Cascade R-CNN with OHEM

[ZengyuanYu]

@hellock Thanks your work! I use mmdetection for my finally thesis. Now I meet some question:

• 1. I want to compare OHEM and Random use Cascade R-CNN, But got error. I don't debug it, So will you give me some advice? my config

     model settings

     model = dict( type='CascadeRCNN', num_stages=3, pretrained='modelzoo://resnet101', backbone=dict( type='ResNet', depth=101, num_stages=4, out_indices=(0, 1, 2, 3), frozen_stages=1, style='pytorch'), 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_scales=[8], anchor_ratios=[0.5, 1.0, 2.0], anchor_strides=[4, 8, 16, 32, 64], target_means=[.0, .0, .0, .0], target_stds=[1.0, 1.0, 1.0, 1.0], use_sigmoid_cls=True), bbox_roi_extractor=dict( type='SingleRoIExtractor', roi_layer=dict(type='RoIAlign', out_size=7, sample_num=2), out_channels=256, featmap_strides=[4, 8, 16, 32]), bbox_head=[ dict( type='SharedFCBBoxHead', num_fcs=2, in_channels=256, fc_out_channels=1024, roi_feat_size=7, num_classes=2, target_means=[0., 0., 0., 0.], target_stds=[0.1, 0.1, 0.2, 0.2], reg_class_agnostic=True), dict( type='SharedFCBBoxHead', num_fcs=2, in_channels=256, fc_out_channels=1024, roi_feat_size=7, num_classes=2, target_means=[0., 0., 0., 0.], target_stds=[0.05, 0.05, 0.1, 0.1], reg_class_agnostic=True), dict( type='SharedFCBBoxHead', num_fcs=2, in_channels=256, fc_out_channels=1024, roi_feat_size=7, num_classes=2, target_means=[0., 0., 0., 0.], target_stds=[0.033, 0.033, 0.067, 0.067], reg_class_agnostic=True) ])

     model training and testing settings

     train_cfg = dict( rpn=dict( assigner=dict( type='MaxIoUAssigner', pos_iou_thr=0.7, neg_iou_thr=0.3, min_pos_iou=0.3, 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=0, pos_weight=-1, smoothl1_beta=1 / 9.0, debug=False), rcnn=[ dict( assigner=dict( type='MaxIoUAssigner', pos_iou_thr=0.5, neg_iou_thr=0.5, min_pos_iou=0.5, ignore_iof_thr=-1), sampler=dict( type='OHEMSampler', num=512, pos_fraction=0.25, neg_pos_ub=-1, add_gt_as_proposals=True), pos_weight=-1, debug=False), dict( assigner=dict( type='MaxIoUAssigner', pos_iou_thr=0.6, neg_iou_thr=0.6, min_pos_iou=0.6, ignore_iof_thr=-1), sampler=dict( type='OHEMSampler', num=512, pos_fraction=0.25, neg_pos_ub=-1, add_gt_as_proposals=True), pos_weight=-1, debug=False), dict( assigner=dict( type='MaxIoUAssigner', pos_iou_thr=0.7, neg_iou_thr=0.7, min_pos_iou=0.7, ignore_iof_thr=-1), sampler=dict( type='OHEMSampler', num=512, pos_fraction=0.25, neg_pos_ub=-1, add_gt_as_proposals=True), pos_weight=-1, debug=False) ], stage_loss_weights=[1, 0.5, 0.25]) test_cfg = dict( rpn=dict( nms_across_levels=False, nms_pre=2000, nms_post=2000, max_num=2000, nms_thr=0.7, min_bbox_size=0), rcnn=dict( score_thr=0.05, nms=dict(type='nms', iou_thr=0.5), max_per_img=100), keep_all_stages=False)

     dataset settings

     dataset_type = 'CocoDataset' data_root = '/home/yu/mmdetection/data/coco-wheat/' img_norm_cfg = dict( mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True) data = dict( imgs_per_gpu=1, workers_per_gpu=1, train=dict( type=dataset_type, ann_file=data_root + 'annotations/trainval.json', img_prefix=data_root + 'trainval', img_scale=(1333, 800), img_norm_cfg=img_norm_cfg, size_divisor=32, flip_ratio=0.5, with_mask=False, with_crowd=True, with_label=True), val=dict( type=dataset_type, ann_file=data_root + 'annotations/val.json', img_prefix=data_root + 'val/', img_scale=(1333, 800), img_norm_cfg=img_norm_cfg, size_divisor=32, flip_ratio=0, with_mask=False, with_crowd=True, with_label=True), test=dict( type=dataset_type, ann_file=data_root + 'annotations/test.json', img_prefix=data_root + 'test/', img_scale=(1333, 800), img_norm_cfg=img_norm_cfg, size_divisor=32, flip_ratio=0, with_mask=False, with_label=False, test_mode=True))

     optimizer

     optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0001) optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))

     learning policy

     lr_config = dict( policy='step', warmup='linear', warmup_iters=500, warmup_ratio=1.0 / 3, step=[8, 11]) checkpoint_config = dict(interval=10)

     yapf:disable

     log_config = dict( interval=50, hooks=[ dict(type='TextLoggerHook'),

     dict(type='TensorboardLoggerHook')

     ])

     yapf:enable

     runtime settings

     total_epochs = 200 dist_params = dict(backend='nccl') log_level = 'INFO' work_dir = './work_dirs/cascade_rcnn_r101_fpn_1x' load_from = None resume_from = None workflow = [('train', 1)]

error msg loading annotations into memory... Done (t=0.08s) creating index... index created! 2019-02-24 20:31:17,671 - INFO - Start running, host: yu@xc-pc, work_dir: /home/yu/mmdetection/data/result/cascade_rcnn_r101_OHEM_wheat 2019-02-24 20:31:17,671 - INFO - workflow: [('train', 1)], max: 200 epochs Traceback (most recent call last): File "tools/train.py", line 90, in main() File "tools/train.py", line 86, in main logger=logger) File "/home/yu/mmdetection/mmdet/apis/train.py", line 59, in train_detector _non_dist_train(model, dataset, cfg, validate=validate) File "/home/yu/mmdetection/mmdet/apis/train.py", line 121, in _non_dist_train runner.run(data_loaders, cfg.workflow, cfg.total_epochs) File "/home/yu/.virtualenvs/mmdetetion/lib/python3.6/site-packages/mmcv/runner/runner.py", line 349, in run epoch_runner(data_loaders[i], kwargs) File "/home/yu/.virtualenvs/mmdetetion/lib/python3.6/site-packages/mmcv/runner/runner.py", line 255, in train self.model, data_batch, train_mode=True, kwargs) File "/home/yu/mmdetection/mmdet/apis/train.py", line 37, in batch_processor losses = model(data) File "/home/yu/.virtualenvs/mmdetetion/lib/python3.6/site-packages/torch/nn/modules/module.py", line 477, in call result = self.forward(*input, *kwargs) File "/home/yu/.virtualenvs/mmdetetion/lib/python3.6/site-packages/torch/nn/parallel/data_parallel.py", line 121, in forward return self.module(inputs[0], kwargs[0]) File "/home/yu/.virtualenvs/mmdetetion/lib/python3.6/site-packages/torch/nn/modules/module.py", line 477, in call result = self.forward(input, kwargs) File "/home/yu/mmdetection/mmdet/models/detectors/base.py", line 80, in forward return self.forward_train(img, img_meta, kwargs) File "/home/yu/mmdetection/mmdet/models/detectors/cascade_rcnn.py", line 141, in forward_train cfg=rcnn_train_cfg) File "/home/yu/mmdetection/mmdet/core/utils/misc.py", line 24, in multi_apply return tuple(map(list, zip(map_results))) File "/home/yu/mmdetection/mmdet/core/bbox/assign_sampling.py", line 30, in assign_and_sample bbox_sampler = build_sampler(cfg.sampler) File "/home/yu/mmdetection/mmdet/core/bbox/assign_sampling.py", line 22, in build_sampler cfg, samplers, default_args=kwargs) File "/home/yu/.virtualenvs/mmdetetion/lib/python3.6/site-packages/mmcv/runner/utils.py", line 72, in obj_from_dict return obj_type(**args) TypeError: init() missing 1 required positional argument: 'context'

[ZengyuanYu]

I use Faster R-CNN with OHEM is OK.

[hellock]

We have not tried OHEM in Cascade R-CNN and it is currently not supported. You can refer to here and here if you want to add OHEM in Cascade R-CNN.

[ZengyuanYu]

We have not tried OHEM in Cascade R-CNN and it is currently not supported. You can refer to here and here if you want to add OHEM in Cascade R-CNN.

OK, I will do it for refer code.Thank you!

[1224wxwx]

I use Faster R-CNN with OHEM is OK.

Could you please tell me whether OHEM helped you? After I used OHEM, it became very difficult for loss to decrease(both on train dataset and test dataset) and the result was worse than before.

[zvadaszi]

Did OHEM helped with Cascade R-CNN?