fat-921
commented
1 year ago this is my config: data_root = '/labelme2coco_unlabeled_20230704/' num_classes = 4 batch_size = 2 img_scale = (2048, 920) METAINFO = { 'classes': ('污点', '黑棉', '破损', '褶皱'),
palette is a list of color tuples, which is used for visualization.
'palette':
[(220, 20, 60), (119, 11, 32), (0, 0, 142), (0, 0, 230)]}
backend_args = None train_pipeline = [ dict(type='LoadImageFromFile', backend_args=None), dict(type='LoadAnnotations', with_bbox=True), dict(type='Resize', scale=img_scale, keep_ratio=True), dict(type='RandomFlip', prob=0.5), dict(type='PackDetInputs') ] test_pipeline = [ dict( type='LoadImageFromFile', backend_args=None, imdecode_backend='pillow'), dict( type='FixScaleResize', scale=img_scale, keep_ratio=True, backend='pillow'), dict(type='LoadAnnotations', with_bbox=True), dict( type='PackDetInputs', meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape', 'scale_factor', 'text', 'custom_entities')) ] train_dataloader = dict( batch_size=batch_size, num_workers=2, persistent_workers=True, sampler=dict(type='DefaultSampler', shuffle=True), batch_sampler=dict(type='AspectRatioBatchSampler'), dataset=dict( type='CocoDataset', data_root=data_root, metainfo=METAINFO, ann_file='train.json', data_prefix=dict(img=''), filter_cfg=dict(filter_empty_gt=True, min_size=32), pipeline=[ dict(type='LoadImageFromFile', backend_args=None), dict(type='LoadAnnotations', with_bbox=True), dict(type='Resize', scale=img_scale, keep_ratio=True), dict(type='RandomFlip', prob=0.5), dict(type='PackDetInputs') ], backend_args=None)) val_dataloader = dict( batch_size=1, num_workers=2, persistent_workers=True, drop_last=False, sampler=dict(type='DefaultSampler', shuffle=False), dataset=dict( type='CocoDataset', data_root=data_root, metainfo=METAINFO, ann_file='val.json', data_prefix=dict(img=''), test_mode=True, pipeline=[ dict( type='LoadImageFromFile', backend_args=None, imdecode_backend='pillow'), dict( type='FixScaleResize', scale=img_scale, keep_ratio=True, backend='pillow'), dict(type='LoadAnnotations', with_bbox=True), dict( type='PackDetInputs', meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape', 'scale_factor', 'text', 'custom_entities')) ], backend_args=None, return_classes=True)) test_dataloader = dict( batch_size=1, num_workers=2, persistent_workers=True, drop_last=False, sampler=dict(type='DefaultSampler', shuffle=False), dataset=dict( type='CocoDataset', data_root=data_root, metainfo=METAINFO, ann_file='val.json', data_prefix=dict(img=''), test_mode=True, pipeline=[ dict( type='LoadImageFromFile', backend_args=None, imdecode_backend='pillow'), dict( type='FixScaleResize', scale=img_scale, keep_ratio=True, backend='pillow'), dict(type='LoadAnnotations', with_bbox=True), dict( type='PackDetInputs', meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape', 'scale_factor', 'text', 'custom_entities')) ], backend_args=None, return_classes=True)) val_evaluator = dict( type='CocoMetric', ann_file=data_root + '/val.json', metric='bbox', format_only=False, backend_args=None) test_evaluator = dict( type='CocoMetric', ann_file=data_root + '/val.json', metric='bbox', format_only=False, backend_args=None) train_cfg = dict(type='EpochBasedTrainLoop', max_epochs=12, val_interval=1) val_cfg = dict(type='ValLoop') test_cfg = dict(type='TestLoop') param_scheduler = [ dict( type='LinearLR', start_factor=0.001, by_epoch=False, begin=0, end=500), dict( type='MultiStepLR', begin=0, end=12, by_epoch=True, milestones=[8, 11], gamma=0.1) ] optim_wrapper = dict( type='OptimWrapper', optimizer=dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)) auto_scale_lr = dict(enable=False, base_batch_size=16) default_scope = 'mmdet' default_hooks = dict( timer=dict(type='IterTimerHook'), logger=dict(type='LoggerHook', interval=10), param_scheduler=dict(type='ParamSchedulerHook'), checkpoint=dict(type='CheckpointHook', interval=5, max_keep_ckpts=3, save_best='auto'), sampler_seed=dict(type='DistSamplerSeedHook'), visualization=dict(type='DetVisualizationHook')) env_cfg = dict( cudnn_benchmark=False, mp_cfg=dict(mp_start_method='fork', opencv_num_threads=0), dist_cfg=dict(backend='nccl')) vis_backends = [dict(type='LocalVisBackend')] visualizer = dict( type='DetLocalVisualizer', vis_backends=[dict(type='LocalVisBackend')], name='visualizer') log_processor = dict(type='LogProcessor', window_size=50, by_epoch=True) log_level = 'INFO' load_from = None resume = False lang_model_name = 'bert-base-uncased' model = dict( type='GLIP', data_preprocessor=dict( type='DetDataPreprocessor', mean=[103.53, 116.28, 123.675], std=[57.375, 57.12, 58.395], bgr_to_rgb=False, pad_size_divisor=32), backbone=dict( type='SwinTransformer', embed_dims=96, depths=[2, 2, 6, 2], num_heads=[3, 6, 12, 24], window_size=7, mlp_ratio=4, qkv_bias=True, qk_scale=None, drop_rate=0.0, attn_drop_rate=0.0, drop_path_rate=0.2, patch_norm=True, out_indices=(1, 2, 3), with_cp=False, convert_weights=False), neck=dict( type='FPN', in_channels=[192, 384, 768], out_channels=256, start_level=0, relu_before_extra_convs=True, add_extra_convs='on_output', num_outs=5), bbox_head=dict( type='ATSSVLFusionHead',
lang_model_name='bert-base-uncased',
lang_model_name='../checkpoints/bert-base-uncased/',
num_classes=num_classes,
in_channels=256,
feat_channels=256,
anchor_generator=dict(
type='AnchorGenerator',
ratios=[1.0],
octave_base_scale=8,
scales_per_octave=1,
strides=[8, 16, 32, 64, 128],
center_offset=0.5),
bbox_coder=dict(
type='DeltaXYWHBBoxCoderForGLIP',
target_means=[0.0, 0.0, 0.0, 0.0],
target_stds=[0.1, 0.1, 0.2, 0.2])),
language_model=dict(type='BertModel',
# name='bert-base-uncased',
name='../checkpoints/bert-base-uncased/'
),
train_cfg=dict(
assigner=dict(type='ATSSAssigner', topk=9),
allowed_border=-1,
pos_weight=-1,
debug=False),
test_cfg=dict(
nms_pre=1000,
min_bbox_size=0,
score_thr=0.05,
nms=dict(type='nms', iou_threshold=0.6),
max_per_img=100))launcher = 'none' work_dir = './work_dirs/glip_atss_swin-t_a_fpn_dyhead_pretrain_my_datasets'
xiaomoguhzz
Thanks for your error report and we appreciate it a lot.
Checklist
Describe the bug I have this problem when using GLIP. I downloaded the 'bert-base-uncased' independently on huggingface. The data set uses data I made myself
Reproduction
Did you make any modifications on the code or config? Did you understand what you have modified? I modified
data_root,num_classes,img_scale,metainfo,lang_model_name,language_modelWhat dataset did you use? my dataset use
CocoDatasetEnvironment sys.platform: linux Python: 3.9.16 (main, Mar 8 2023, 14:00:05) [GCC 11.2.0] CUDA available: True numpy_random_seed: 2147483648 GPU 0,1: NVIDIA GeForce RTX 3090 Ti CUDA_HOME: :/usr/local/cuda-11.3 GCC: gcc (Ubuntu 9.4.0-1ubuntu1~20.04.1) 9.4.0 PyTorch: 1.12.1+cu113 PyTorch compiling details: PyTorch built with:
TorchVision: 0.13.1+cu113 OpenCV: 4.7.0 MMEngine: 0.7.1 MMDetection: 3.1.0+
Error traceback If applicable, paste the error trackback here.
Bug fix If you have already identified the reason, you can provide the information here. If you are willing to create a PR to fix it, please also leave a comment here and that would be much appreciated!