#AI夏令营 #Datawhale #夏令营
写在最前
本文用于记录Datawhale夏令营 CV part 学习过程。夏令营以学习CV进阶内容为主,并参与以城市治理为主题的相关比赛。后续将不断进行更新。
Task 2 baseline代码及进阶
安装四个Python库:opencv-python、pandas、matplotlib 和 ultralytics
!/opt/miniconda/bin/pip install opencv-python pandas matplotlib ultralytics
导入包
import os, sys
import cv2, glob, json
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import os, sys:
os:这个模块提供了许多与操作系统交互的函数。例如,你可以使用os模块来创建、删除、更改目录和文件,以及执行其他与文件系统相关的操作。
sys:这个模块提供对解释器使用或维护的变量的访问,以及与解释器强烈相关的函数。例如,sys.argv可以用来访问命令行参数。
import cv2, glob, json:
cv2:这是OpenCV(Open Source Computer Vision Library)的Python绑定。OpenCV是一个开源的计算机视觉和机器学习库,用于处理图像和视频数据。
glob:这个模块提供了一个函数来查找与特定模式匹配的所有路径名。这对于查找符合特定规则的文件很有用。
json:这个模块提供了解析和生成JSON数据(JavaScript Object Notation)的功能。JSON是一种轻量级的数据交换格式,易于阅读和编写,同时也易于机器解析和生成。
import numpy as np:
numpy:这是Python中一个强大的科学计算库,主要用于对数组和矩阵进行操作。它提供了高性能的多维数组对象和一系列工具,用于处理这些数组。在导入时通常使用np作为别名,以便在代码中更方便地引用。
import pandas as pd:
pandas:这是一个提供高性能、易于使用的数据结构和数据分析工具的Python库。它特别适合于处理表格数据,如CSV文件或SQL数据库。在导入时通常使用pd作为别名。
import matplotlib.pyplot as plt:
matplotlib.pyplot:这是matplotlib库的一个模块,它提供了类似于MATLAB的绘图功能。matplotlib是一个非常流行的Python绘图库,用于创建高质量的图形和图表。在导入时通常使用plt作为别名。
导入训练集及测试集
!apt install zip unzip -y
!apt install unar -y
!wget "https://comp-public-prod.obs.cn-east-3.myhuaweicloud.com/dataset/2024/%E8%AE%AD%E7%BB%83%E9%9B%86%28%E6%9C%89%E6%A0%87%E6%B3%A8%E7%AC%AC%E4%B8%80%E6%89%B9%29.zip?AccessKeyId=583AINLNMLDRFK7CC1YM&Expires=1739168844&Signature=9iONBSJORCS8UNr2m/VZnc7yYno%3D" -O 训练集\(有标注第一批\).zip
!unar -q 训练集\(有标注第一批\).zip
!wget "https://comp-public-prod.obs.cn-east-3.myhuaweicloud.com/dataset/2024/%E6%B5%8B%E8%AF%95%E9%9B%86.zip?AccessKeyId=583AINLNMLDRFK7CC1YM&Expires=1739168909&Signature=CRsB54VqOtrzIdUHC3ay0l2ZGNw%3D" -O 测试集.zip
!unar -q 测试集.zip
数据读取
train_anno = json.load(open('训练集(有标注第一批)/标注/45.json', encoding='utf-8'))
train_anno[0], len(train_anno)
读取结果:
({'frame_id': 0,
'event_id': 1,
'category': '非机动车违停',
'bbox': [746, 494, 988, 786]},
1688)
训练集读取
pd.read_json('训练集(有标注第一批)/标注/45.json')
读取结果:
0 1 非机动车违停 [746, 494, 988, 786]
1 0 2 非机动车违停 [755, 606, 967, 843]
2 0 3 非机动车违停 [502, 33, 829, 365]
3 0 4 机动车违停 [549, 784, 1345, 1079]
4 1 1 非机动车违停 [746, 494, 988, 786]
… … … … …
1683 420 4 机动车违停 [549, 784, 1345, 1079]
1684 421 4 机动车违停 [549, 784, 1345, 1079]
1685 421 1 非机动车违停 [746, 494, 988, 786]
1686 421 2 非机动车违停 [755, 606, 967, 843]
1687 421 3 非机动车违停 [502, 33, 829, 365]
video_path = '训练集(有标注第一批)/视频/45.mp4'
cap = cv2.VideoCapture(video_path)
while True:
# 读取下一帧
ret, frame = cap.read()
if not ret:
break
break
bbox = [746, 494, 988, 786]
pt1 = (bbox[0], bbox[1])
pt2 = (bbox[2], bbox[3])
color = (0, 255, 0)
thickness = 2 # 线条粗细
cv2.rectangle(frame, pt1, pt2, color, thickness)
frame = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
plt.imshow(frame)frame.shape
数据处理
if not os.path.exists('yolo-dataset/'):
os.mkdir('yolo-dataset/')
if not os.path.exists('yolo-dataset/train'):
os.mkdir('yolo-dataset/train')
if not os.path.exists('yolo-dataset/val'):
os.mkdir('yolo-dataset/val')
dir_path = os.path.abspath('./') + '/'
# 需要按照你的修改path
with open('yolo-dataset/yolo.yaml', 'w', encoding='utf-8') as up:
up.write(f'''
path: {dir_path}/yolo-dataset/
train: train/
val: val/
names:
0: 非机动车违停
1: 机动车违停
2: 垃圾桶满溢
3: 违法经营
''')
train
train_annos = glob.glob('训练集(有标注第一批)/标注/*.json')
train_videos = glob.glob('训练集(有标注第一批)/视频/*.mp4')
train_annos.sort(); train_videos.sort();
category_labels = ["非机动车违停", "机动车违停", "垃圾桶满溢", "违法经营"]
分别对视频数据进行处理
for anno_path, video_path in zip(train_annos[:5], train_videos[:5]):
print(video_path)
anno_df = pd.read_json(anno_path)
cap = cv2.VideoCapture(video_path)
frame_idx = 0
while True:
ret, frame = cap.read()
if not ret:
break
img_height, img_width = frame.shape[:2]
frame_anno = anno_df[anno_df['frame_id'] == frame_idx]
cv2.imwrite('./yolo-dataset/train/' + anno_path.split('/')[-1][:-5] + '_' + str(frame_idx) + '.jpg', frame)
if len(frame_anno) != 0:
with open('./yolo-dataset/train/' + anno_path.split('/')[-1][:-5] + '_' + str(frame_idx) + '.txt', 'w') as up:
for category, bbox in zip(frame_anno['category'].values, frame_anno['bbox'].values):
category_idx = category_labels.index(category)
x_min, y_min, x_max, y_max = bbox
x_center = (x_min + x_max) / 2 / img_widthfor anno_path,
for anno_path, video_path in zip(train_annos[-3:], train_videos[-3:]):
print(video_path)
anno_df = pd.read_json(anno_path)
cap = cv2.VideoCapture(video_path)
frame_idx = 0
while True:
ret, frame = cap.read()
if not ret:
break
img_height, img_width = frame.shape[:2]
frame_anno = anno_df[anno_df['frame_id'] == frame_idx]
cv2.imwrite('./yolo-dataset/val/' + anno_path.split('/')[-1][:-5] + '_' + str(frame_idx) + '.jpg', frame)
if len(frame_anno) != 0:
with open('./yolo-dataset/val/' + anno_path.split('/')[-1][:-5] + '_' + str(frame_idx) + '.txt', 'w') as up:
for category, bbox in zip(frame_anno['category'].values, frame_anno['bbox'].values):
category_idx = category_labels.index(category)
x_min, y_min, x_max, y_max = bbox
x_center = (x_min + x_max) / 2 / img_width
y_center = (y_min + y_max) / 2 / img_height
width = (x_max - x_min) / img_width
height = (y_max - y_min) / img_height
up.write(f'{category_idx} {x_center} {y_center} {width} {height}\n')
frame_idx += 1
y_center = (y_min + y_max) / 2 / img_height
width = (x_max - x_min) / img_width
height = (y_max - y_min) / img_height
if x_center > 1:
print(bbox)
up.write(f'{category_idx} {x_center} {y_center} {width} {height}\n')
frame_idx += 1
!wget http://mirror.coggle.club/yolo/yolov8n-v8.2.0.pt -O yolov8n.pt
!mkdir -p ~/.config/Ultralytics/
!wget http://mirror.coggle.club/yolo/Arial.ttf -O ~/.config/Ultralytics/Arial.ttf
import os
os.environ["CUDA_VISIBLE_DEVICES"] = "0"
import warnings
warnings.filterwarnings('ignore')
from ultralytics import YOLO
model = YOLO("yolov8n.pt")
results = model.train(data="yolo-dataset/yolo.yaml", epochs=2, imgsz=1080, batch=16)
category_labels = ["非机动车违停", "机动车违停", "垃圾桶满溢", "违法经营"]
if not os.path.exists('result/'):
os.mkdir('result')
Test
from ultralytics import YOLO
model = YOLO("runs/detect/train/weights/best.pt")
import glob
for path in glob.glob('测试集/*.mp4'):
submit_json = []
results = model(path, conf=0.05, imgsz=1080, verbose=False)
for idx, result in enumerate(results):
boxes = result.boxes # Boxes object for bounding box outputs
masks = result.masks # Masks object for segmentation masks outputs
keypoints = result.keypoints # Keypoints object for pose outputs
probs = result.probs # Probs object for classification outputs
obb = result.obb # Oriented boxes object for OBB outputs
if len(boxes.cls) == 0:
continue
xywh = boxes.xyxy.data.cpu().numpy().round()
cls = boxes.cls.data.cpu().numpy().round()
conf = boxes.conf.data.cpu().numpy()
for i, (ci, xy, confi) in enumerate(zip(cls, xywh, conf)):
submit_json.append(
{
'frame_id': idx,
'event_id': i+1,
'category': category_labels[int(ci)],
'bbox': list([int(x) for x in xy]),
"confidence": float(confi)
}
)
with open('./result/' + path.split('/')[-1][:-4] + '.json', 'w', encoding='utf-8') as up:
json.dump(submit_json, up, indent=4, ensure_ascii=False)
结果输出
!\rm result/.ipynb_checkpoints/ -rf
!\rm result.zip
!zip -r result.zip result/