checkpoint = 'https://download.openmmlab.com/mmdetection/v3.0/rtmdet/cspnext_rsb_pretrain/cspnext-l_8xb256-rsb-a1-600e_in1k-6a760974.pth' # noqa angle_version = 'le90' model = dict( type='mmdet.RTMDet', data_preprocessor=dict( type='mmdet.DetDataPreprocessor', mean=[103.53, 116.28...
01/30 13:08:57 - mmengine - INFO - Config: angle_version = 'le90' backend_args = None data_root = '../DOTASplit/' dataset_type = 'DOTADataset' default_hooks = dict( checkpoint=dict(interval=1, type='CheckpointHook'), logger=dict(interval=50, type='LoggerHook'), param_scheduler=...
{angle version}: like oc, le135, or le90. An example of RotatedRetinaNet To help the users have a basic idea of a complete config and the modules in a modern detection system, we make brief comments on the config of RotatedRetinaNet using ResNet50 and FPN as the following. For more...
第一步:将[xc, yc, w, h, angle]标注形式的旋转框转换为polygon的4个角点坐标的形式 get_rotated_vertices<T>(box1, pts1); get_rotated_vertices<T>(box2, pts2); 第二步:获取构成四边形的顶点intersections结构体数组,以及交点个数num; template <typename T> HOST_DEVICE_INLINE int get_intersect...
(type='RegularizeRotatedBox',# 统一旋转框表示形式angle_version=angle_version),# 根据角度的定义方式进行dict(type='mmdet.PackDetInputs') ] train_dataloader = dict( batch_size=train_batch_size_per_gpu, num_workers=train_num_workers, persistent_workers=persistent_workers, pin_memory=True, ...
需要指定mmcv_version,前面报错有提示: Please install mmcv>=1.4.5, <=1.6.0,故选择1.6.0进行安装 pip install mmcv-full==1.6.0 -f https://download.openmmlab.com/mmcv/dist/cu101/torch1.7.0/index.html 安装完成后,输入指令再次进行测试:
angle_version = 'le90' model = dict( type='RotatedRetinaNet', backbone=dict( type='ResNet', depth=50, num_stages=4, out_indices=(0, 1, 2, 3), frozen_stages=1, zero_init_residual=False, norm_cfg=dict(type='BN', requires_grad=True), ...
MMRotate is an open-source toolbox for rotated object detection based on PyTorch. It is a part of theOpenMMLab project. The master branch works withPyTorch 1.6+. video.MP4 Major Features Support multiple angle representations MMRotate provides three mainstream angle representations to meet different...
MMRotate provides three mainstream angle representations to meet different paper settings. Modular Design We decompose the rotated object detection framework into different components, which makes it much easy and flexible to build a new model by combining different modules. Strong baseline and State of...
model: redet_re50_refpn_1x_dota_le90.py dataset_type = 'DOTADataset' angle_version = 'le90' dataset: no problem when use "r3det" with angle_version = 'oc' and dataset_type = 'DOTADataset' ERROR Traceback RuntimeError: DataLoader worker (...