search

czczup / ViT-Adapter

[ICLR 2023 Spotlight] Vision Transformer Adapter for Dense Predictions
https://arxiv.org/abs/2205.08534
Apache License 2.0
1.21k stars 135 forks source link

Error during detection Train!! TypeError: '<' not supported between instances of 'str' and 'int' #128

Open fine4546 opened 1 year ago

fine4546 commented 1 year ago

File "./train.py", line 194, in main() File "./train.py", line 184, in main train_detector(model, File "/home/ddh/anaconda3/envs/mm38_Detec_cu11_1/lib/python3.8/site-packages/mmdet/apis/train.py", line 208, in train_detector runner.run(data_loaders, cfg.workflow) File "/home/ddh/anaconda3/envs/mm38_Detec_cu11_1/lib/python3.8/site-packages/mmcv/runner/epoch_based_runner.py", line 127, in run epoch_runner(data_loaders[i], **kwargs) File "/home/ddh/anaconda3/envs/mm38_Detec_cu11_1/lib/python3.8/site-packages/mmcv/runner/epoch_based_runner.py", line 54, in train self.call_hook('after_train_epoch') File "/home/ddh/anaconda3/envs/mm38_Detec_cu11_1/lib/python3.8/site-packages/mmcv/runner/base_runner.py", line 309, in call_hook getattr(hook, fn_name)(self) File "/home/ddh/anaconda3/envs/mm38_Detec_cu11_1/lib/python3.8/site-packages/mmcv/runner/hooks/evaluation.py", line 267, in after_train_epoch self._do_evaluate(runner) File "/home/ddh/anaconda3/envs/mm38_Detec_cu11_1/lib/python3.8/site-packages/mmdet/core/evaluation/eval_hooks.py", line 125, in _do_evaluate key_score = self.evaluate(runner, results) File "/home/ddh/anaconda3/envs/mm38_Detec_cu11_1/lib/python3.8/site-packages/mmcv/runner/hooks/evaluation.py", line 361, in evaluate eval_res = self.dataloader.dataset.evaluate( File "/home/ddh/anaconda3/envs/mm38_Detec_cu11_1/lib/python3.8/site-packages/mmdet/datasets/coco.py", line 549, in evaluate cocoEval.evaluate() File "/home/ddh/anaconda3/envs/mm38_Detec_cu11_1/lib/python3.8/site-packages/pycocotools/cocoeval.py", line 154, in evaluate self.evalImgs = [evaluateImg(imgId, catId, areaRng, maxDet) File "/home/ddh/anaconda3/envs/mm38_Detec_cu11_1/lib/python3.8/site-packages/pycocotools/cocoeval.py", line 154, in self.evalImgs = [evaluateImg(imgId, catId, areaRng, maxDet) File "/home/ddh/anaconda3/envs/mm38_Detec_cu11_1/lib/python3.8/site-packages/pycocotools/cocoeval.py", line 251, in evaluateImg if g['ignore'] or (g['area']<aRng[0] or g['area']>aRng[1]): TypeError: '<' not supported between instances of 'str' and 'int'

Why is this happening? How can I fix it? Thank you

other config ======================================================================= detection/configs/mask_rcnn_mask_rcnn_deit_adapter_small_fpn_3x_coco.py

Copyright (c) Shanghai AI Lab. All rights reserved.

base = [ '../base/models/mask_rcnn_r50_fpn.py', '../base/datasets/coco_instance.py', '../base/schedules/schedule_3x.py', '../base/default_runtime.py' ]

pretrained = 'https://dl.fbaipublicfiles.com/deit/deit_small_patch16_224-cd65a155.pth'

pretrained = None #'pretrained/deit_small_patch16_224-cd65a155.pth' model = dict( backbone=dict( delete=True, type='ViTAdapter', patch_size=16, embed_dim=384, depth=12, num_heads=6, mlp_ratio=4, drop_path_rate=0.2, conv_inplane=64, n_points=4, deform_num_heads=6, cffn_ratio=0.25, deform_ratio=1.0, interaction_indexes=[[0, 2], [3, 5], [6, 8], [9, 11]], window_attn=[True, True, False, True, True, False, True, True, False, True, True, False], window_size=[14, 14, None, 14, 14, None, 14, 14, None, 14, 14, None], pretrained=pretrained), neck=dict( type='FPN', in_channels=[384, 384, 384, 384], out_channels=256, num_outs=5))

optimizer

img_norm_cfg = dict( mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)

augmentation strategy originates from DETR / Sparse RCNN

train_pipeline = [ dict(type='LoadImageFromFile'), dict(type='LoadAnnotations', with_bbox=True, with_mask=True), dict(type='RandomFlip', flip_ratio=0.5), dict(type='AutoAugment', policies=[ [ dict(type='Resize', img_scale=[(480, 1333), (512, 1333), (544, 1333), (576, 1333), (608, 1333), (640, 1333), (672, 1333), (704, 1333), (736, 1333), (768, 1333), (800, 1333)], multiscale_mode='value', keep_ratio=True) ], [ dict(type='Resize', img_scale=[(400, 1333), (500, 1333), (600, 1333)], multiscale_mode='value', keep_ratio=True), dict(type='RandomCrop', crop_type='absolute_range', crop_size=(384, 600), allow_negative_crop=True), dict(type='Resize', img_scale=[(480, 1333), (512, 1333), (544, 1333), (576, 1333), (608, 1333), (640, 1333), (672, 1333), (704, 1333), (736, 1333), (768, 1333), (800, 1333)], multiscale_mode='value', override=True, keep_ratio=True) ] ]), dict(type='RandomCrop', crop_type='absolute_range', crop_size=(1024, 1024), allow_negative_crop=True), dict(type='Normalize', **img_norm_cfg), dict(type='Pad', size_divisor=32), dict(type='DefaultFormatBundle'), dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks']), ] data = dict(train=dict(pipeline=train_pipeline)) optimizer = dict( delete=True, type='AdamW', lr=0.0001, weight_decay=0.05, paramwise_cfg=dict( custom_keys={ 'level_embed': dict(decay_mult=0.), 'pos_embed': dict(decay_mult=0.), 'norm': dict(decay_mult=0.), 'bias': dict(decay_mult=0.) })) optimizer_config = dict(grad_clip=None) fp16 = dict(loss_scale=dict(init_scale=512)) checkpoint_config = dict( interval=1, max_keep_ckpts=3, save_last=True, )

============================================================== mask_rcnn_r50_fpn.py

model settings

model = dict( type='MaskRCNN', 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', init_cfg=dict(type='Pretrained', checkpoint='torchvision://resnet50')), 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], 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='StandardRoIHead', 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=32, 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, loss_cls=dict( type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0), loss_bbox=dict(type='L1Loss', loss_weight=1.0)), 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='FCNMaskHead', num_convs=4, in_channels=256, conv_out_channels=256, num_classes=32, loss_mask=dict( type='CrossEntropyLoss', use_mask=True, 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,
            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_pre=2000,
        max_per_img=1000,
        nms=dict(type='nms', iou_threshold=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_pre=1000,
        max_per_img=1000,
        nms=dict(type='nms', iou_threshold=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)))
czczup commented 11 months ago

Thanks for your feedback. I have not encountered this problem. I guess it may be due to the environment. Can you give me more information about your environment?