hi tnx for implementation im using forked orginal ReDet i need add Poly IoU Loss but in adding ext i dont know how to that in colab cell i put this:

 #!/usr/bin/env python
import os
import subprocess
import time
# from setuptools import find_packages, setup


import torch
from torch.utils.cpp_extension import (BuildExtension, CppExtension,
                                       CUDAExtension)
 
 
 
 def make_cuda_ext(name, module, sources, sources_cuda=[]):

    define_macros = []
    extra_compile_args = {'cxx': []}

    if torch.cuda.is_available() or os.getenv('FORCE_CUDA', '0') == '1':
        define_macros += [('WITH_CUDA', None)]
        extension = CUDAExtension
        extra_compile_args['nvcc'] = [
            '-D__CUDA_NO_HALF_OPERATORS__',
            '-D__CUDA_NO_HALF_CONVERSIONS__',
            '-D__CUDA_NO_HALF2_OPERATORS__',
        ]
        sources += sources_cuda
    else:
        print(f'Compiling {name} without CUDA')
        extension = CppExtension
        # raise EnvironmentError('CUDA is required to compile MMDetection!')

    return extension(
        name=f'{module}.{name}',
        sources=[os.path.join(*module.split('.'), p) for p in sources],
        define_macros=define_macros,
        extra_compile_args=extra_compile_args)

  setup(
      ext_modules=[
                      make_cuda_ext(
                        name='convex_ext',
                        module='mmdet.ops.convex',
                        sources=[
                            'src/convex_cpu.cpp',
                            'src/convex_ext.cpp'
                        ],
                        sources_cuda=['src/convex_cuda.cu']),
               ],
        cmdclass={'build_ext': BuildExtension},
        zip_safe=False
        )

and got err:

File "<ipython-input-44-a399c1bfcad4>", line 38
    setup(
          ^
IndentationError: unindent does not match any outer indentation level

i want add it seperatly what should i do??

Traceback (most recent call last): File "tools/test.py", line 153, in main() File "tools/test.py", line 147, in main dataset.format_results(outputs, **kwargs) File "/root/wtl2/OBBDetection/mmdet/datasets/obb/dota.py", line 123, in format_results bboxes, scores = dets[:, :-1], dets[:, [-1]] dets的shape是(6,)，我怀疑是dets.shape的问题

1修改类别为我自己数据集的类别，但继续用dota1格式。 'DOTA1_0': ('ore-oil', 'Container', 'Fishing', 'yacht', 'LawEnforce', 'Small', 'Passenger'), #'DOTA1_0': ('large-vehicle', 'swimming-pool', 'helicopter', 'bridge', # 'plane', 'ship', 'soccer-ball-field', 'basketball-court', # 'ground-track-field', 'small-vehicle', 'baseball-diamond', # 'tennis-court', 'roundabout', 'storage-tank', 'harbor'),

2配置文件里面修改类别数目 num_classes=7,

3运行报错：2021-08-31 20:17:55,895 - mmdet - INFO - workflow: [('train', 1)], max: 12 epochs Traceback (most recent call last): File "tools/train.py", line 153, in main() File "tools/train.py", line 142, in main train_detector( File "/media/asus/299D817A2D97AD94/ok_PROJs/OBBDetection/mmdet/apis/train.py", line 129, in train_detector runner.run(data_loaders, cfg.workflow, cfg.total_epochs) File "/home/asus/anaconda3/envs/Beta/lib/python3.8/site-packages/mmcv/runner/epoch_based_runner.py", line 122, in run epoch_runner(data_loaders[i], **kwargs) File "/home/asus/anaconda3/envs/Beta/lib/python3.8/site-packages/mmcv/runner/epoch_based_runner.py", line 27, in train for i, data_batch in enumerate(data_loader): File "/home/asus/anaconda3/envs/Beta/lib/python3.8/site-packages/torch/utils/data/dataloader.py", line 435, in next data = self._next_data() File "/home/asus/anaconda3/envs/Beta/lib/python3.8/site-packages/torch/utils/data/dataloader.py", line 1085, in _next_data return self._process_data(data) File "/home/asus/anaconda3/envs/Beta/lib/python3.8/site-packages/torch/utils/data/dataloader.py", line 1111, in _process_data data.reraise() File "/home/asus/anaconda3/envs/Beta/lib/python3.8/site-packages/torch/_utils.py", line 428, in reraise raise self.exc_type(msg) ValueError: Caught ValueError in DataLoader worker process 0. Original Traceback (most recent call last): File "/home/asus/anaconda3/envs/Beta/lib/python3.8/site-packages/torch/utils/data/_utils/worker.py", line 198, in _worker_loop data = fetcher.fetch(index) File "/home/asus/anaconda3/envs/Beta/lib/python3.8/site-packages/torch/utils/data/_utils/fetch.py", line 44, in fetch data = [self.dataset[idx] for idx in possibly_batched_index] File "/home/asus/anaconda3/envs/Beta/lib/python3.8/site-packages/torch/utils/data/_utils/fetch.py", line 44, in data = [self.dataset[idx] for idx in possibly_batched_index] File "/media/asus/299D817A2D97AD94/ok_PROJs/OBBDetection/mmdet/datasets/custom.py", line 187, in getitem data = self.prepare_train_img(idx) File "/media/asus/299D817A2D97AD94/ok_PROJs/OBBDetection/mmdet/datasets/custom.py", line 210, in prepare_train_img return self.pipeline(results) File "/media/asus/299D817A2D97AD94/ok_PROJs/OBBDetection/mmdet/datasets/pipelines/compose.py", line 40, in call data = t(data) File "/media/asus/299D817A2D97AD94/ok_PROJs/OBBDetection/mmdet/datasets/pipelines/obb/base.py", line 393, in call results['angle'] = self.get_random_angle(results) File "/media/asus/299D817A2D97AD94/ok_PROJs/OBBDetection/mmdet/datasets/pipelines/obb/base.py", line 303, in get_random_angle vert_lbls = [results['cls'].index(c) for c in self.vert_cls] File "/media/asus/299D817A2D97AD94/ok_PROJs/OBBDetection/mmdet/datasets/pipelines/obb/base.py", line 303, in vert_lbls = [results['cls'].index(c) for c in self.vert_cls] ValueError: tuple.index(x): x not in tuple

仿佛是类别哪里还需要修改，想问下，你有什么好的建议或者知道修改哪里么

I re-implemented your work for training Dota dataset but I got much lower mAP for dota test dataset.

*** training & validation**---------------------------------------------------------------------------------------------------------------

• dataset : DOTA - v1.0 (training, validation dataset -- all cropped by using your img_split.py)
• configuration : faster_rcnn_orpn_r101_fpn_1x_ms_rr_dota10.py
• parameters : not changed at all (same with your implementation)

*** test**-------------------------------------------------------------------------------------------------------------------------------------

• dataset : DOTA - v1.0 (test dataset -- all cropped by using your img_split.py)
• configuration : faster_rcnn_orpn_r101_fpn_1x_ms_rr_dota10.py
• used epoch 12 checkpoint
• sent to DOTA v 1.0 server - Evaluation of DOTA Task1 and got this result ---> mAP: 0.41229681978600863 ap of each class: plane:0.5396662332791309, baseball-diamond:0.2710892710892711, bridge:0.5154165616433038, ground-track-field:0.1484848484848485, small-vehicle:0.27250426663927574, large-vehicle:0.2622058637252267, ship:0.7108541529636384, tennis-court:0.5453417550191744, basketball-court:0.33560606060606063, storage-tank:0.09090909090909091, soccer-ball- field:0.22898154477101842, roundabout:0.19935158396696856, harbor:0.7828865404399028, swimming- pool:0.7302785521014554, helicopter:0.5508759711517627

According to your report, it should be 80.52 (backbone resnet101). What have I done wrong? What should I change? Waiting for your quick response! Thank you!

I am trying to run OBB with FCOS in dataset HRSC2016. To do so I have based the config.py on an example of OBB with FCOS in dataset DOTA and removed these two parts: dict(type='LoadDOTASpecialInfo') dict(type='DOTASpecialIgnore', ignore_size=2)

I managed to execute the training with no problem. Then, when I try to run the testing, I get this error. What am I doing wrong?

Starting loading HRSC dataset information.
Finishing loading HRSC, get 2124 images, using 0.171s.
load checkpoint from local path: work_dirs/fcos_obb_r50_caffe_fpn_gn-head_4x4_1x_hrsc/latest.pth
[>>>>>>>>>>>>>>>                                   ] 137/453, 17.9 task/s, elapsed: 8s, ETA:    18s
[>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>] 453/453, 17.9 task/s, elapsed: 25s, ETA:     0sTraceback (most recent call last):
  File "tools/test.py", line 153, in <module>
    main()
  File "tools/test.py", line 149, in main
    dataset.evaluate(outputs, args.eval, **kwargs)
  File "/work/OBBDetection/mmdet/datasets/obb/hrsc.py", line 126, in evaluate
    logger=logger)
  File "/work/OBBDetection/mmdet/core/evaluation/obb/obb_mean_ap.py", line 291, in eval_arb_map
    mean_ap, eval_results, dataset, area_ranges, logger=logger)
  File "/work/OBBDetection/mmdet/core/evaluation/obb/obb_mean_ap.py", line 354, in print_map_summary
    label_names[j], num_gts[i, j], results[j]['num_dets'],
IndexError: tuple index out of range

The configuration file is:

_base_ = [
    '../_base_/datasets/hrsc.py',
    '../_base_/schedules/schedule_1x.py',
    '../../_base_/default_runtime.py'
]
# model settings
model = dict(
    type='FCOSOBB',
    pretrained='open-mmlab://detectron/resnet50_caffe',
    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=False),
        norm_eval=True,
        style='caffe'),
    neck=dict(
        type='FPN',
        in_channels=[256, 512, 1024, 2048],
        out_channels=256,
        start_level=1,
        add_extra_convs=True,
        extra_convs_on_inputs=False,  # use P5
        num_outs=5,
        relu_before_extra_convs=True),
    bbox_head=dict(
        type='OBBFCOSHead',
        num_classes=15,
        in_channels=256,
        stacked_convs=4,
        feat_channels=256,
        strides=[8, 16, 32, 64, 128],
        scale_theta=True,
        loss_cls=dict(
            type='FocalLoss',
            use_sigmoid=True,
            gamma=2.0,
            alpha=0.25,
            loss_weight=1.0),
        loss_bbox=dict(type='PolyIoULoss', loss_weight=1.0),
        loss_centerness=dict(
            type='CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0)))
# training and testing settings
train_cfg = dict(
    assigner=dict(
        type='MaxIoUAssigner',
        pos_iou_thr=0.5,
        neg_iou_thr=0.4,
        min_pos_iou=0,
        ignore_iof_thr=-1),
    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='obb_nms', iou_thr=0.1),
    max_per_img=2000)
img_norm_cfg = dict(
    mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=False)
train_pipeline = [
    dict(type='LoadImageFromFile'),
    dict(type='LoadOBBAnnotations', with_bbox=True,
         with_label=True, obb_as_mask=True),
    dict(type='Resize', img_scale=(1024, 1024), keep_ratio=True),
    dict(type='OBBRandomFlip', h_flip_ratio=0.5, v_flip_ratio=0.5),
    dict(type='Normalize', **img_norm_cfg),
    dict(type='RandomOBBRotate', rotate_after_flip=True,
         angles=(0, 0), vert_rate=0.5, vert_cls=['roundabout', 'storage-tank']),
    dict(type='Pad', size_divisor=32),
    #dict(type='DOTASpecialIgnore', ignore_size=2),
    dict(type='FliterEmpty'),
    dict(type='Mask2OBB', obb_type='obb'),
    dict(type='OBBDefaultFormatBundle'),
    dict(type='OBBCollect', keys=['img', 'gt_bboxes', 'gt_obboxes', 'gt_labels'])
]
test_pipeline = [
    dict(type='LoadImageFromFile'),
    dict(
        type='MultiScaleFlipRotateAug',
        img_scale=[(1024, 1024)],
        h_flip=False,
        v_flip=False,
        rotate=False,
        transforms=[
            dict(type='Resize', keep_ratio=True),
            dict(type='OBBRandomFlip'),
            dict(type='Normalize', **img_norm_cfg),
            dict(type='RandomOBBRotate', rotate_after_flip=True),
            dict(type='Pad', size_divisor=32),
            dict(type='ImageToTensor', keys=['img']),
            dict(type='OBBCollect', keys=['img']),
        ])
]
data = dict(
    samples_per_gpu=2,
    workers_per_gpu=4,
    train=dict(pipeline=train_pipeline),
    val=dict(pipeline=test_pipeline),
    test=dict(pipeline=test_pipeline))
# optimizer
optimizer = dict(
    lr=0.0025, paramwise_cfg=dict(bias_lr_mult=2., bias_decay_mult=0.))
optimizer_config = dict(
    _delete_=True, grad_clip=dict(max_norm=35, norm_type=2))
# learning policy
lr_config = dict(
    policy='step',
    warmup='constant',
    warmup_iters=500,
    warmup_ratio=1.0 / 3,
    step=[8, 11])
total_epochs = 36

当我运行训练命令： python train.py OBBDetection/tools/work_dirs/faster_rcnn_orpn_r50_fpn_1x_dota10/faster_rcnn_orpn_r50_fpn_1x_dota10.py 会出现下面报错： RuntimeError: CUDA error: invalid device function CUDA kernel errors might be asynchronously reported at some other API call,so the stacktrace below might be incorrect. For debugging consider passing CUDA_LAUNCH_BLOCKING=1. Segmentation fault (core dumped) 我的环境如下： TorchVision: 0.10.0 OpenCV: 4.5.3 MMCV: 0.6.2 MMDetection: 2.2.0+6505a9d MMDetection Compiler: GCC 7.3 MMDetection CUDA Compiler: 10.0 如果您能提供帮助将万分感谢~

感谢您提供优质的代码! 您好, 我在我的项目中用到了您关于RoIAlignRotated部分的代码, 在单gpu模式下它十分有效, 运行也很快(此时我裁剪的是feature, 所以我将feature和roi都放到了gpu上). 但是当我使用多gpu加载模型时, 产生了以下报错: line 32, in forward features, rois, spatial_scale, out_h, out_w, sample_num, aligned) RuntimeError: CUDA error: an illegal memory access was encountered 我尝试将RoIAlignRotated其他变量都放在同一个gpu上, 但是结果依然是错误的. 请问您有什么方法吗? 期待您的回复!

The mAP we got only 66.95, not 69 as you said.

mAP: 0.6695016721761877 ap of each class: plane:0.8933495268168008, baseball-diamond:0.7374626613068532, bridge:0.4122850723332845, ground-track-field:0.6670794506088387, small-vehicle:0.760291145560589, large-vehicle:0.6047573582066816, ship:0.7630074552316077, tennis-court:0.9088855421686749, basketball-court:0.7977999161008033, storage-tank:0.8171024978735246, soccer-ball-field:0.5278917624380285, roundabout:0.635699247940088, harbor:0.514493570948177, swimming-pool:0.6264466877239606, helicopter:0.3759731873849022

I don't know what went wrong?

Here is our cfg:

2021-10-21 15:01:46,198 - mmdet - INFO - Environment info:

sys.platform: linux Python: 3.7.7 (default, Mar 23 2020, 22:36:06) [GCC 7.3.0] CUDA available: True CUDA_HOME: /usr/local/cuda NVCC: Cuda compilation tools, release 10.1, V10.1.243 GPU 0: GeForce RTX 2080 Ti GCC: gcc (Ubuntu 7.4.0-1ubuntu1~18.04.1) 7.4.0 PyTorch: 1.7.1 PyTorch compiling details: PyTorch built with:

• GCC 7.3
• C++ Version: 201402
• Intel(R) Math Kernel Library Version 2020.0.0 Product Build 20191122 for Intel(R) 64 architecture applications
• Intel(R) MKL-DNN v1.6.0 (Git Hash 5ef631a030a6f73131c77892041042805a06064f)
• 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_70,code=sm_70;-gencode;arch=compute_75,code=sm_75
• 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-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 -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,

TorchVision: 0.8.2 OpenCV: 4.2.0 MMCV: 0.6.2 MMDetection: 2.2.0+unknown MMDetection Compiler: GCC 7.4 MMDetection CUDA Compiler: 10.1

2021-10-21 15:01:46,199 - mmdet - INFO - Distributed training: True 2021-10-21 15:01:46,373 - mmdet - INFO - Config: dataset_type = 'DOTADataset' data_root = '/data/zy/datasets/split_ss_dota1_0/' 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='LoadOBBAnnotations', with_bbox=True, with_label=True, with_poly_as_mask=True), dict(type='LoadDOTASpecialInfo'), dict(type='Resize', img_scale=(1024, 1024), keep_ratio=True), dict(type='OBBRandomFlip', h_flip_ratio=0.5, v_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='RandomOBBRotate', rotate_after_flip=True, angles=(0, 0), vert_rate=0.5, vert_cls=['roundabout', 'storage-tank']), dict(type='Pad', size_divisor=32), dict(type='DOTASpecialIgnore', ignore_size=2), dict(type='FliterEmpty'), dict(type='Mask2OBB', obb_type='obb'), dict(type='OBBDefaultFormatBundle'), dict( type='OBBCollect', keys=['img', 'gt_bboxes', 'gt_obboxes', 'gt_labels']) ] test_pipeline = [ dict(type='LoadImageFromFile'), dict( type='MultiScaleFlipRotateAug', img_scale=[(1024, 1024)], h_flip=False, v_flip=False, rotate=False, transforms=[ dict(type='Resize', keep_ratio=True), dict(type='OBBRandomFlip'), dict( type='Normalize', mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True), dict(type='RandomOBBRotate', rotate_after_flip=True), dict(type='Pad', size_divisor=32), dict(type='ImageToTensor', keys=['img']), dict(type='OBBCollect', keys=['img']) ]) ] data = dict( samples_per_gpu=2, workers_per_gpu=4, train=dict( type='DOTADataset', task='Task1', ann_file='/data/zy/datasets/split_ss_dota1_0/trainval/annfiles/', img_prefix='/data/zy/datasets/split_ss_dota1_0/trainval/images/', pipeline=[ dict(type='LoadImageFromFile'), dict( type='LoadOBBAnnotations', with_bbox=True, with_label=True, with_poly_as_mask=True), dict(type='LoadDOTASpecialInfo'), dict(type='Resize', img_scale=(1024, 1024), keep_ratio=True), dict(type='OBBRandomFlip', h_flip_ratio=0.5, v_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='RandomOBBRotate', rotate_after_flip=True, angles=(0, 0), vert_rate=0.5, vert_cls=['roundabout', 'storage-tank']), dict(type='Pad', size_divisor=32), dict(type='DOTASpecialIgnore', ignore_size=2), dict(type='FliterEmpty'), dict(type='Mask2OBB', obb_type='obb'), dict(type='OBBDefaultFormatBundle'), dict( type='OBBCollect', keys=['img', 'gt_bboxes', 'gt_obboxes', 'gt_labels']) ]), test=dict( type='DOTADataset', task='Task1', ann_file='/data/zy/datasets/split_ss_dota1_0/test/annfiles/', img_prefix='/data/zy/datasets/split_ss_dota1_0/test/images/', pipeline=[ dict(type='LoadImageFromFile'), dict( type='MultiScaleFlipRotateAug', img_scale=[(1024, 1024)], h_flip=False, v_flip=False, rotate=False, transforms=[ dict(type='Resize', keep_ratio=True), dict(type='OBBRandomFlip'), dict( type='Normalize', mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True), dict(type='RandomOBBRotate', rotate_after_flip=True), dict(type='Pad', size_divisor=32), dict(type='ImageToTensor', keys=['img']), dict(type='OBBCollect', keys=['img']) ]) ])) evaluation = None optimizer = dict(type='SGD', lr=0.0025, momentum=0.9, weight_decay=0.0001) optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2)) lr_config = dict( policy='step', warmup='linear', warmup_iters=500, warmup_ratio=0.001, step=[8, 11]) total_epochs = 12 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)] model = dict( type='RetinaNetOBB', 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'), neck=dict( type='FPN', in_channels=[256, 512, 1024, 2048], out_channels=256, start_level=1, add_extra_convs='on_input', num_outs=5), bbox_head=dict( type='OBBRetinaHead', num_classes=15, in_channels=256, stacked_convs=4, feat_channels=256, anchor_generator=dict( type='Theta0AnchorGenerator', octave_base_scale=4, scales_per_octave=3, ratios=[0.5, 1.0, 2.0], strides=[8, 16, 32, 64, 128]), bbox_coder=dict( type='OBB2OBBDeltaXYWHTCoder', target_means=[0.0, 0.0, 0.0, 0.0, 0.0], target_stds=[1.0, 1.0, 1.0, 1.0, 1.0]), loss_cls=dict( type='FocalLoss', use_sigmoid=True, gamma=2.0, alpha=0.25, loss_weight=1.0), loss_bbox=dict(type='L1Loss', loss_weight=1.0))) train_cfg = dict( assigner=dict( type='MaxIoUAssigner', pos_iou_thr=0.5, neg_iou_thr=0.4, min_pos_iou=0, gpu_assign_thr=-1, ignore_iof_thr=-1, iou_calculator=dict(type='OBBOverlaps')), allowed_border=-1, pos_weight=-1, debug=False) test_cfg = dict( nms_pre=2000, min_bbox_size=0, score_thr=0.05, nms=dict(type='obb_nms', iou_thr=0.1), max_per_img=2000) work_dir = './work_dirs/retinanet_obb_r50_fpn_1x_dota10' gpu_ids = range(0, 1)

Hi,

Thanks for the great work, I wonder if you have done experiments on the DOTA-v1.5 which is a more challenging dataset.

Because our results with your Orient RCNN code on DOTA-v1.5 is only about 71% mAP.

感谢您辛勤付出的工作！ 在使用python tools/test.py ${CONFIG_FILE} ${CHECKPOINT_FILE} [--out ${RESULT_FILE}] [--eval ${EVAL_METRICS}] [--show]进行测试之后，在文件夹中所生成的图片是裁剪后的1024*1024的sub image而并非原始图片，另外所有的标注框均是绿色，想问下应该如何将图片重新拼接？并且将不同类别设置成不同颜色方便观察？

作者您好！

我正常训练DOTA1.0数据后，在运行：

python test/tools.py config/obb/oriented_rcnn/faster_rcnn_orpn_r101_1x_data10.py work_dirs/faster_rcnn_orpn_r101_1x_data10/latest.pth --show-dir

出现以下Bug：

在 File " / 00D / 0bbdetection / Bboxtoolkit / Bboxtoolkit / visualization / show . py " , line 70 , in < Listcomp > bboxes=[ boxes [ labels == i ] for i in range ( labels . max() ) + 1 ) ] 出现：

Indexerror : boolean index did not match indexed array along dimension 0 ; dimension is 9 but corresponding boolean dimension is 17

只修改了配置路径，其它未做修改。

请问使用DOTA格式的数据集（不是DOTA数据集）进行训练，请问还要进行测试吗？最后要如何计算mAP呢？ Please use DOTA format dataset (not DOTA dataset) for training. Do you still need to test? Finally, how to calculate mAP？

The following error occurs when using DOTA data set for training. The server uses RTX 2080 Ti; frame #4: + 0x6ea43a (0x7f34d219543a in /home/lxj/anaconda3/envs/obbdetection/lib/python3.7/site-packages/torch/lib/libtorch_python.so) frame #5: + 0x6ea4e1 (0x7f34d21954e1 in /home/lxj/anaconda3/envs/obbdetection/lib/python3.7/site-packages/torch/lib/libtorch_python.so) frame #6: python() [0x4d76aa] frame #7: python() [0x4ad077] frame #8: python() [0x4c21db] frame #9: python() [0x4c21db] frame #10: python() [0x4bcd88] frame #11: python() [0x4d0f00] frame #12: python() [0x4d0f16] frame #13: python() [0x4d0f16] frame #14: python() [0x4d0f16] frame #15: python() [0x4d0f16] frame #16: python() [0x4d0f16] frame #17: python() [0x4d0f16] frame #18: python() [0x4a0cf7] frame #22: python() [0x549129] frame #24: __libc_start_main + 0xf0 (0x7f34e9db0840 in /lib/x86_64-linux-gnu/libc.so.6) frame #25: python() [0x548e9e]

Aborted (core dumped)

bbox_roi_extractor=dict(
            type='OBBSingleRoIExtractor',
            roi_layer=dict(type='RoIAlignRotated', out_size=7, sample_num=2),
            out_channels=256,
            extend_factor=(1.4, 1.2),
            featmap_strides=[4, 8, 16, 32])

Thank you for your great work! I want to how why extend roi here? How to set extend_factor?

训练的指令·是python tools/train.py configs/obb/oriented_rcnn/faster_rcnn_orpn_r50_fpn_1x_dota10.py，小白，请问哪里出现了问题，其中mmdet/detectors/init.py文件中__all__列表中已经加入了OrientedRCNN

Hello, I want to train model with different hyperparameters so I changed the hyperparameter of cfg.data.train like img_scale in the loop but I get the below error:

raceback (most recent call last): File "/miniconda3/envs/myenv/lib/python3.7/site-packages/yapf/yapflib/yapf_api.py", line 183, in FormatCode tree = pytree_utils.ParseCodeToTree(unformatted_source) File "/miniconda3/envs/myenv/lib/python3.7/site-packages/yapf/yapflib/pytree_utils.py", line 131, in ParseCodeToTree raise e File "/miniconda3/envs/myenv/lib/python3.7/site-packages/yapf/yapflib/pytree_utils.py", line 129, in ParseCodeToTree ast.parse(code) File "/miniconda3/envs/myenv/lib/python3.7/ast.py", line 35, in parse return compile(source, filename, mode, PyCF_ONLY_AST) File "", line 152 config='dataset_type = 'DOTADataset' ^ SyntaxError: invalid syntax

During handling of the above exception, another exception occurred:

Traceback (most recent call last): File "tools/train.py", line 211, in main() File "tools/train.py", line 195, in main config=cfg.pretty_text, File "h/miniconda3/envs/myenv/lib/python3.7/site-packages/mmcv/utils/config.py", line 508, in pretty_text text, _ = FormatCode(text, style_config=yapf_style, verify=True) File "/miniconda3/envs/myenv/lib/python3.7/site-packages/yapf/yapflib/yapf_api.py", line 186, in FormatCode raise errors.YapfError(errors.FormatErrorMsg(e)) yapf.yapflib.errors.YapfError: :152:43: invalid syntax

I changed train.py like this: backbone = {'pretrained':['torchvision://resnet101', 'torchvision://resnet50'], 'backbone':{'depth':[101,50]}} data_train = {'img_scale' : [(512, 512),(1024,1024), (640, 640)]}

for b in range(len(backbone['pretrained'])): cfg.model['pretrained'] = backbone['pretrained'][b] cfg.model['backbone']['depth'] = backbone['backbone']['depth'][b] # print("model***************************************************************************************************") # print(type(cfg.model)) # print(cfg.model) # print("***************************************************************************************************") model = build_detector(cfg.model, train_cfg=cfg.train_cfg, test_cfg=cfg.test_cfg)
for d in range(len(data_train['img_scale'])): cfg.data.train.pipeline[3].img_scale = data_train['img_scale'][d] cfg.data.train.pipeline[3].img_scale = data_train['img_scale'][d] print(cfg.data.train['pipeline'][3]['img_scale'], " ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ " ,data_train['img_scale'][d]) datasets = [build_dataset(cfg.data.train)] if len(cfg.workflow) == 2: val_dataset = copy.deepcopy(cfg.data.val) val_dataset.pipeline = cfg.data.train.pipeline datasets.append(build_dataset(val_dataset)) if cfg.checkpoint_config is not None: # save mmdet version, config file content and class names in # checkpoints as meta data cfg.checkpoint_config.meta = dict( mmdet_version=version, config=cfg.pretty_text, CLASSES=datasets[0].CLASSES) # add an attribute for visualization convenience model.CLASSES = datasets[0].CLASSES train_detector( model, datasets, cfg, distributed=distributed, validate=(not args.no_validate), timestamp=timestamp, meta=meta)