we1pingyu commented 4 years ago

Checklist

I have searched related issues but cannot get the expected help.
The bug has not been fixed in the latest version.

Describe the bug Cannot modify classes in config.py. Have to modify hard code. And if you modify the config, the training will start with a evaluation. Only happens in mmdet v2.0. Reproduction

What command or script did you run?

./tools/dist_train.sh configs/cascade_rcnn/cascade_rcnn_x101_64x4d_fpn.py  2  --work-dir /data/cascade_rcnn_x101_64x4d_fpn

Did you make any modifications on the code or config? Did you understand what you have modified?


_base_ = './cascade_rcnn_r50_fpn_1x_coco.py'
model = dict(
type='CascadeRCNN',
pretrained='open-mmlab://resnext101_64x4d',
backbone=dict(
    type='ResNeXt',
    depth=101,
    groups=64,
    base_width=4,
    num_stages=4,
    out_indices=(0, 1, 2, 3),
    frozen_stages=1,
    norm_cfg=dict(type='BN', requires_grad=True),
    style='pytorch'),
rpn_head=dict(
    type='RPNHead',
    in_channels=256,
    feat_channels=256,
    anchor_generator=dict(
        type='AnchorGenerator',
        scales=[4],
        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='SmoothL1Loss', beta=1.0 / 9.0, loss_weight=1.0)),

roi_head=dict(
    type='CascadeRoIHead',
    num_stages=3,
    stage_loss_weights=[1, 0.5, 0.25],
    bbox_roi_extractor=dict(
        type='SingleRoIExtractor',
        roi_layer=dict(type='RoIAlign', out_size=7, sample_num=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=10,
            bbox_coder=dict(
                type='DeltaXYWHBBoxCoder',
                target_means=[0., 0., 0., 0.],
                target_stds=[0.1, 0.1, 0.2, 0.2]),
            reg_class_agnostic=True,
            loss_cls=dict(
                type='CrossEntropyLoss',
                use_sigmoid=False,
                loss_weight=1.0),
            loss_bbox=dict(type='SmoothL1Loss', beta=1.0,
                           loss_weight=1.0)),
        dict(
            type='Shared2FCBBoxHead',
            in_channels=256,
            fc_out_channels=1024,
            roi_feat_size=7,
            num_classes=10,
            bbox_coder=dict(
                type='DeltaXYWHBBoxCoder',
                target_means=[0., 0., 0., 0.],
                target_stds=[0.05, 0.05, 0.1, 0.1]),
            reg_class_agnostic=True,
            loss_cls=dict(
                type='CrossEntropyLoss',
                use_sigmoid=False,
                loss_weight=1.0),
            loss_bbox=dict(type='SmoothL1Loss', beta=1.0,
                           loss_weight=1.0)),
        dict(
            type='Shared2FCBBoxHead',
            in_channels=256,
            fc_out_channels=1024,
            roi_feat_size=7,
            num_classes=10,
            bbox_coder=dict(
                type='DeltaXYWHBBoxCoder',
                target_means=[0., 0., 0., 0.],
                target_stds=[0.033, 0.033, 0.067, 0.067]),
            reg_class_agnostic=True,
            loss_cls=dict(
                type='CrossEntropyLoss',
                use_sigmoid=False,
                loss_weight=1.0),
            loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0))
    ]))
# dataset settings
dataset_type = 'CocoDataset'
classes = ('pedestrian', 'people', 'bicycle', 'car', 'van', 'truck', 'tricycle', 'awning-tricycle', 'bus', 'motor')
data_root = '/data/'
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='MinIoURandomCrop',
     min_ious=(0.1, 0.3, 0.5, 0.7, 0.9),
     min_crop_size=0.3),
dict(type='Resize', img_scale=(1520, 1002), keep_ratio=True),
dict(type='RandomFlip', flip_ratio=0.5),
dict(type='Normalize', **img_norm_cfg),
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=(1520, 1002),
    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']),
    ])
]
data = dict(
samples_per_gpu=1,
workers_per_gpu=2,
train=dict(
    type=dataset_type,
    classes=classes,
    ann_file=data_root + 'xxx/train.json',
    img_prefix=data_root + 'xxx/images/',
    pipeline=train_pipeline),
val=dict(
    type=dataset_type,
    classes=classes,
    ann_file=data_root + 'xxx/val.json',
    img_prefix=data_root + 'xxx/images/',
    pipeline=test_pipeline),
test=dict(
    type=dataset_type,
    classes=classes,
    ann_file=data_root + 'xxx/val.json',
    img_prefix=data_root + 'xxx/images/',
    pipeline=test_pipeline))
evaluation = dict(interval=1, metric='bbox')
optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0001)
lr_config = dict(
policy='step',
warmup='linear',
warmup_iters=500,
warmup_ratio=1.0 / 3,
step=[12, 18, 26])
total_epochs = 30

3. What dataset did you use?

**Environment**

sys.platform: linux Python: 3.7.7 (default, May 7 2020, 21:25:33) [GCC 7.3.0] CUDA available: True CUDA_HOME: /usr/local/cuda-10.1 NVCC: Cuda compilation tools, release 10.1, V10.1.243 GPU 0,1: GeForce GTX 1080 Ti GCC: gcc (Ubuntu 7.5.0-3ubuntu1~18.04) 7.5.0 PyTorch: 1.3.1 PyTorch compiling details: PyTorch built with:

GCC 7.3
Intel(R) Math Kernel Library Version 2019.0.4 Product Build 20190411 for Intel(R) 64 architecture applications
Intel(R) MKL-DNN v0.20.5 (Git Hash 0125f28c61c1f822fd48570b4c1066f96fcb9b2e)
OpenMP 201511 (a.k.a. OpenMP 4.5)
NNPACK is enabled
CUDA Runtime 10.1
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 7.6.3
Magma 2.5.1
Build settings: BLAS=MKL, BUILD_NAMEDTENSOR=OFF, BUILD_TYPE=Release, CXX_FLAGS= -Wno-deprecated -fvisibility-inlines-hidden -fopenmp -DUSE_FBGEMM -DUSE_QNNPACK -DUSE_PYTORCH_QNNPACK -O2 -fPIC -Wno-narrowing -Wall -Wextra -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-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 -Wno-stringop-overflow, DISABLE_NUMA=1, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, USE_CUDA=True, 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: 0.4.2 OpenCV: 4.2.0 MMCV: 0.5.9 MMDetection: 2.0.0+204f751 MMDetection Compiler: GCC 7.5 MMDetection CUDA Compiler: 10.1


**Error traceback**
If applicable, paste the error trackback here.

Traceback (most recent call last): File "./tools/train.py", line 161, in main() File "./tools/train.py", line 157, in main meta=meta) File "/home/omnisky/yuweiping/mmdetection/mmdet/apis/train.py", line 179, in train_detector runner.run(data_loaders, cfg.workflow, cfg.total_epochs) File "/home/omnisky/anaconda3/envs/mmdet2/lib/python3.6/site-packages/mmcv/runner/runner.py", line 384, in run epoch_runner(data_loaders[i], kwargs) File "/home/omnisky/anaconda3/envs/mmdet2/lib/python3.6/site-packages/mmcv/runner/runner.py", line 293, in train self.call_hook('after_train_epoch') File "/home/omnisky/anaconda3/envs/mmdet2/lib/python3.6/site-packages/mmcv/runner/runner.py", line 245, in call_hook getattr(hook, fn_name)(self) File "/home/omnisky/yuweiping/mmdetection/mmdet/core/evaluation/eval_hooks.py", line 74, in after_train_epoch self.evaluate(runner, results) File "/home/omnisky/yuweiping/mmdetection/mmdet/core/evaluation/eval_hooks.py", line 32, in evaluate results, logger=runner.logger, self.eval_kwargs) File "/home/omnisky/yuweiping/mmdetection/mmdet/datasets/coco.py", line 343, in evaluate result_files, tmp_dir = self.format_results(results, jsonfile_prefix) File "/home/omnisky/yuweiping/mmdetection/mmdet/datasets/coco.py", line 306, in format_results result_files = self.results2json(results, jsonfile_prefix) File "/home/omnisky/yuweiping/mmdetection/mmdet/datasets/coco.py", line 240, in results2json if isinstance(results[0], list): IndexError: list index out of range

VoThanhDanh95 commented 4 years ago

I meet the same error. After taking a lot of time to debug, I found that I have to commend these 2 lines (file: datasets/custom.py, line number: 73-74). I still don't know is that a bug?

if self.custom_classes:

    #     self.data_infos = self.get_subset_by_classes()

igonro commented 4 years ago

Same error here. I think that the change of pycocotools broke some things. I've been using this repository with no problems for the past months, but with that change I'm facing a few bugs. :cry: