first commit

shuangw98 · Apr 11, 2020 · 2633bd2 · 2633bd2
commit 2633bd2
Show file tree

Hide file tree

Showing 275 changed files with 35,251 additions and 0 deletions.
diff --git a/README.md b/README.md
@@ -0,0 +1,32 @@
+# 水下目标检测竞赛
+## 代码环境及依赖
+* OS：Ubuntu 16.10
+* GPU: 1 * 32G-V100
+* python：3.7.6
+* pytorch：1.1.0
+* cudatoolkit：10.0.130
+
+## 训练
+```
+python tools/train.py configs/cascade_rcnn_dconv_c3-c5_r101_fpn_1x.py --gpus 1
+python tools/train.py configs/cascade_rcnn_dconv_c3-c5_r101_fpn_1x.py --gpus 1
+python tools/train.py configs/cascade_rcnn_dconv_c3-c5_r101_fpn_ms800_2000.py --gpus 1
+```
+
+## 预测
+```
+python tools/test.py configs/cascade_rcnn_dcn_x101_64x4d_fpn_1x.py work_dirs/cas_dcn_x101_64x4d_fpn_htc_1x/epoch_4939A.pth --format_only
+
+python tools/test.py configs/cascade_rcnn_dconv_c3-c5_r101_fpn_1x.py  work_dirs/cascade_rcnn_dconv_c3-c5_r101_fpn_1x/epoch_4935A.pth --eval bbox
+
+python tools/test.py configs/cascade_rcnn_dconv_c3-c5_r50_fpn_ms800_2000.py  work_dirs/cascade_rcnn_dconv_c3-c5_r50_fpn_ms800_2000/epoch_12.pth --eval bbox
+```
+
+**融合:**
+```
+python tools/json_merge.py
+```
+**生成提交文件:**
+```
+python tools/json2csv.py    #结果保存在./data文件夹中
+```
diff --git a/configs/cascade_rcnn_dcn_x101_64x4d_fpn_1x.py b/configs/cascade_rcnn_dcn_x101_64x4d_fpn_1x.py
@@ -0,0 +1,255 @@
+# model settings
+model = dict(
+    type='CascadeRCNN',
+    num_stages=3,
+    pretrained=None,
+    backbone=dict(
+        type='ResNeXt',
+        depth=101,
+        groups=64,
+        base_width=4,
+        num_stages=4,
+        out_indices=(0, 1, 2, 3),
+        frozen_stages=1,
+        style='pytorch',
+        dcn=dict(
+            type='DCN',
+            deformable_groups=1,
+            fallback_on_stride=False),
+        stage_with_dcn=(False, True, True, True)),
+    neck=dict(
+        type='FPN_CARAFE',
+        in_channels=[256, 512, 1024, 2048],
+        out_channels=256,
+        num_outs=5,
+        start_level=0,
+        end_level=-1,
+        norm_cfg=None,
+        activation=None,
+        order=('conv', 'norm', 'act'),
+        upsample_cfg=dict(
+            type='carafe',
+            up_kernel=5,
+            up_group=1,
+            encoder_kernel=3,
+            encoder_dilation=1,
+            compressed_channels=64)),
+    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],
+        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)),
+    bbox_roi_extractor=dict(
+        type='SingleRoIExtractor',
+        roi_layer=dict(type='RoIAlign', out_size=7, sample_num=2),
+        out_channels=256,
+        add_context=True,
+        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=6,
+            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='SharedFCBBoxHead',
+            num_fcs=2,
+            in_channels=256,
+            fc_out_channels=1024,
+            roi_feat_size=7,
+            num_classes=6,
+            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='SharedFCBBoxHead',
+            num_fcs=2,
+            in_channels=256,
+            fc_out_channels=1024,
+            roi_feat_size=7,
+            num_classes=6,
+            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)),
+    ])
+# 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,
+        debug=False),
+    rpn_proposal=dict(
+        nms_across_levels=False,
+        nms_pre=2000,
+        nms_post=2000,
+        max_num=2000,
+        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,
+                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),
+        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='RandomSampler',
+                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='RandomSampler',
+                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=1000,
+        nms_post=1000,
+        max_num=1000,
+        nms_thr=0.7,
+        min_bbox_size=0),
+    rcnn=dict(
+        score_thr=0.001, nms=dict(type='soft_nms', iou_thr=0.5, min_score=0.001), max_per_img=200))
+# dataset settings
+dataset_type = 'CocoDataset'
+data_root = '/home/aistudio/work/datasets/water/'
+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=[(3840, 800), (3840, 1800)],
+         multiscale_mode='range', keep_ratio=True),
+    dict(type='RandomFlip', flip_ratio=0.5),
+    dict(type='BBoxJitter', min=0.9, max=1.1),
+    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=[(3840, 800), (3840, 1000), (3840, 1200), (3840, 1400), (3840, 1600), (3840, 1800)],  
+        flip=True,
+        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(
+    imgs_per_gpu=1,
+    workers_per_gpu=0,
+    train=dict(
+        type=dataset_type,
+        ann_file=data_root + 'train.json', 
+        img_prefix='/home/aistudio/work/datasets/water/train/image',    
+        pipeline=train_pipeline),
+    test=dict(
+        type=dataset_type,
+        ann_file='./data/test5.json',
+        img_prefix=data_root + 'test-A-image/',
+        pipeline=test_pipeline))
+    # test=dict(
+    #     type=dataset_type,
+    #     ann_file=data_root + 'val.json',   
+    #     img_prefix='/home/aistudio/work/datasets/water/train/image/',    
+    #     pipeline=test_pipeline))
+# optimizer
+optimizer = dict(type='SGD', lr=1.25e-3, 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=1)
+# yapf:disable
+log_config = dict(
+    interval=50,
+    hooks=[
+        dict(type='TextLoggerHook'),
+        # dict(type='TensorboardLoggerHook')
+    ])
+# yapf:enable
+# runtime settings
+total_epochs = 12
+dist_params = dict(backend='nccl')
+log_level = 'INFO'
+work_dir = './work_dirs/cas_dcn_x101_64x4d_fpn_htc_1x'
+load_from = './weights/htc_dconv_c3-c5_mstrain_400_1400_x101_64x4d_fpn_converted.pth'  
+resume_from = None
+workflow = [('train', 1)]