search

open-mmlab / mmtracking

OpenMMLab Video Perception Toolbox. It supports Video Object Detection (VID), Multiple Object Tracking (MOT), Single Object Tracking (SOT), Video Instance Segmentation (VIS) with a unified framework.
https://mmtracking.readthedocs.io/en/latest/
Apache License 2.0
3.55k stars 595 forks source link

TypeError: forward_train() missing 4 required positional arguments: 'ref_img', 'ref_img_metas', 'ref_gt_bboxes', and 'ref_gt_labels' #804

Open lijoe123 opened 1 year ago

lijoe123 commented 1 year ago

Hello, I want to train the masktrack_rcnn with the coco dataset. So i had reset the dataset of masktrack_rcnn_r50_fpn_12e_youtubevis2019.py------'../../_base_/datasets/coco_instance.py' and the num_classes=6. image

By the way, i had reset the /home/music/Downloads/mmtracking-master/mmtrack/datasets/coco_video_dataset.py-------CLASSES = ('aircraft', 'buildings', 'electrical', 'person', 'tree', 'wire') and theload_as_video=False image

And my env:

------------------------------------------------------------
sys.platform: linux
Python: 3.8.15 (default, Nov 24 2022, 15:19:38) [GCC 11.2.0]
CUDA available: True
GPU 0: NVIDIA GeForce RTX 3090 Ti
CUDA_HOME: None
GCC: gcc (Ubuntu 9.4.0-1ubuntu1~20.04.1) 9.4.0
PyTorch: 1.12.1
PyTorch compiling details: PyTorch built with:
  - GCC 9.3
  - C++ Version: 201402
  - Intel(R) oneAPI Math Kernel Library Version 2021.4-Product Build 20210904 for Intel(R) 64 architecture applications
  - Intel(R) MKL-DNN v2.6.0 (Git Hash 52b5f107dd9cf10910aaa19cb47f3abf9b349815)
  - OpenMP 201511 (a.k.a. OpenMP 4.5)
  - LAPACK is enabled (usually provided by MKL)
  - NNPACK is enabled
  - CPU capability usage: AVX2
  - CUDA Runtime 11.3
  - NVCC architecture flags: -gencode;arch=compute_37,code=sm_37;-gencode;arch=compute_50,code=sm_50;-gencode;arch=compute_60,code=sm_60;-gencode;arch=compute_61,code=sm_61;-gencode;arch=compute_70,code=sm_70;-gencode;arch=compute_75,code=sm_75;-gencode;arch=compute_80,code=sm_80;-gencode;arch=compute_86,code=sm_86;-gencode;arch=compute_37,code=compute_37
  - CuDNN 8.3.2  (built against CUDA 11.5)
  - Magma 2.5.2
  - Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, CUDA_VERSION=11.3, CUDNN_VERSION=8.3.2, CXX_COMPILER=/opt/rh/devtoolset-9/root/usr/bin/c++, CXX_FLAGS= -fabi-version=11 -Wno-deprecated -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -fopenmp -DNDEBUG -DUSE_KINETO -DUSE_FBGEMM -DUSE_QNNPACK -DUSE_PYTORCH_QNNPACK -DUSE_XNNPACK -DSYMBOLICATE_MOBILE_DEBUG_HANDLE -DEDGE_PROFILER_USE_KINETO -O2 -fPIC -Wno-narrowing -Wall -Wextra -Werror=return-type -Wno-missing-field-initializers -Wno-type-limits -Wno-array-bounds -Wno-unknown-pragmas -Wno-unused-parameter -Wno-unused-function -Wno-unused-result -Wno-unused-local-typedefs -Wno-strict-overflow -Wno-strict-aliasing -Wno-error=deprecated-declarations -Wno-stringop-overflow -Wno-psabi -Wno-error=pedantic -Wno-error=redundant-decls -Wno-error=old-style-cast -fdiagnostics-color=always -faligned-new -Wno-unused-but-set-variable -Wno-maybe-uninitialized -fno-math-errno -fno-trapping-math -Werror=format -Werror=cast-function-type -Wno-stringop-overflow, LAPACK_INFO=mkl, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, TORCH_VERSION=1.12.1, USE_CUDA=ON, USE_CUDNN=ON, USE_EXCEPTION_PTR=1, USE_GFLAGS=OFF, USE_GLOG=OFF, USE_MKL=ON, USE_MKLDNN=OFF, USE_MPI=OFF, USE_NCCL=ON, USE_NNPACK=ON, USE_OPENMP=ON, USE_ROCM=OFF, 

TorchVision: 0.13.1
OpenCV: 4.6.0
MMCV: 1.7.0
MMCV Compiler: GCC 9.3
MMCV CUDA Compiler: 11.3
MMTracking: 0.14.0+

This my config:

2022-12-16 10:09:31,585 - mmtrack - INFO - Distributed training: False
2022-12-16 10:09:32,054 - mmtrack - INFO - Config:
model = dict(
    detector=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, 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=6,
                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=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=6,
                loss_mask=dict(
                    type='CrossEntropyLoss', use_mask=True, loss_weight=1.0))),
        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=64,
                    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=200,
                max_per_img=200,
                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=128,
                    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=200,
                max_per_img=200,
                nms=dict(type='nms', iou_threshold=0.7),
                min_bbox_size=0),
            rcnn=dict(
                score_thr=0.01,
                nms=dict(type='nms', iou_threshold=0.5),
                max_per_img=100,
                mask_thr_binary=0.5)),
        init_cfg=dict(
            type='Pretrained',
            checkpoint=
            'https://download.openmmlab.com/mmdetection/v2.0/mask_rcnn/mask_rcnn_r50_fpn_1x_coco/mask_rcnn_r50_fpn_1x_coco_20200205-d4b0c5d6.pth'
        )),
    type='MaskTrackRCNN',
    track_head=dict(
        type='RoITrackHead',
        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]),
        embed_head=dict(
            type='RoIEmbedHead',
            num_fcs=2,
            roi_feat_size=7,
            in_channels=256,
            fc_out_channels=1024),
        train_cfg=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=128,
                pos_fraction=0.25,
                neg_pos_ub=-1,
                add_gt_as_proposals=True),
            pos_weight=-1,
            debug=False)),
    tracker=dict(
        type='MaskTrackRCNNTracker',
        match_weights=dict(det_score=1.0, iou=2.0, det_label=10.0),
        num_frames_retain=20))
dataset_type = 'CocoDataset'
data_root = '/home/music/Downloads/mmtracking-master/data/coco/'
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),
    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 = dict(
    samples_per_gpu=6,
    workers_per_gpu=2,
    train=dict(
        type='CocoDataset',
        ann_file=
        '/home/music/Downloads/mmtracking-master/data/coco/annotations/train.json',
        img_prefix=
        '/home/music/Downloads/mmtracking-master/data/coco/train2023/',
        pipeline=[
            dict(type='LoadImageFromFile'),
            dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
            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'])
        ]),
    val=dict(
        type='CocoDataset',
        ann_file=
        '/home/music/Downloads/mmtracking-master/data/coco/annotations/val.json',
        img_prefix='/home/music/Downloads/mmtracking-master/data/coco/val2023/',
        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'])
                ])
        ]),
    test=dict(
        type='CocoDataset',
        ann_file=
        '/home/music/Downloads/mmtracking-master/data/coco/annotations/val.json',
        img_prefix='/home/music/Downloads/mmtracking-master/data/coco/val2023/',
        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'])
                ])
        ]))
evaluation = dict(metric=['bbox', 'segm'], classwise=True)
optimizer = dict(type='SGD', lr=0.00125, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
checkpoint_config = dict(interval=1)
log_config = dict(interval=50, hooks=[dict(type='TextLoggerHook')])
dist_params = dict(backend='nccl')
log_level = 'INFO'
load_from = None
resume_from = None
workflow = [('train', 1)]
opencv_num_threads = 0
mp_start_method = 'fork'
lr_config = dict(
    policy='step',
    warmup='linear',
    warmup_iters=500,
    warmup_ratio=0.3333333333333333,
    step=[8, 11])
total_epochs = 12
work_dir = 'work_dir/masktrack_coco'
gpu_ids = [0]

Best wish! Thank you!

lijoe123 commented 1 year ago

And the error: image

dyhBUPT commented 1 year ago

Hi, it seems that you use CocoDataset in your config file, not CocoVideoDataset.

lijoe123 commented 1 year ago

Thank you for your answer. But the coco_video_dataset show that class: CocoVideoDataset(**CocoDataset**):, image Are the cocovideodataset(cocodataset) different? I wonder if they can share？ And you told me that, i can use the CocoDataset from mmdet in #801 . Could tell me how to use the cocodataset to train the mmtracking model?

dyhBUPT commented 1 year ago

To train MaskRCNN, you need to pass ref_xxx to the model, as in: https://github.com/open-mmlab/mmtracking/blob/b1679f990bce7abc18e852004d2f70b09904e238/mmtrack/models/vis/masktrack_rcnn.py#L40-L57

Therefore, you need to use CocoVideoDataset, which can prepare ref_xxx data, as in: https://github.com/open-mmlab/mmtracking/blob/b1679f990bce7abc18e852004d2f70b09904e238/mmtrack/datasets/coco_video_dataset.py#L252-L270

Please check it.

lijoe123 commented 1 year ago

Thank you for your reply! I had check the two script above, and i had try to prepare ref_xxx data according the mmdetection/mmdet/datasets/coco.py. But it fail. I am appreciate that if you can give me an example about how to use the coco dataset. Thank you so much.

dyhBUPT commented 1 year ago

I'm sorry but I haven't tried to use coco to train VIS model. Maybe you can refer to the CocoVideoDataset.

Best wishes.

lijoe123 commented 1 year ago

It's OK. Thank you so much!