mmdet实例分割
环境
mmdet 3.0
数据集标注
1、使用labelme软件标注
2、得到json文件，把json文件放到一个文件夹内,img放到一个文件夹
3、使用split.py划分数据集
import os
import random
import shutil
img_folder = 'data/img/'
json_folder = 'data/json/'
train_folder = 'data/train/'
val_folder = 'data/val/'
img_files = os.listdir(img_folder)
json_files = os.listdir(json_folder)
random.shuffle(img_files)
num_samples = len(img_files)
num_train = int(num_samples * 0.8)
num_val = num_samples - num_train
train_img_files = img_files[:num_train]
val_img_files = img_files[num_train:]
for img_file in train_img_files:
src_img_path = os.path.join(img_folder, img_file)
dst_img_path = os.path.join(train_folder, img_file)
os.makedirs(os.path.dirname(dst_img_path), exist_ok=True)
shutil.copy(src_img_path, dst_img_path)
json_file = img_file.replace('.png', '.json')
src_json_path = os.path.join(json_folder, json_file)
dst_json_path = os.path.join(train_folder, json_file)
shutil.copy(src_json_path, dst_json_path)
for img_file in val_img_files:
src_img_path = os.path.join(img_folder, img_file)
dst_img_path = os.path.join(val_folder, img_file)
os.makedirs(os.path.dirname(dst_img_path), exist_ok=True)
shutil.copy(src_img_path, dst_img_path)
json_file = img_file.replace('.png', '.json')
src_json_path = os.path.join(json_folder, json_file)
dst_json_path = os.path.join(val_folder, json_file)
shutil.copy(src_json_path, dst_json_path)
3、分别进入train、val中使用python labelme2coco.py json coco --labels labels.txt 转换得到coco格式的数据集
label.txt中内容如下
__ignore__
_background_
top
side
下面这个代码生成的json文件中，路径有一部分是用的\\，linux需要/ （之前是win转的格式，linux训练，可以试试linux转 linux训练）
#!/usr/bin/env python
# `labelme2coco.py`
import argparse
import collections
import datetime
import glob
import json
import os
import os.path as osp
import sys
import uuid
from PIL import Image
import imgviz
import numpy as np
import labelme
try:
import pycocotools.mask
except ImportError:
print("Please install pycocotools:\n\n pip install pycocotools\n")
sys.exit(1)
def main():
parser = argparse.ArgumentParser(
formatter_class=argparse.ArgumentDefaultsHelpFormatter
)
parser.add_argument("input_dir", help="input annotated directory")
parser.add_argument("output_dir", help="output dataset directory")
parser.add_argument("--labels", help="labels file", required=True)
parser.add_argument(
"--noviz", help="no visualization", action="store_true"
)
args = parser.parse_args()
if osp.exists(args.output_dir):
print("Output directory already exists:", args.output_dir)
sys.exit(1)
os.makedirs(args.output_dir)
os.makedirs(osp.join(args.output_dir, "JPEGImages"))
if not args.noviz:
os.makedirs(osp.join(args.output_dir, "Visualization"))
print("Creating dataset:", args.output_dir)
now = datetime.datetime.now()
data = dict(
info=dict(
description=None,
url=None,
version=None,
year=now.year,
contributor=None,
date_created=now.strftime("%Y-%m-%d %H:%M:%S.%f"),
),
licenses=[
dict(
url=None,
id=0,
name=None,
)
],
images=[
# license, url, file_name, height, width, date_captured, id
],
type="instances",
annotations=[
# segmentation, area, iscrowd, image_id, bbox, category_id, id
],
categories=[
# supercategory, id, name
],
)
class_name_to_id = {}
for i, line in enumerate(open(args.labels).readlines()):
class_id = i - 1 # starts with -1
class_name = line.strip()
if class_id <span style="font-weight: bold;" class="mark"> -1:
assert class_name </span> "__ignore__"
continue
class_name_to_id[class_name] = class_id
data["categories"].append(
dict(
supercategory=None,
id=class_id,
name=class_name,
)
)
out_ann_file = osp.join(args.output_dir, "annotations.json")
label_files = glob.glob(osp.join(args.input_dir, "*.json"))
for image_id, filename in enumerate(label_files):
print("Generating dataset from:", filename)
label_file = labelme.LabelFile(filename=filename)
base = osp.splitext(osp.basename(filename))[0]
out_img_file = osp.join(args.output_dir, "JPEGImages", base + ".jpg")
img = labelme.utils.img_data_to_arr(label_file.imageData)
#import cv2
#cv2.imwrite(out_img_file, img)
img = Image.fromarray(img)
img = img.convert('RGB')
img = np.array(img)
imgviz.io.imsave(out_img_file, img)
data["images"].append(
dict(
license=0,
url=None,
file_name=osp.relpath(out_img_file, osp.dirname(out_ann_file)),
height=img.shape[0],
width=img.shape[1],
date_captured=None,
id=image_id,
)
)
masks = {} # for area
segmentations = collections.defaultdict(list) # for segmentation
for shape in label_file.shapes:
points = shape["points"]
label = shape["label"]
group_id = shape.get("group_id")
shape_type = shape.get("shape_type", "polygon")
mask = labelme.utils.shape_to_mask(
img.shape[:2], points, shape_type
)
if group_id is None:
group_id = uuid.uuid1()
instance = (label, group_id)
if instance in masks:
masks[instance] = masks[instance] | mask
else:
masks[instance] = mask
if shape_type == "rectangle":
(x1, y1), (x2, y2) = points
x1, x2 = sorted([x1, x2])
y1, y2 = sorted([y1, y2])
points = [x1, y1, x2, y1, x2, y2, x1, y2]
if shape_type == "circle":
(x1, y1), (x2, y2) = points
r = np.linalg.norm([x2 - x1, y2 - y1])
# r(1-cos(a/2))<x, a=2*pi/N => N>pi/arccos(1-x/r)
# x: tolerance of the gap between the arc and the line segment
n_points_circle = max(int(np.pi / np.arccos(1 - 1 / r)), 12)
i = np.arange(n_points_circle)
x = x1 + r * np.sin(2 * np.pi / n_points_circle * i)
y = y1 + r * np.cos(2 * np.pi / n_points_circle * i)
points = np.stack((x, y), axis=1).flatten().tolist()
else:
points = np.asarray(points).flatten().tolist()
segmentations[instance].append(points)
segmentations = dict(segmentations)
for instance, mask in masks.items():
cls_name, group_id = instance
if cls_name not in class_name_to_id:
continue
cls_id = class_name_to_id[cls_name]
mask = np.asfortranarray(mask.astype(np.uint8))
mask = pycocotools.mask.encode(mask)
area = float(pycocotools.mask.area(mask))
bbox = pycocotools.mask.toBbox(mask).flatten().tolist()
data["annotations"].append(
dict(
id=len(data["annotations"]),
image_id=image_id,
category_id=cls_id,
segmentation=segmentations[instance],
area=area,
bbox=bbox,
iscrowd=0,
)
)
if not args.noviz:
viz = img
if masks:
labels, captions, masks = zip(
*[
(class_name_to_id[cnm], cnm, msk)
for (cnm, gid), msk in masks.items()
if cnm in class_name_to_id
]
)
viz = imgviz.instances2rgb(
image=img,
labels=labels,
masks=masks,
captions=captions,
font_size=15,
line_width=2,
)
out_viz_file = osp.join(
args.output_dir, "Visualization", base + ".jpg"
)
imgviz.io.imsave(out_viz_file, viz)
with open(out_ann_file, "w") as f:
json.dump(data, f)
if __name__ == "__main__":
main()
5、按照如下格式存放，红框内是必须的
instances_train2017.json
训练
和mmdet检测训练基本一致，根据配置文件找即可
python tools/train.py configs/balloon/mask-rcnn_r50-caffe_fpn_ms-poly-1x_balloon.py
python tools / train . py configs / faster_rcnn / faster_rcnn_r101_fpn_1x_coco . py - -work - dir work_dirs
测试
python image_demo.py 128.jpg work_dirs/mask-rcnn_r50_fpn_1x_coco.py --weights work_dirs/epoch_12.pth --show
在output中有json文件生成，可以通过下面代码读取json文件，生成二值化掩膜图像
readjson.py
#!--*-- coding: utf- --*--
import numpy as np
import pycocotools.mask as mask_utils
import json
import cv2
json_path = "outputs/preds/512.json"
with open(json_path, "r", encoding="utf-8") as f:
content = json.load(f)
print(content)
for m in content['masks']:
img = np.array(mask_utils.decode(m), dtype=np.float32)
cv2.imshow("img", img)
cv2.waitKey(0)