From a2451b09f2eb609f6d9b19cc6b13f30be52badf2 Mon Sep 17 00:00:00 2001
From: pangjm <pjmzju@gmail.com>
Date: Thu, 11 Oct 2018 16:02:34 +0800
Subject: [PATCH] update fast rcnn configs
---
configs/fast_mask_rcnn_r50_fpn_1x.py | 132 +++++++++++++++++++++++++++
configs/fast_rcnn_r50_fpn_1x.py | 118 ++++++++++++++++++++++++
configs/faster_rcnn_r50_fpn_1x.py | 3 +-
configs/mask_rcnn_r50_fpn_1x.py | 3 +-
4 files changed, 252 insertions(+), 4 deletions(-)
create mode 100644 configs/fast_mask_rcnn_r50_fpn_1x.py
create mode 100644 configs/fast_rcnn_r50_fpn_1x.py
diff --git a/configs/fast_mask_rcnn_r50_fpn_1x.py b/configs/fast_mask_rcnn_r50_fpn_1x.py
new file mode 100644
index 0000000..1878a27
--- /dev/null
+++ b/configs/fast_mask_rcnn_r50_fpn_1x.py
@@ -0,0 +1,132 @@
+# model settings
+model = dict(
+ type='FastRCNN',
+ pretrained='modelzoo://resnet50',
+ backbone=dict(
+ type='ResNet',
+ depth=50,
+ 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),
+ 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='SharedFCRoIHead',
+ 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=False),
+ 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))
+# model training and testing settings
+train_cfg = dict(
+ rcnn=dict(
+ mask_size=28,
+ pos_iou_thr=0.5,
+ neg_iou_thr=0.5,
+ crowd_thr=1.1,
+ roi_batch_size=512,
+ add_gt_as_proposals=True,
+ pos_fraction=0.25,
+ pos_balance_sampling=False,
+ neg_pos_ub=512,
+ neg_balance_thr=0,
+ min_pos_iou=0.5,
+ pos_weight=-1,
+ debug=False))
+test_cfg = dict(
+ rcnn=dict(
+ score_thr=0.05, max_per_img=100, nms_thr=0.5, mask_thr_binary=0.5))
+# 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,
+ proposal_file=data_root + 'proposals/train2017_r50_fpn_rpn_1x.pkl',
+ 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,
+ proposal_file=data_root + 'proposals/val2017_r50_fpn_rpn_1x.pkl',
+ 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,
+ proposal_file=data_root + 'proposals/val2017_r50_fpn_rpn_1x.pkl',
+ size_divisor=32,
+ flip_ratio=0,
+ with_mask=False,
+ 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=20,
+ 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/fast_mask_rcnn_r50_fpn_1x'
+load_from = None
+resume_from = None
+workflow = [('train', 1)]
diff --git a/configs/fast_rcnn_r50_fpn_1x.py b/configs/fast_rcnn_r50_fpn_1x.py
new file mode 100644
index 0000000..bdff052
--- /dev/null
+++ b/configs/fast_rcnn_r50_fpn_1x.py
@@ -0,0 +1,118 @@
+# model settings
+model = dict(
+ type='FastRCNN',
+ pretrained='modelzoo://resnet50',
+ backbone=dict(
+ type='ResNet',
+ depth=50,
+ 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),
+ 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='SharedFCRoIHead',
+ 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=False))
+# model training and testing settings
+train_cfg = dict(
+ rcnn=dict(
+ pos_iou_thr=0.5,
+ neg_iou_thr=0.5,
+ crowd_thr=1.1,
+ roi_batch_size=512,
+ add_gt_as_proposals=True,
+ pos_fraction=0.25,
+ pos_balance_sampling=False,
+ neg_pos_ub=512,
+ neg_balance_thr=0,
+ min_pos_iou=0.5,
+ pos_weight=-1,
+ debug=False))
+test_cfg = dict(rcnn=dict(score_thr=0.05, max_per_img=100, nms_thr=0.5))
+# 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,
+ proposal_file=data_root + 'proposals/train2017_r50_fpn_rpn_1x.pkl',
+ flip_ratio=0.5,
+ with_mask=False,
+ 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,
+ proposal_file=data_root + 'proposals/val2017_r50_fpn_rpn_1x.pkl',
+ 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/instances_val2017.json',
+ img_prefix=data_root + 'val2017/',
+ img_scale=(1333, 800),
+ img_norm_cfg=img_norm_cfg,
+ proposal_file=data_root + 'proposals/val2017_r50_fpn_rpn_1x.pkl',
+ size_divisor=32,
+ flip_ratio=0,
+ with_mask=False,
+ 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=20,
+ 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/fast_rcnn_r50_fpn_1x'
+load_from = None
+resume_from = None
+workflow = [('train', 1)]
diff --git a/configs/faster_rcnn_r50_fpn_1x.py b/configs/faster_rcnn_r50_fpn_1x.py
index b15405e..1c06c4c 100644
--- a/configs/faster_rcnn_r50_fpn_1x.py
+++ b/configs/faster_rcnn_r50_fpn_1x.py
@@ -65,7 +65,7 @@ train_cfg = dict(
pos_balance_sampling=False,
neg_pos_ub=512,
neg_balance_thr=0,
- min_pos_iou=1.1,
+ min_pos_iou=0.5,
pos_weight=-1,
debug=False))
test_cfg = dict(
@@ -139,7 +139,6 @@ log_config = dict(
# yapf:enable
# runtime settings
total_epochs = 12
-device_ids = range(8)
dist_params = dict(backend='nccl')
log_level = 'INFO'
work_dir = './work_dirs/faster_rcnn_r50_fpn_1x'
diff --git a/configs/mask_rcnn_r50_fpn_1x.py b/configs/mask_rcnn_r50_fpn_1x.py
index e2d4721..8868cf6 100644
--- a/configs/mask_rcnn_r50_fpn_1x.py
+++ b/configs/mask_rcnn_r50_fpn_1x.py
@@ -77,7 +77,7 @@ train_cfg = dict(
pos_balance_sampling=False,
neg_pos_ub=512,
neg_balance_thr=0,
- min_pos_iou=1.1,
+ min_pos_iou=0.5,
pos_weight=-1,
debug=False))
test_cfg = dict(
@@ -152,7 +152,6 @@ log_config = dict(
# yapf:enable
# runtime settings
total_epochs = 12
-device_ids = range(8)
dist_params = dict(backend='nccl')
log_level = 'INFO'
work_dir = './work_dirs/mask_rcnn_r50_fpn_1x'
--
GitLab