search

open-mmlab / mmdetection

OpenMMLab Detection Toolbox and Benchmark
https://mmdetection.readthedocs.io
Apache License 2.0
29.14k stars 9.39k forks source link

RecursionError: maximum recursion depth exceeded while calling a Python object #4593

Closed anshkumar closed 3 years ago

anshkumar commented 3 years ago

I'm getting following error while trying to train a model.

My training config is as follows:

# https://mmdetection.readthedocs.io/en/latest/tutorials/config.html#an-example-of-mask-r-cnn
model = dict(
    type='FasterRCNN',
    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',
        dcn=dict(type='DCNv2', deform_groups=4, fallback_on_stride=False),
        stage_with_dcn=(False, True, True, True)),
    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], # Basic scale of the anchor, the area of the anchor in one position of a feature map will be scale * base_sizes
            ratios=[0.05, 0.5, 1.0, 2.0, 20.0], # The ratio between height and width.
            strides=[4, 8, 16, 32, 64, 128]), # The strides of the anchor generator. This is consistent with the FPN feature strides. The strides will be taken as base_sizes if base_sizes is not set.
        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( # RoIHead encapsulates the second stage of two-stage/cascade detectors.
        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, # Number of classes for classification
            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))),
    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=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=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)))

# Modify dataset related settings
# dataset_type = None
# data_root = None
img_norm_cfg = None #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),
    # 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'])
]
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'])
    #     ])
]

classes = ('big_crack_and_cuts','decayed','major_hole','shriveled','sprouted','white_decay')
data = dict(
    samples_per_gpu=4,  # Batch size of a single GPU
    workers_per_gpu=4,  # Worker to pre-fetch data for each single GPU
    train=dict(
        type='CocoDataset',
        img_prefix='/home/deploy/ved/dataset/sort_potato_l2/train/images/',
        classes=classes,
        ann_file='/home/deploy/ved/dataset/sort_potato_l2/train/train.json',
        pipeline=train_pipeline,
        ),
    val=dict(
        type='CocoDataset',
        img_prefix='/home/deploy/ved/dataset/sort_potato_l2/val/images/',
        classes=classes,
        ann_file='/home/deploy/ved/dataset/sort_potato_l2/val/val.json',
        pipeline=test_pipeline),
    test=None
    )

evaluation = dict(  # The config to build the evaluation hook, refer to https://github.com/open-mmlab/mmdetection/blob/master/mmdet/core/evaluation/eval_hooks.py#L7 for more details.
    interval=1,  # Evaluation interval
    metric=['bbox'])  # Metrics used during evaluation
optimizer = dict(  # Config used to build optimizer, support all the optimizers in PyTorch whose arguments are also the same as those in PyTorch
    type='SGD',  # Type of optimizers, refer to https://github.com/open-mmlab/mmdetection/blob/master/mmdet/core/optimizer/default_constructor.py#L13 for more details
    lr=0.004,  # Learning rate of optimizers, see detail usages of the parameters in the documentaion of PyTorch
    momentum=0.9,  # Momentum
    weight_decay=0.0001)  # Weight decay of SGD
optimizer_config = dict(  # Config used to build the optimizer hook, refer to https://github.com/open-mmlab/mmcv/blob/master/mmcv/runner/hooks/optimizer.py#L8 for implementation details.
    grad_clip=None)  # Most of the methods do not use gradient clip
lr_config = dict(  # Learning rate scheduler config used to register LrUpdater hook
    policy='step',  # The policy of scheduler, also support CosineAnnealing, Cyclic, etc. Refer to details of supported LrUpdater from https://github.com/open-mmlab/mmcv/blob/master/mmcv/runner/hooks/lr_updater.py#L9.
    warmup='linear',  # The warmup policy, also support `exp` and `constant`.
    warmup_iters=500,  # The number of iterations for warmup
    warmup_ratio=
    0.001,  # The ratio of the starting learning rate used for warmup
    step=[8, 11])  # Steps to decay the learning rate
total_epochs = 50  # Total epochs to train the model
checkpoint_config = dict(  # Config to set the checkpoint hook, Refer to https://github.com/open-mmlab/mmcv/blob/master/mmcv/runner/hooks/checkpoint.py for implementation.
    interval=1,
    max_keep_ckpts=5)  # The save interval is 1
log_config = dict(  # config to register logger hook
    interval=50,  # Interval to print the log
    hooks=[
        dict(type='TensorboardLoggerHook')  # The Tensorboard logger is also supported
        # dict(type='TextLoggerHook')
    ])  # The logger used to record the training process.
dist_params = dict(backend='nccl')  # Parameters to setup distributed training, the port can also be set.
log_level = 'INFO'  # The level of logging.
load_from = None  # load models as a pre-trained model from a given path. This will not resume training.
resume_from = None  # Resume checkpoints from a given path, the training will be resumed from the epoch when the checkpoint's is saved.
workflow = [('train', 1)]  # Workflow for runner. [('train', 1)] means there is only one workflow and the workflow named 'train' is executed once. The workflow trains the model by 12 epochs according to the total_epochs.
work_dir = '/home/deploy/ved/faster_rcnn_r50_fpn_mdconv_c3-c5_group4'  # Directory to save the model checkpoints and logs for the current experiments.
gpu_ids = [0]

I'm using a custom dataset.

Environment

fatal: not a git repository (or any of the parent directories): .git
sys.platform: linux
Python: 3.7.9 (default, Aug 31 2020, 12:42:55) [GCC 7.3.0]
CUDA available: True
GPU 0: Tesla P100-PCIE-16GB
CUDA_HOME: /usr/local/cuda
NVCC: Cuda compilation tools, release 10.2, V10.2.89
GCC: gcc (Ubuntu 7.5.0-3ubuntu1~18.04) 7.5.0
PyTorch: 1.6.0
PyTorch compiling details: PyTorch built with:
  - GCC 7.3
  - C++ Version: 201402
  - Intel(R) Math Kernel Library Version 2020.0.2 Product Build 20200624 for Intel(R) 64 architecture applications
  - Intel(R) MKL-DNN v1.5.0 (Git Hash e2ac1fac44c5078ca927cb9b90e1b3066a0b2ed0)
  - OpenMP 201511 (a.k.a. OpenMP 4.5)
  - NNPACK is enabled
  - CPU capability usage: AVX2
  - CUDA Runtime 10.2
  - 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_37,code=compute_37
  - CuDNN 7.6.5
  - Magma 2.5.2
  - Build settings: BLAS=MKL, BUILD_TYPE=Release, CXX_FLAGS= -Wno-deprecated -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -fopenmp -DNDEBUG -DUSE_FBGEMM -DUSE_QNNPACK -DUSE_PYTORCH_QNNPACK -DUSE_XNNPACK -DUSE_VULKAN_WRAPPER -O2 -fPIC -Wno-narrowing -Wall -Wextra -Werror=return-type -Wno-missing-field-initializers -Wno-type-limits -Wno-array-bounds -Wno-unknown-pragmas -Wno-sign-compare -Wno-unused-parameter -Wno-unused-variable -Wno-unused-function -Wno-unused-result -Wno-unused-local-typedefs -Wno-strict-overflow -Wno-strict-aliasing -Wno-error=deprecated-declarations -Wno-stringop-overflow -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 -Wno-stringop-overflow, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, USE_CUDA=ON, USE_EXCEPTION_PTR=1, USE_GFLAGS=OFF, USE_GLOG=OFF, USE_MKL=ON, USE_MKLDNN=ON, USE_MPI=OFF, USE_NCCL=ON, USE_NNPACK=ON, USE_OPENMP=ON, USE_STATIC_DISPATCH=OFF, 

TorchVision: 0.7.0
OpenCV: 4.5.1
MMCV: 1.2.6
MMCV Compiler: GCC 7.3
MMCV CUDA Compiler: 10.2
MMDetection: 2.9.0+

Error traceback

2021-02-06 08:03:34,562 - mmdet - INFO - load model from: torchvision://resnet50
2021-02-06 08:03:34,766 - mmdet - WARNING - The model and loaded state dict do not match exactly

unexpected key in source state_dict: fc.weight, fc.bias

missing keys in source state_dict: layer2.0.conv2.conv_offset.weight, layer2.0.conv2.conv_offset.bias, layer2.1.conv2.conv_offset.weight, layer2.1.conv2.conv_offset.bias, layer2.2.conv2.conv_offset.weight, layer2.2.conv2.conv_offset.bias, layer2.3.conv2.conv_offset.weight, layer2.3.conv2.conv_offset.bias, layer3.0.conv2.conv_offset.weight, layer3.0.conv2.conv_offset.bias, layer3.1.conv2.conv_offset.weight, layer3.1.conv2.conv_offset.bias, layer3.2.conv2.conv_offset.weight, layer3.2.conv2.conv_offset.bias, layer3.3.conv2.conv_offset.weight, layer3.3.conv2.conv_offset.bias, layer3.4.conv2.conv_offset.weight, layer3.4.conv2.conv_offset.bias, layer3.5.conv2.conv_offset.weight, layer3.5.conv2.conv_offset.bias, layer4.0.conv2.conv_offset.weight, layer4.0.conv2.conv_offset.bias, layer4.1.conv2.conv_offset.weight, layer4.1.conv2.conv_offset.bias, layer4.2.conv2.conv_offset.weight, layer4.2.conv2.conv_offset.bias

fatal: not a git repository (or any of the parent directories): .git
2021-02-06 08:03:36,760 - mmdet - INFO - Start running, host: deploy@GPU-NISHANT-VM5, work_dir: /home/deploy/ved/faster_rcnn_r50_fpn_mdconv_c3-c5_group4
2021-02-06 08:03:36,760 - mmdet - INFO - workflow: [('train', 1)], max: 50 epochs
Traceback (most recent call last):
  File "/home/deploy/mmdetection/tools/train.py", line 187, in <module>
    main()
  File "/home/deploy/mmdetection/tools/train.py", line 183, in main
    meta=meta)
  File "/home/deploy/mmdetection/mmdet/apis/train.py", line 150, in train_detector
    runner.run(data_loaders, cfg.workflow, cfg.total_epochs)
  File "/home/deploy/miniconda3/envs/mmdetection/lib/python3.7/site-packages/mmcv/runner/epoch_based_runner.py", line 125, in run
    epoch_runner(data_loaders[i], **kwargs)
  File "/home/deploy/miniconda3/envs/mmdetection/lib/python3.7/site-packages/mmcv/runner/epoch_based_runner.py", line 47, in train
    for i, data_batch in enumerate(self.data_loader):
  File "/home/deploy/miniconda3/envs/mmdetection/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 363, in __next__
    data = self._next_data()
  File "/home/deploy/miniconda3/envs/mmdetection/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 989, in _next_data
    return self._process_data(data)
  File "/home/deploy/miniconda3/envs/mmdetection/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 1014, in _process_data
    data.reraise()
  File "/home/deploy/miniconda3/envs/mmdetection/lib/python3.7/site-packages/torch/_utils.py", line 395, in reraise
    raise self.exc_type(msg)
RecursionError: Caught RecursionError in DataLoader worker process 0.
Original Traceback (most recent call last):
  File "/home/deploy/miniconda3/envs/mmdetection/lib/python3.7/site-packages/torch/utils/data/_utils/worker.py", line 185, in _worker_loop
    data = fetcher.fetch(index)
  File "/home/deploy/miniconda3/envs/mmdetection/lib/python3.7/site-packages/torch/utils/data/_utils/fetch.py", line 47, in fetch
    return self.collate_fn(data)
  File "/home/deploy/miniconda3/envs/mmdetection/lib/python3.7/site-packages/mmcv/parallel/collate.py", line 81, in collate
    for key in batch[0]
  File "/home/deploy/miniconda3/envs/mmdetection/lib/python3.7/site-packages/mmcv/parallel/collate.py", line 81, in <dictcomp>
    for key in batch[0]
  File "/home/deploy/miniconda3/envs/mmdetection/lib/python3.7/site-packages/mmcv/parallel/collate.py", line 81, in collate
    for key in batch[0]
  File "/home/deploy/miniconda3/envs/mmdetection/lib/python3.7/site-packages/mmcv/parallel/collate.py", line 81, in <dictcomp>
    for key in batch[0]
  File "/home/deploy/miniconda3/envs/mmdetection/lib/python3.7/site-packages/mmcv/parallel/collate.py", line 77, in collate
    return [collate(samples, samples_per_gpu) for samples in transposed]
  File "/home/deploy/miniconda3/envs/mmdetection/lib/python3.7/site-packages/mmcv/parallel/collate.py", line 77, in <listcomp>
    return [collate(samples, samples_per_gpu) for samples in transposed]
  ...

  File "/home/deploy/miniconda3/envs/mmdetection/lib/python3.7/site-packages/mmcv/parallel/collate.py", line 23, in collate
    if not isinstance(batch, Sequence):
  File "/home/deploy/miniconda3/envs/mmdetection/lib/python3.7/abc.py", line 139, in __instancecheck__
    return _abc_instancecheck(cls, instance)
  File "/home/deploy/miniconda3/envs/mmdetection/lib/python3.7/abc.py", line 143, in __subclasscheck__
    return _abc_subclasscheck(cls, subclass)
RecursionError: maximum recursion depth exceeded while calling a Python object

My custom training json is this.

anshkumar commented 3 years ago

The problem was with the data pipeline. When I changed it to the following, it worked:

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),
    dict(type='Resize', img_scale=(750, 750), keep_ratio=True),
    dict(type='RandomFlip', flip_ratio=0.5),
    dict(type='Normalize', **img_norm_cfg),
    dict(type='DefaultFormatBundle'),
    dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels'])
]
test_pipeline = [
    dict(type='LoadImageFromFile'),
    dict(
        type='MultiScaleFlipAug',
        img_scale=(750, 750),
        flip=False,
        transforms=[
            dict(type='Resize', keep_ratio=True),
            dict(type='RandomFlip'),
            dict(type='Normalize',**img_norm_cfg),
            dict(type='Pad', size_divisor=32),
            dict(type='ImageToTensor', keys=['img']),
            dict(type='Collect', keys=['img'])
        ])
]
neel04 commented 3 years ago

@ZwwWayne @anshkumar I have the same problem and I am unable to solve. despite specifying my datasets and inheriting from base, I am lost as to how I should proceed and how configs are to be created. :( they seem pretty complicated...