安装tensorboard
pip install tensorboard
安装pydot
pip install pydot
安装scipy
pip install scipy -i https://pypi.tuna.tsinghua.edu.cn/simple
进入Sparse R-CNN目录，目录根据自己的实际情况更改。
cd D:\SparseR-CNN-main
编译Detectron2和Sparse R-CNN
python setup.py build develop
看到如下信息，则表明安装完成，如果缺少库的情况，则需要安装库，再编译，直到编译成功！
=================================================================
新建input_img和output_img文件夹，imgs文件夹存放待测试的图片。
图片如下：
下载模型“r50_100pro_3x_model.pth”(注：如果不能下载，关注我的公众号获取连接。)，将其放到“projects/SparseRCNN”目录下面。
执行命令：
python demo/demo.py --config-file projects/SparseRCNN/configs/sparsercnn.res50.100pro.3x.yaml --input imgs/*.jpg --output imgout --opts MODEL.WEIGHTS projects/SparseRCNN/r50_100pro_3x_model.pth
运行结果：
能够运行demo说明环境已经没有问题了。
==================================================================
本次采用的数据集是Labelme标注的数据集，地址：链接：https://pan.baidu.com/s/1nxo9-NpNWKK4PwDZqwKxGQ 提取码：kp4e，需要将其转为COCO格式的数据集。转换代码如下：
新建labelme2coco.py
import argparse
import json
import matplotlib.pyplot as plt
import skimage.io as io
import cv2
from labelme import utils
import numpy as np
import glob
import PIL.Image
REQUIRE_MASK = False
labels = {‘aircraft’: 1, ‘oiltank’: 2}
class labelme2coco(object):
def init(self, labelme_json=[], save_json_path=‘./new.json’):
‘’’
:param labelme_json: the list of all labelme json file paths
:param save_json_path: the path to save new json
‘’’
self.labelme_json = labelme_json
self.save_json_path = save_json_path
self.images = []
self.categories = []
self.annotations = []
self.data_coco = {}
self.label = []
self.annID = 1
self.height = 0
self.width = 0
self.require_mask = REQUIRE_MASK
self.save_json()
def data_transfer(self):
for num, json_file in enumerate(self.labelme_json):
if not json_file == self.save_json_path:
with open(json_file, ‘r’) as fp:
data = json.load(fp)
self.images.append(self.image(data, num))
for shapes in data[‘shapes’]:
print("label is ")
print(shapes[‘label’])
label = shapes[‘label’]
if label[1] not in self.label:
if label not in self.label:
print("find new category: ")
self.categories.append(self.categorie(label))
print(self.categories)
self.label.append(label[1])
self.label.append(label)
points = shapes[‘points’]
self.annotations.append(self.annotation(points, label, num))
self.annID += 1
def image(self, data, num):
image = {}
img = utils.img_b64_to_arr(data[‘imageData’])
height, width = img.shape[:2]
img = None
image[‘height’] = height
image[‘width’] = width
image[‘id’] = num + 1
image[‘file_name’] = data[‘imagePath’].split(‘/’)[-1]
self.height = height
self.width = width
return image
def categorie(self, label):
categorie = {}
categorie[‘supercategory’] = label
categorie[‘supercategory’] = label
categorie[‘id’] = labels[label] # 0 默认为背景
categorie[‘name’] = label
return categorie
def annotation(self, points, label, num):
annotation = {}
print(points)
x1 = points[0][0]
y1 = points[0][1]
x2 = points[1][0]
y2 = points[1][1]
contour = np.array([[x1, y1], [x2, y1], [x2, y2], [x1, y2]]) # points = [[x1, y1], [x2, y2]] for rectangle
contour = contour.astype(int)
area = cv2.contourArea(contour)
print("contour is ", contour, " area = ", area)
annotation[‘segmentation’] = [list(np.asarray([[x1, y1], [x2, y1], [x2, y2], [x1, y2]]).flatten())]
[list(np.asarray(contour).flatten())]
annotation[‘iscrowd’] = 0
annotation[‘area’] = area
annotation[‘image_id’] = num + 1
if self.require_mask:
annotation[‘bbox’] = list(map(float, self.getbbox(points)))
else:
x1 = points[0][0]
y1 = points[0][1]
width = points[1][0] - x1
height = points[1][1] - y1
annotation[‘bbox’] = list(np.asarray([x1, y1, width, height]).flatten())
annotation[‘category_id’] = self.getcatid(label)
annotation[‘id’] = self.annID
return annotation
def getcatid(self, label):
for categorie in self.categories:
if label[1]==categorie[‘name’]:
if label == categorie[‘name’]:
return categorie[‘id’]
return -1
def getbbox(self, points):
polygons = points
mask = self.polygons_to_mask([self.height, self.width], polygons)
return self.mask2box(mask)
def mask2box(self, mask):
np.where(mask==1)
index = np.argwhere(mask == 1)
rows = index[:, 0]
clos = index[:, 1]
left_top_r = np.min(rows) # y
left_top_c = np.min(clos) # x
right_bottom_r = np.max(rows)
right_bottom_c = np.max(clos)
return [left_top_c, left_top_r, right_bottom_c - left_top_c, right_bottom_r - left_top_r]
def polygons_to_mask(self, img_shape, polygons):
mask = np.zeros(img_shape, dtype=np.uint8)
mask = PIL.Image.fromarray(mask)
xy = list(map(tuple, polygons))
PIL.ImageDraw.Draw(mask).polygon(xy=xy, outline=1, fill=1)
mask = np.array(mask, dtype=bool)
return mask
def data2coco(self):
data_coco = {}
data_coco[‘images’] = self.images
data_coco[‘categories’] = self.categories
data_coco[‘annotations’] = self.annotations
return data_coco
def save_json(self):
print(“in save_json”)
self.data_transfer()
self.data_coco = self.data2coco()
print(self.save_json_path)
json.dump(self.data_coco, open(self.save_json_path, ‘w’), indent=4)
labelme_json = glob.glob(‘LabelmeData/*.json’)
from sklearn.model_selection import train_test_split
trainval_files, test_files = train_test_split(labelme_json, test_size=0.2, random_state=55)
import os
if not os.path.exists(“projects/SparseRCNN/datasets/coco/annotations”):
os.makedirs(“projects/SparseRCNN/datasets/coco/annotations/”)
if not os.path.exists(“projects/SparseRCNN/datasets/coco/train2017”):
os.makedirs(“projects/SparseRCNN/datasets/coco/train2017”)
if not os.path.exists(“projects/SparseRCNN/datasets/coco/val2017”):
os.makedirs(“projects/SparseRCNN/datasets/coco/val2017”)
labelme2coco(trainval_files, ‘projects/SparseRCNN/datasets/coco/annotations/instances_train2017.json’)
labelme2coco(test_files, ‘projects/SparseRCNN/datasets/coco/annotations/instances_val2017.json’)
import shutil
for file in trainval_files:
shutil.copy(os.path.splitext(file)[0] + “.jpg”, “projects/SparseRCNN/datasets/coco/train2017/”)
for file in test_files:
shutil.copy(os.path.splitext(file)[0] + “.jpg”, “projects/SparseRCNN/datasets/coco/val2017/”)
===================================================================
在projects/SparseRCNN目录，新建change_model_size.py文件
import torch
import numpy as np
import pickle
num_class = 2
pretrained_weights = torch.load(‘r50_100pro_3x_model.pth’)
pretrained_weights[“head.head_series.0.class_logits.weight”].resize_(num_class,256)
pretrained_weights[“head.head_series.0.class_logits.bias”].resize_(num_class)
pretrained_weights[“head.head_series.1.class_logits.weight”].resize_(num_class,256)
pretrained_weights[“head.head_series.1.class_logits.bias”].resize_(num_class)
pretrained_weights[“head.head_series.2.class_logits.weight”].resize_(num_class,256)
pretrained_weights[“head.head_series.2.class_logits.bias”].resize_(num_class)
pretrained_weights[“head.head_series.3.class_logits.weight”].resize_(num_class,256)
pretrained_weights[“head.head_series.3.class_logits.bias”].resize_(num_class)
pretrained_weights[“head.head_series.4.class_logits.weight”].resize_(num_class,256)
pretrained_weights[“head.head_series.4.class_logits.bias”].resize_(num_class)
pretrained_weights[“head.head_series.5.class_logits.weight”].resize_(num_class,256)
pretrained_weights[“head.head_series.5.class_logits.bias”].resize_(num_class)
torch.save(pretrained_weights, “model_%d.pth”%num_class)
这个文件的目的是修改模型输出的size，numclass按照本次打算训练的数据集的类别设置。
路径：“detectron2/engine/defaults.py”
–config-file：模型的配置文件，SparseRCNN的模型配置文件放在“projects/SparseRCNN/configs”下面。名字和预训练模型对应。
parser.add_argument(“–config-file”, default=“./configs/sparsercnn.res50.100pro.3x.yaml”, metavar=“FILE”, help=“path to config file”)
resume 是否再次，训练，如果设置为true，则接着上次训练的结果训练。所以第一次训练不用设置。
parser.add_argument(
“–resume”,
action=“store_true”,
help="Whether to attempt to resume from the checkpoint directory. "
“See documentation of DefaultTrainer.resume_or_load() for what it means.”,
)
–num-gpus，gpu的个数，如果只有一个设置为1，如果有多个，可以自己设置想用的个数。
parser.add_argument(“–num-gpus”, type=int, default=1, help=“number of gpus per machine”)
opts指的是yaml文件的参数。
上面的参数可以设置，也可以不设置，设置之后可以直接运行不用再考虑设置参数，如果不设置每次训练的时候配置一次参数。
修改类别，文件路径“projects/SparseRCNN/config.py”，
cfg.MODEL.SparseRCNN.NUM_CLASSES = 2
修改yaml文件参数
sparsercnn.res50.100pro.3x.yaml中修改预训练模型的路径。
WEIGHTS: “model_2.pth”
BASE_LR：设置学习率。
STEPS：设置训练多少步之后调整学习率。
MAX_ITER：最大迭代次数。
CHECKPOINT_PERIOD：设置迭代多少次保存一次模型
IMS_PER_BATCH：batchsize的大小，根据显存大小设置。
NUM_CLASSES：数据集中物体类别的种类。
NUM_PROPOSALS：提议框的个数。
BASE_LR: 0.00025 #在Base-SparseRCNN.yaml中
IMS_PER_BATCH: 2#在Base-SparseRCNN.yaml中
NUM_CLASSES：2
STEPS: (21000, 25000)
MAX_ITER: 54000
CHECKPOINT_PERIOD: 5000
主要修改该setup函数，增加数据集注册。
NUM_CLASSES=2
最后
不知道你们用的什么环境，我一般都是用的Python3.6环境和pycharm解释器，没有软件，或者没有资料，没人解答问题，都可以免费领取（包括今天的代码），过几天我还会做个视频教程出来，有需要也可以领取~
给大家准备的学习资料包括但不限于：
Python 环境、pycharm编辑器/永久激活/翻译插件
python 零基础视频教程
Python 界面开发实战教程
Python 爬虫实战教程
Python 数据分析实战教程
python 游戏开发实战教程
Python 电子书100本
Python 学习路线规划
网上学习资料一大堆，但如果学到的知识不成体系，遇到问题时只是浅尝辄止，不再深入研究，那么很难做到真正的技术提升。
一个人可以走的很快，但一群人才能走的更远！不论你是正从事IT行业的老鸟或是对IT行业感兴趣的新人，都欢迎加入我们的的圈子（技术交流、学习资源、职场吐槽、大厂内推、面试辅导），让我们一起学习成长！
扫一扫
664
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
