haoran1062
commented
5 years ago this is my config base on cascade_mask_rcnn_r50_fpn_1x.py
# model settings
model = dict(
type='CascadeRCNN',
num_stages=3,
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),
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=1023,
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=1023, #
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=1023,
target_means=[0., 0., 0., 0.],
target_stds=[0.033, 0.033, 0.067, 0.067],
reg_class_agnostic=True)
],
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=1023))
# model training and testing settings
train_cfg = dict(
rpn=dict(
assigner=dict(
pos_iou_thr=0.7,
neg_iou_thr=0.3,
min_pos_iou=0.3,
ignore_iof_thr=-1),
sampler=dict(
num=256,
pos_fraction=0.5,
neg_pos_ub=-1,
add_gt_as_proposals=False,
pos_balance_sampling=False,
neg_balance_thr=0),
allowed_border=0,
pos_weight=-1,
smoothl1_beta=1 / 9.0,
debug=False),
rcnn=[
dict(
assigner=dict(
pos_iou_thr=0.5,
neg_iou_thr=0.5,
min_pos_iou=0.5,
ignore_iof_thr=-1),
sampler=dict(
num=512,
pos_fraction=0.25,
neg_pos_ub=-1,
add_gt_as_proposals=True,
pos_balance_sampling=False,
neg_balance_thr=0),
mask_size=28,
pos_weight=-1,
debug=False),
dict(
assigner=dict(
pos_iou_thr=0.6,
neg_iou_thr=0.6,
min_pos_iou=0.6,
ignore_iof_thr=-1),
sampler=dict(
num=512,
pos_fraction=0.25,
neg_pos_ub=-1,
add_gt_as_proposals=True,
pos_balance_sampling=False,
neg_balance_thr=0),
mask_size=28,
pos_weight=-1,
debug=False),
dict(
assigner=dict(
pos_iou_thr=0.7,
neg_iou_thr=0.7,
min_pos_iou=0.7,
ignore_iof_thr=-1),
sampler=dict(
num=512,
pos_fraction=0.25,
neg_pos_ub=-1,
add_gt_as_proposals=True,
pos_balance_sampling=False,
neg_balance_thr=0),
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=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,
mask_thr_binary=0.5),
keep_all_stages=False)
# dataset settings
dataset_type = 'MyDataset'# 'CustomDataset'
data_root = '/home/ubuntu/project/ConvertToCOCOData/'
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 + 'data/OutCOCOData/test.json',
img_prefix='/home/ubuntu/project/ConvertToCOCOData/',
img_scale=(1280, 720),
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 + 'data/OutCOCOData/test.json',
img_prefix='/home/ubuntu/project/ConvertToCOCOData/',
img_scale=(1280, 720),
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 + 'data/OutCOCOData/test.json',
img_prefix='/home/ubuntu/project/ConvertToCOCOData/',
img_scale=(1280, 720),
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=0.0025, 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=1,
hooks=[
dict(type='TextLoggerHook'),
# dict(type='TensorboardLoggerHook')
])
# yapf:enable
# runtime settings
total_epochs = 5
dist_params = dict(backend='nccl')
log_level = 'INFO'
work_dir = './work_dirs/cascade_mask_rcnn_r50_fpn_1x'
load_from = None
resume_from = None
workflow = [('train', 1)]
hellock
but I found yesterday My 100 epoch weight have better output:
I just overwrite CustomDatasets to eval my data, and for test, I try to use a very little datasets(only ten picture) to train base on
cascade_mask_rcnn_r50_fpn_1x.py(change 81class to 1023 class, ),and the log isand I try to test the model by two ways:
python3 tools/test.py configs/my_cascade_mask_rcnn_r50.py work_dir/latest.pth --show, Output Nothing, no bbox, no maskfrom mmdet.models import build_detector from mmdet.apis import inference_detector, show_result import numpy as np, pycocotools.mask as maskUtils, mmcv from mmdet.core import tensor2imgs, get_classes from glob import glob
config_path = 'configs/my_cascade_mask_rcnn_r50.py' model_path = 'work_dir/latest.pth'
config_path = 'configs/cascade_mask_rcnn_r50_fpn_1x.py' model_path = '/home/ubuntu/Downloads/cascade_mask_rcnn_r50_fpn_20e_20181123-6e0c9713.pth'
cfg = mmcv.Config.fromfile(config_path) cfg.model.pretrained = None
img_norm_cfg = dict( mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
def show_mask_result(img, result, dataset='mydata', score_thr=0.3): assert isinstance(result, tuple) bbox_result, segm_result = result
construct the model and load checkpoint
model = build_detector(cfg.model, test_cfg=cfg.testcfg) = load_checkpoint(model, model_path)
img_list = glob('/data/PycharmProjects/mask_rcnn/other_code/datasets/25class_v1_badcase/*.jpg')
img_list = glob('/home/ubuntu/project/ConvertToCOCOData/data/miniData/100class_mini/imgs/*.jpg')
for i, result in enumerate(inference_detector(model, img_list[:1], cfg, device='cuda:0')): print(i, img_list[i]) print(result[0]) show_mask_result(mmcv.imread(img_list[i]), result)
show_result(mmcv.imread(img_list[i]), result[0])
encoding:utf-8
import os.path as osp import mmcv, cv2, numpy as np
from .custom import CustomDataset
class MyDataset(CustomDataset): """Custom dataset for detection.