目录
- 重要的参考链接
- 第一步:更改权重文件
- 第二步:将数据集整理为coco数据集的格式
- 第三步:更改detr.py
- 第四步:在终端设置训练参数进行训练
- 第五步:检测效果,但是没有没有打印出来那些map指标
重要的参考链接
- 视频学习-关于DETR的讲解合集:DETR源码讲解:训练自己的数据集(这个小姐姐讲的很清楚,还有另外一个视频关于Deformable Detr的,Deformable Detr 论文思想讲解(一听就会))
- 这小姐姐自己写了一个预测代码,但是还没有公布出来的,我在这个博客中看到有分享
predict.py
,可以好好看一下:windows10复现DEtection TRansformers(DETR)并实现自己的数据集(这个博客是真的详细,可能视频中的小姐姐就是参照的这个博客,里面的预测代码大概率也是来自于这里)
- 这小姐姐自己写了一个预测代码,但是还没有公布出来的,我在这个博客中看到有分享
- 视频学习-跟着李沐学AI的论文精度:DETR 论文精读【论文精读】(有3篇相关的B站笔记,可以去看一下)
- 这个注意力机制要好好学一下,跟那个生物机制很像:详解可变形注意力模块(Deformable Attention Module)
重点:
- 标签格式是
COCO类型的json文件
,暂时可以先参考这个VOC格式数据集转为COCO格式数据集脚本,而且必须要命名为./instances_train2017.json
和./instances_val2017.json
- DETR
对小目标不友好
,检测大目标倒是可以 - DETR在精度上没有比过当时的SOTA,能这么被喜爱是因为
它的论文思想很精妙,真正实现了end-to-end
训练自己的代码,参考:
- 视频学习-关于DETR的讲解合集:DETR源码讲解:训练自己的数据集
- 【DETR】训练自己的数据集-实践笔记
- DETR训练自己的数据集
- windows10复现DEtection TRansformers(DETR)并实现自己的数据集
暂存:
- 目标检测算法:Cascade RCNN | 视频讲解
缺点:
- DETR需要很多的epoch才能够收敛
- 小目标性能不好
- 增大尺度或者使用多尺度,会增加计算量
- 注意力模块比较稀疏,收敛比较慢
第一步:更改权重文件
-
先下载
detr-r50-e632da11.pth
权重,点击即可下载👉https://dl.fbaipublicfiles.com/detr/detr-r50-e632da11.pth -
再运行以下代码(其中,
num_class
:假如json
文件中类别id
的最大数值为90
,则num_class
应当被设置为90+1
。最大值90
可以通过此方式查找:在json
文件中Ctrl+F
检索定位到最后一个supercategory
,查看id
值即可。下图展示的是视频1中定位的COCO数据集中的最大类别编号为90)
这是在视频下的回复:
import torch
# 下载地址: https://dl.fbaipublicfiles.com/detr/detr-r50-e632da11.pth
pretrained_weights = torch.load('./detr-r50-e632da11.pth')
num_classes = 5
pretrained_weights['model']['class_embed.weight'].resize_(num_classes + 1, 256)
pretrained_weights['model']['class_embed.bias'].resize_(num_classes + 1)
torch.save(pretrained_weights, 'detr-r50_%d.pth' % num_classes)
第二步:将数据集整理为coco数据集的格式
代码参考自:windows10复现DEtection TRansformers(DETR)并实现自己的数据集
以下暂存我自己改了一点的代码,就是只管了将xml格式转为json文件,没有管将图片移动的事:
# coding:utf-8
# conference link: https://blog.csdn.net/w1520039381/article/details/118905718
# pip install lxml
import os
import glob
import json
import shutil
import numpy as np
import xml.etree.ElementTree as ET
path2 = "C:/Users/Desktop/VOC2007"
START_BOUNDING_BOX_ID = 1
def get(root, name):
return root.findall(name)
def get_and_check(root, name, length):
vars = root.findall(name)
if len(vars) == 0:
raise NotImplementedError('Can not find %s in %s.' % (name, root.tag))
if length > 0 and len(vars) != length:
raise NotImplementedError('The size of %s is supposed to be %d, but is %d.' % (name, length, len(vars)))
if length == 1:
vars = vars[0]
return vars
def convert(xml_list, json_file):
json_dict = {"images": [], "type": "instances", "annotations": [], "categories": []}
categories = pre_define_categories.copy()
bnd_id = START_BOUNDING_BOX_ID
all_categories = {}
for index, line in enumerate(xml_list):
# print("Processing %s"%(line))
xml_f = line
tree = ET.parse(xml_f)
root = tree.getroot()
filename = os.path.basename(xml_f)[:-4] + ".jpg"
image_id = 20190000001 + index
size = get_and_check(root, 'size', 1)
width = int(get_and_check(size, 'width', 1).text)
height = int(get_and_check(size, 'height', 1).text)
image = {'file_name': filename, 'height': height, 'width': width, 'id': image_id}
json_dict['images'].append(image)
## Cruuently we do not support segmentation
# segmented = get_and_check(root, 'segmented', 1).text
# assert segmented == '0'
for obj in get(root, 'object'):
category = get_and_check(obj, 'name', 1).text
if category in all_categories: # 记录类别个数
all_categories[category] += 1
else:
all_categories[category] = 1
if category not in categories:
if only_care_pre_define_categories: # 只关注特定的类别,也就是遇到定义好的类别之外的类别一律不管
continue
new_id = len(categories) + 1
print(
"[warning] category '{}' not in 'pre_define_categories'({}), create new id: {} automatically".format(
category, pre_define_categories, new_id))
categories[category] = new_id
category_id = categories[category]
bndbox = get_and_check(obj, 'bndbox', 1)
xmin = int(float(get_and_check(bndbox, 'xmin', 1).text))
ymin = int(float(get_and_check(bndbox, 'ymin', 1).text))
xmax = int(float(get_and_check(bndbox, 'xmax', 1).text))
ymax = int(float(get_and_check(bndbox, 'ymax', 1).text))
assert (xmax > xmin), "xmax <= xmin, {}".format(line)
assert (ymax > ymin), "ymax <= ymin, {}".format(line)
o_width = abs(xmax - xmin)
o_height = abs(ymax - ymin)
ann = {'area': o_width * o_height, 'iscrowd': 0, 'image_id':
image_id, 'bbox': [xmin, ymin, o_width, o_height],
'category_id': category_id, 'id': bnd_id, 'ignore': 0,
'segmentation': []}
json_dict['annotations'].append(ann)
bnd_id = bnd_id + 1
for cate, cid in categories.items():
cat = {'supercategory': 'none', 'id': cid, 'name': cate}
json_dict['categories'].append(cat)
json_fp = open(json_file, 'w')
json_str = json.dumps(json_dict)
json_fp.write(json_str)
json_fp.close()
print("------------create {} done--------------".format(json_file))
print("find {} categories: {} -->>> your pre_define_categories {}: {}".format(len(all_categories),
all_categories.keys(),
len(pre_define_categories),
pre_define_categories.keys()))
print("category: id --> {}".format(categories))
print(categories.keys())
print(categories.values())
if __name__ == '__main__':
classes = ['D00', 'D10', 'D20', 'D40']
pre_define_categories = {}
for i, cls in enumerate(classes):
pre_define_categories[cls] = i + 1
# pre_define_categories = {'a1': 1, 'a3': 2, 'a6': 3, 'a9': 4, "a10": 5} ##
only_care_pre_define_categories = True
# only_care_pre_define_categories = False ##
# train_ratio = 0.9
save_json_train = 'instances_train2017.json'
save_json_val = 'instances_val2017.json'
xml_dir = r"F:\A_Publicdatasets\RDD2022_released_through_CRDDC2022\RDD2022\A_unitedataset\annotations"
xml_list_train = glob.glob(xml_dir + "/train/*.xml")
xml_list_val = glob.glob(xml_dir + "/val/*.xml")
# xml_list = np.sort(xml_list)
# np.random.seed(100)
# np.random.shuffle(xml_list)
# train_num = int(len(xml_list) * train_ratio)
# xml_list_train = xml_list[:train_num]
# xml_list_val = xml_list[train_num:]
convert(xml_list_train, os.path.join(xml_dir, save_json_train))
convert(xml_list_val, os.path.join(xml_dir, save_json_val))
# if os.path.exists(path2 + "/annotations"):
# shutil.rmtree(path2 + "/annotations")
# os.makedirs(path2 + "/annotations")
# if os.path.exists(path2 + "/images/train2014"):
# shutil.rmtree(path2 + "/images/train2014")
# os.makedirs(path2 + "/images/train2014")
# if os.path.exists(path2 + "/images/val2014"):
# shutil.rmtree(path2 + "/images/val2014")
# os.makedirs(path2 + "/images/val2014")
#
# f1 = open("train.txt", "w")
# for xml in xml_list_train:
# img = xml[:-4] + ".jpg"
# f1.write(os.path.basename(xml)[:-4] + "\n")
# shutil.copyfile(img, path2 + "/images/train2014/" + os.path.basename(img))
#
# f2 = open("test.txt", "w")
# for xml in xml_list_val:
# img = xml[:-4] + ".jpg"
# f2.write(os.path.basename(xml)[:-4] + "\n")
# shutil.copyfile(img, path2 + "/images/val2014/" + os.path.basename(img))
# f1.close()
# f2.close()
# print("-------------------------------")
# print("train number:", len(xml_list_train))
# print("val number:", len(xml_list_val))
第三步:更改detr.py
第四步:在终端设置训练参数进行训练
注意:如果是在windows下面跑的话,num_workers
应该设置成0
python main.py --dataset_file "coco" --coco_path data/coco --epochs 100 --lr=1e-4 --batch_size=2 --num_workers=4 --output_dir="outputs" --resume="detr-r50_3.pth"
第五步:检测效果,但是没有没有打印出来那些map指标
⭐来自博客:windows10复现DEtection TRansformers(DETR)并实现自己的数据集
其中要改的地方有:
-
102行左右的
model = detr_resnet50(False, 5)
中的5
改为本博客第一步:更改权重文件的 num_class
,否则会报错通道数不匹配
-
103行左右
state_dict = torch.load
后面改为训练好后的checkpoint.pth地址
-
108行左右
im = Image.open
后面改为待检测的图片地址
(注意,现在只能检测单张,且没有实现保存图片,需要自己改下代码) -
20行左右的
CLASSES
后面的数组值按顺序写成自己的检测类别名
-
93行左右的
keep = probas.max(-1).values > 0.7
中的0.7
可以调大调小,应该是confidence
的作用,也就是值越高的话,显示出来的框就会越少
import math
from PIL import Image
import requests
import matplotlib.pyplot as plt
# import ipywidgets as widgets
# from IPython.display import display, clear_output
import torch
from torch import nn
from torchvision.models import resnet50
import torchvision.transforms as T
from hubconf import *
from util.misc import nested_tensor_from_tensor_list
torch.set_grad_enabled(False)
# COCO classes
CLASSES = [
'D00', 'D10', 'D20', 'D40'
]
# colors for visualization
COLORS = [[0.000, 0.447, 0.741], [0.850, 0.325, 0.098]]
# standard PyTorch mean-std input image normalization
transform = T.Compose([
T.Resize(800),
T.ToTensor(),
T.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
])
# for output bounding box post-processing
def box_cxcywh_to_xyxy(x):
x_c, y_c, w, h = x.unbind(1)
b = [(x_c - 0.5 * w), (y_c - 0.5 * h),
(x_c + 0.5 * w), (y_c + 0.5 * h)]
return torch.stack(b, dim=1)
def rescale_bboxes(out_bbox, size):
img_w, img_h = size
b = box_cxcywh_to_xyxy(out_bbox)
b = b * torch.tensor([img_w, img_h, img_w, img_h], dtype=torch.float32)
return b
def plot_results(pil_img, prob, boxes):
plt.figure(figsize=(16, 10))
plt.imshow(pil_img)
ax = plt.gca()
colors = COLORS * 100
for p, (xmin, ymin, xmax, ymax), c in zip(prob, boxes.tolist(), colors):
ax.add_patch(plt.Rectangle((xmin, ymin), xmax - xmin, ymax - ymin,
fill=False, color=c, linewidth=3))
cl = p.argmax()
text = f'{CLASSES[cl]}: {p[cl]:0.2f}'
ax.text(xmin, ymin, text, fontsize=15,
bbox=dict(facecolor='yellow', alpha=0.5))
plt.axis('off')
plt.show()
def detect(im, model, transform):
# mean-std normalize the input image (batch-size: 1)
img = transform(im).unsqueeze(0)
# propagate through the model
outputs = model(img)
# keep only predictions with 0.7+ confidence
probas = outputs['pred_logits'].softmax(-1)[0, :, :-1]
keep = probas.max(-1).values > 0.00001
# convert boxes from [0; 1] to image scales
bboxes_scaled = rescale_bboxes(outputs['pred_boxes'][0, keep], im.size)
return probas[keep], bboxes_scaled
def predict(im, model, transform):
# mean-std normalize the input image (batch-size: 1)
anImg = transform(im)
data = nested_tensor_from_tensor_list([anImg])
# propagate through the model
outputs = model(data)
# keep only predictions with 0.7+ confidence
probas = outputs['pred_logits'].softmax(-1)[0, :, :-1]
keep = probas.max(-1).values > 0.7 # 0.7 好像是调整置信度的
# print(probas[keep])
# convert boxes from [0; 1] to image scales
bboxes_scaled = rescale_bboxes(outputs['pred_boxes'][0, keep], im.size)
return probas[keep], bboxes_scaled
if __name__ == "__main__":
model = detr_resnet50(False, 5) # 这里与前面的num_classes数值相同,就是最大的category id值 + 1
state_dict = torch.load(r"G:\pycharmprojects\detr-main\output\checkpoint.pth", map_location='cpu')
model.load_state_dict(state_dict["model"])
model.eval()
# im = Image.open('data/coco/train2017/001554.jpg')
im = Image.open(r'F:\A_Publicdatasets\RDD2022_released_through_CRDDC2022\RDD2022\A_unitedataset\images\val\China_Drone_000038.jpg')
scores, boxes = predict(im, model, transform)
plot_results(im, scores, boxes)
文章出处登录后可见!