 575, in evaluate self.eval_cocofied_lvis_result( File "/home/lvshuzhou/RefineMask-main/mmdet/datasets/coco.py", line 673, in eval_cocofied_lvis_result lvis_gt = LVIS(gt_file) File "/home/lvshuzhou/anaconda3/envs/refinemask/lib/python3.8/site-packages/lvis/lvis.py", line 27, in init self.dataset = self._load_json(annotation_path) File "/home/lvshuzhou/anaconda3/envs/refinemask/lib/python3.8/site-packages/lvis/lvis.py", line 35, in _load_json with open(path, 'r') as f: FileNotFoundError: [Errno 2] No such file or directory: '/home/data/lsz/dataset/instance_version/annotations/lvis_v0.5_val_cocofied.json'

这是我的配置文件 model = dict( type='MaskRCNN', pretrained='torchvision://resnet50', backbone=dict( type='ResNet', depth=50, num_stages=4, out_indices=(0, 1, 2, 3), frozen_stages=1, norm_cfg=dict(type='BN', requires_grad=True), norm_eval=True, 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_generator=dict( type='AnchorGenerator', scales=[8], ratios=[0.5, 1.0, 2.0], 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='L1Loss', loss_weight=1.0)), roi_head=dict( type='RefineRoIHead', bbox_roi_extractor=dict( type='SingleRoIExtractor', roi_layer=dict(type='RoIAlign', output_size=7, sampling_ratio=0), out_channels=256, featmap_strides=[4, 8, 16, 32]), bbox_head=dict( type='Shared2FCBBoxHead', in_channels=256, fc_out_channels=1024, roi_feat_size=7, num_classes=22, bbox_coder=dict( type='DeltaXYWHBBoxCoder', target_means=[0.0, 0.0, 0.0, 0.0], target_stds=[0.1, 0.1, 0.2, 0.2]), reg_class_agnostic=False, loss_cls=dict( type='CrossEntropyLoss', use_sigmoid=False, loss_weight=2.0), loss_bbox=dict(type='L1Loss', loss_weight=2.0)), mask_roi_extractor=dict( type='SingleRoIExtractor', roi_layer=dict(type='RoIAlign', output_size=14, sampling_ratio=0), out_channels=256, featmap_strides=[4, 8, 16, 32]), mask_head=dict( type='RefineMaskHead', num_convs_instance=2, num_convs_semantic=4, conv_in_channels_instance=256, conv_in_channels_semantic=256, conv_kernel_size_instance=3, conv_kernel_size_semantic=3, conv_out_channels_instance=256, conv_out_channels_semantic=256, conv_cfg=None, norm_cfg=None, dilations=[1, 3, 5], semantic_out_stride=4, mask_use_sigmoid=True, stage_num_classes=[22, 22, 22, 22], stage_sup_size=[14, 28, 56, 112], upsample_cfg=dict(type='bilinear', scale_factor=2), loss_cfg=dict( type='RefineCrossEntropyLoss', stage_instance_loss_weight=[0.25, 0.5, 0.75, 1.0], semantic_loss_weight=1.0, boundary_width=2, start_stage=1))))

train_cfg = dict( rpn=dict( assigner=dict( type='MaxIoUAssigner', pos_iou_thr=0.7, 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=-1, pos_weight=-1, debug=False), rpn_proposal=dict( nms_across_levels=False, nms_pre=2000, nms_post=1000, max_num=1000, 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, match_low_quality=True, ignore_iof_thr=-1), sampler=dict( type='RandomSampler', num=512, pos_fraction=0.25, neg_pos_ub=-1, add_gt_as_proposals=True), mask_size=28, pos_weight=-1, debug=False))

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=0.05, nms=dict(type='nms', iou_threshold=0.5), max_per_img=100, mask_thr_binary=0.5))

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, with_mask=True, poly2mask=False), dict(type='Resize', img_scale=(1333, 800), keep_ratio=True), dict(type='RandomFlip', flip_ratio=0.5), dict( type='Normalize', mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True), dict(type='Pad', size_divisor=32), dict(type='DefaultFormatBundle'), dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks']) ]

test_pipeline = [ dict(type='LoadImageFromFile'), dict( type='MultiScaleFlipAug', img_scale=(1333, 800), 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='Pad', size_divisor=32), dict(type='ImageToTensor', keys=['img']), dict(type='Collect', keys=['img']) ]) ]

data_root = '/home/data/lsz/dataset/instance_version' # change this to your own path data = dict( samples_per_gpu=2, workers_per_gpu=1, train=dict( type='CocoDataset', ann_file='instances_train_trashcan.json', img_prefix='train/', pipeline=[ dict(type='LoadImageFromFile'), dict( type='LoadAnnotations', with_bbox=True, with_mask=True, poly2mask=False), dict(type='Resize', img_scale=(1333, 800), keep_ratio=True), dict(type='RandomFlip', flip_ratio=0.5), dict( type='Normalize', mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True), dict(type='Pad', size_divisor=32), dict(type='DefaultFormatBundle'), dict( type='Collect', keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks']) ], data_root=data_root), val=dict( type='CocoDataset', ann_file='instances_val_trashcan.json', img_prefix='val/', pipeline=[ dict(type='LoadImageFromFile'), dict( type='MultiScaleFlipAug', img_scale=(1333, 800), 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='Pad', size_divisor=32), dict(type='ImageToTensor', keys=['img']), dict(type='Collect', keys=['img']) ]) ], data_root=data_root), test=dict( type='CocoDataset', ann_file='instances_val_trashcan.json', img_prefix='val/', pipeline=[ dict(type='LoadImageFromFile'), dict( type='MultiScaleFlipAug', img_scale=(1333, 800), 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='Pad', size_divisor=32), dict(type='ImageToTensor', keys=['img']), dict(type='Collect', keys=['img']) ]) ], data_root=data_root))

evaluation = dict(metric=['bbox', 'segm'], classwise=True, interval=1) optimizer = dict(type='SGD', lr=0.001, momentum=0.9, weight_decay=0.0001)

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)) total_epochs = 12 lr_config = dict( policy='step', warmup='linear', warmup_iters=500, warmup_ratio=0.0001, step=[8, 11]) checkpoint_config = dict(interval=1) log_config = dict(interval=50, hooks=[dict(type='TextLoggerHook')]) dist_params = dict(backend='nccl') log_level = 'INFO' workflow = [('train', 1)] gpu_ids = range(0, 1)

work_dir = None load_from = None resume_from = None

You should make sure that you download the lvis0.5 dataset.
By the way, the official support for the LVIS 0.5 dataset has been discontinued.