code release

d-li14 · Jul 4, 2020 · fefe40d · fefe40d
1 parent 2c447d9
commit fefe40d
Show file tree

Hide file tree

Showing 218 changed files with 33,806 additions and 0 deletions.
diff --git a/INSTALL.md b/INSTALL.md
@@ -0,0 +1,92 @@
+## Installation
+
+### Requirements
+
+- Linux
+- Python 3.5+ ([Say goodbye to Python2](https://python3statement.org/))
+- PyTorch 1.0+ or PyTorch-nightly
+- CUDA 9.0+
+- NCCL 2+
+- GCC 4.9+
+- [mmcv](https://github.com/open-mmlab/mmcv)
+
+We have tested the following versions of OS and softwares:
+
+- OS: Ubuntu 16.04/18.04 and CentOS 7.2
+- CUDA: 9.0/9.2/10.0
+- NCCL: 2.1.15/2.2.13/2.3.7/2.4.2
+- GCC: 4.9/5.3/5.4/7.3
+
+### Install mmdetection
+
+a. Create a conda virtual environment and activate it. Then install Cython.
+
+```shell
+conda create -n open-mmlab python=3.7 -y
+conda activate open-mmlab
+
+conda install cython
+```
+
+b. Install PyTorch stable or nightly and torchvision following the [official instructions](https://pytorch.org/).
+
+c. Clone the mmdetection repository.
+
+```shell
+git clone https://github.com/open-mmlab/mmdetection.git
+cd mmdetection
+```
+
+d. Install mmdetection (other dependencies will be installed automatically).
+
+```shell
+python setup.py develop
+# or "pip install -v -e ."
+```
+
+Note:
+
+1. It is recommended that you run the step e each time you pull some updates from github. If there are some updates of the C/CUDA codes, you also need to run step d.
+The git commit id will be written to the version number with step e, e.g. 0.6.0+2e7045c. The version will also be saved in trained models.
+
+2. Following the above instructions, mmdetection is installed on `dev` mode, any modifications to the code will take effect without installing it again.
+
+### Prepare COCO dataset.
+
+It is recommended to symlink the dataset root to `$MMDETECTION/data`.
+
+```
+mmdetection
+├── mmdet
+├── tools
+├── configs
+├── data
+│   ├── coco
+│   │   ├── annotations
+│   │   ├── train2017
+│   │   ├── val2017
+│   │   ├── test2017
+│   ├── VOCdevkit
+│   │   ├── VOC2007
+│   │   ├── VOC2012
+
+```
+
+### Scripts
+[Here](https://gist.github.com/hellock/bf23cd7348c727d69d48682cb6909047) is
+a script for setting up mmdetection with conda.
+
+### Notice
+You can run `python(3) setup.py develop` or `pip install -v -e .` to install mmdetection if you want to make modifications to it frequently.
+
+If there are more than one mmdetection on your machine, and you want to use them alternatively.
+Please insert the following code to the main file
+```python
+import os.path as osp
+import sys
+sys.path.insert(0, osp.join(osp.dirname(osp.abspath(__file__)), '../'))
+```
+or run the following command in the terminal of corresponding folder.
+```shell
+export PYTHONPATH=`pwd`:$PYTHONPATH
+```
diff --git a/configs/psconv/cascade_mask_rcnn_r101_fpn_1x.py b/configs/psconv/cascade_mask_rcnn_r101_fpn_1x.py
@@ -0,0 +1,261 @@
+# model settings
+model = dict(
+    type='CascadeRCNN',
+    num_stages=3,
+    pretrained='/path/to/ps-resnet101.pth',
+    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],
+        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,
+        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=81,
+            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=81,
+            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=81,
+            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))
+    ],
+    mask_roi_extractor=dict(
+        type='SingleRoIExtractor',
+        roi_layer=dict(type='RoIAlign', out_size=14, sample_num=2),
+        out_channels=256,
+        featmap_strides=[4, 8, 16, 32]),
+    mask_head=dict(
+        type='FCNMaskHead',
+        num_convs=4,
+        in_channels=256,
+        conv_out_channels=256,
+        num_classes=81,
+        loss_mask=dict(
+            type='CrossEntropyLoss', use_mask=True, 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),
+            mask_size=28,
+            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),
+            mask_size=28,
+            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),
+            mask_size=28,
+            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=0.05,
+        nms=dict(type='nms', iou_thr=0.5),
+        max_per_img=100,
+        mask_thr_binary=0.5),
+    keep_all_stages=False)
+# dataset settings
+dataset_type = 'CocoDataset'
+data_root = 'data/coco/'
+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=2,
+    workers_per_gpu=2,
+    train=dict(
+        type=dataset_type,
+        ann_file=data_root + 'annotations/instances_train2017.json',
+        img_prefix=data_root + 'train2017/',
+        img_scale=(1333, 800),
+        img_norm_cfg=img_norm_cfg,
+        size_divisor=32,
+        flip_ratio=0.5,
+        with_mask=True,
+        with_crowd=True,
+        with_label=True),
+    val=dict(
+        type=dataset_type,
+        ann_file=data_root + 'annotations/instances_val2017.json',
+        img_prefix=data_root + 'val2017/',
+        img_scale=(1333, 800),
+        img_norm_cfg=img_norm_cfg,
+        size_divisor=32,
+        flip_ratio=0,
+        with_mask=True,
+        with_crowd=True,
+        with_label=True),
+    test=dict(
+        type=dataset_type,
+        ann_file=data_root + 'annotations/instances_val2017.json',
+        img_prefix=data_root + 'val2017/',
+        img_scale=(1333, 800),
+        img_norm_cfg=img_norm_cfg,
+        size_divisor=32,
+        flip_ratio=0,
+        with_mask=True,
+        with_label=False,
+        test_mode=True))
+# optimizer
+optimizer = dict(type='SGD', lr=0.02, 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/cascade_mask_rcnn_psconv_r101_fpn_1x'
+load_from = None
+resume_from = None
+workflow = [('train', 1)]