基于百度AIStudio飞桨paddleRS-develop版道路模型开发训练

基于百度AIStudio飞桨paddleRS-develop版道路模型开发训练

参考地址：https://aistudio.baidu.com/projectdetail/8271882

基于python35+paddle120+env环境
预测可视化结果：

（一）安装环境：
先上传本地下载的源代码PaddleRS-develop.zip
解压PaddleRS-develop.zip到目录PaddleRS
然后分别执行下面安装命令!pip install

!unzip -q /home/aistudio/data/data191076/PaddleRS-develop.zip && mv PaddleRS-develop PaddleRS
!pip install matplotlib==3.4 scikit-image pycocotools -t /home/aistudio/external-libraries
!pip install  opencv-contrib-python -t /home/aistudio/external-libraries
!pip install -r PaddleRS/requirements.txt  -t /home/aistudio/external-libraries
!pip install -e PaddleRS/  -t /home/aistudio/external-libraries
!pip install paddleslim==2.6.0  -t /home/aistudio/external-libraries

添加环境组件

# 因为`sys.path`可能没有及时更新，这里选择手动更新
import sys
sys.path.append('/home/aistudio/external-libraries')
sys.path.append('/home/aistudio/PaddleRS')

（二）数据预处理tran_dataPre.py

%run tran_dataPre.py

（三）开始模型训练

%run trans.py

（四) tran_dataPre.py内容如下所示：

#先解压数据集
#!unzip -oq -d /home/aistudio/massroad /home/aistudio/data/data56961/mass_road.zip# 划分训练集/验证集/测试集，并生成文件名列表import random
import os.path as osp
from os import listdirimport cv2# 随机数生成器种子
RNG_SEED = 56961
# 调节此参数控制训练集数据的占比
TRAIN_RATIO = 0.9
# 数据集路径
DATA_DIR = '/home/aistudio/massroad'# 分割类别
CLASSES = ('background','road',
)def write_rel_paths(phase, names, out_dir, prefix):"""将文件相对路径存储在txt格式文件中"""with open(osp.join(out_dir, phase+'.txt'), 'w') as f:for name in names:f.write(' '.join([osp.join(prefix, 'input', name),osp.join(prefix, 'output', name)]))f.write('\n')random.seed(RNG_SEED)train_prefix = osp.join('road_segmentation_ideal', 'training')
test_prefix = osp.join('road_segmentation_ideal', 'testing')
train_names = listdir(osp.join(DATA_DIR, train_prefix, 'output'))
train_names = list(filter(lambda n: n.endswith('.png'), train_names))
test_names = listdir(osp.join(DATA_DIR, test_prefix, 'output'))
test_names = list(filter(lambda n: n.endswith('.png'), test_names))
# 对文件名进行排序，以确保多次运行结果一致
train_names.sort()
test_names.sort()
random.shuffle(train_names)
len_train = int(len(train_names)*TRAIN_RATIO)
write_rel_paths('train', train_names[:len_train], DATA_DIR, train_prefix)
write_rel_paths('val', train_names[len_train:], DATA_DIR, train_prefix)
write_rel_paths('test', test_names, DATA_DIR, test_prefix)# 写入类别信息
with open(osp.join(DATA_DIR, 'labels.txt'), 'w') as f:for cls in CLASSES:f.write(cls+'\n')print("数据集划分已完成。")# 将GT中的255改写为1，便于训练import os.path as osp
from glob import globimport cv2
from tqdm import tqdm# 数据集路径
# DATA_DIR = '/home/aistudio/massroad'train_prefix = osp.join('road_segmentation_ideal', 'training')
test_prefix = osp.join('road_segmentation_ideal', 'testing')train_paths = glob(osp.join(DATA_DIR, train_prefix, 'output', '*.png'))
test_paths = glob(osp.join(DATA_DIR, test_prefix, 'output', '*.png'))
for path in tqdm(train_paths+test_paths):im = cv2.imread(path, cv2.IMREAD_GRAYSCALE)im[im>0] = 1# 原地改写cv2.imwrite(path, im)

(五) trans.py内容如下所示：

# 导入需要用到的库import random
import os.path as ospimport cv2
import numpy as np
import paddle
import paddlers as pdrs
from paddlers import transforms as T
from matplotlib import pyplot as plt
from PIL import Imageimport sys
sys.path.append('/home/aistudio/external-libraries')
sys.path.append('/home/aistudio/PaddleRS')# 定义全局变量# 随机种子
SEED = 56961
# 数据集存放目录
DATA_DIR = '/home/aistudio/massroad/'
# 训练集`file_list`文件路径
TRAIN_FILE_LIST_PATH = '/home/aistudio/massroad/train.txt'
# 验证集`file_list`文件路径
VAL_FILE_LIST_PATH = '/home/aistudio/massroad/val.txt'
# 测试集`file_list`文件路径
TEST_FILE_LIST_PATH = '/home/aistudio/massroad/test.txt'
# 数据集类别信息文件路径
LABEL_LIST_PATH = '/home/aistudio/massroad/labels.txt'
# 实验目录，保存输出的模型权重和结果
EXP_DIR =  '/home/aistudio/exp/'# 固定随机种子，尽可能使实验结果可复现random.seed(SEED)
np.random.seed(SEED)
paddle.seed(SEED)# 构建数据集# 定义训练和验证时使用的数据变换（数据增强、预处理等）
train_transforms = T.Compose([T.DecodeImg(),# 随机裁剪T.RandomCrop(crop_size=512),# 以50%的概率实施随机水平翻转T.RandomHorizontalFlip(prob=0.5),# 以50%的概率实施随机垂直翻转T.RandomVerticalFlip(prob=0.5),# 将数据归一化到[-1,1]T.Normalize(mean=[0.5, 0.5, 0.5], std=[0.5, 0.5, 0.5]),T.ArrangeSegmenter('train')
])eval_transforms = T.Compose([T.DecodeImg(),T.Resize(target_size=1500),# 验证阶段与训练阶段的数据归一化方式必须相同T.Normalize(mean=[0.5, 0.5, 0.5], std=[0.5, 0.5, 0.5]),T.ArrangeSegmenter('eval')
])# 分别构建训练和验证所用的数据集
train_dataset = pdrs.datasets.SegDataset(data_dir=DATA_DIR,file_list=TRAIN_FILE_LIST_PATH,label_list=LABEL_LIST_PATH,transforms=train_transforms,num_workers=4,shuffle=True
)val_dataset = pdrs.datasets.SegDataset(data_dir=DATA_DIR,file_list=VAL_FILE_LIST_PATH,label_list=LABEL_LIST_PATH,transforms=eval_transforms,num_workers=0,shuffle=False
)# 构建DeepLab V3+模型，使用ResNet-50作为backbone
model = pdrs.tasks.seg.DeepLabV3P(in_channels=3,num_classes=len(train_dataset.labels),backbone='ResNet50_vd'
)
model.initialize_net(pretrain_weights='CITYSCAPES',save_dir=osp.join(EXP_DIR, 'pretrain'),resume_checkpoint=None,is_backbone_weights=False
)# 构建优化器
optimizer = paddle.optimizer.Adam(learning_rate=0.001, parameters=model.net.parameters()
)# 执行模型训练
model.train(num_epochs=100,train_dataset=train_dataset,train_batch_size=8,eval_dataset=val_dataset,optimizer=optimizer,save_interval_epochs=10,# 每多少次迭代记录一次日志log_interval_steps=30,save_dir=EXP_DIR,# 是否使用early stopping策略，当精度不再改善时提前终止训练early_stop=False,# 是否启用VisualDL日志功能use_vdl=True,# 指定从某个检查点继续训练resume_checkpoint=None
)

（六）训练生成过程信息

Output exceeds the size limit. Open the full output data in a text editor
2024-09-05 14:16:51 [INFO]	Loading pretrained model from /home/aistudio/exp/pretrain/model.pdparams
2024-09-05 14:16:53 [WARNING]	[SKIP] Shape of parameters head.decoder.conv.weight do not match. (pretrained: [19, 256, 1, 1] vs actual: [2, 256, 1, 1])
2024-09-05 14:16:53 [WARNING]	[SKIP] Shape of parameters head.decoder.conv.bias do not match. (pretrained: [19] vs actual: [2])
2024-09-05 14:16:53 [INFO]	There are 358/360 variables loaded into DeepLabV3P.
2024-09-05 14:17:46 [INFO]	[TRAIN] Epoch=1/100, Step=30/90, loss=0.133503, lr=0.001000, time_each_step=1.77s, eta=4:24:32
2024-09-05 14:18:25 [INFO]	[TRAIN] Epoch=1/100, Step=60/90, loss=0.181917, lr=0.001000, time_each_step=1.31s, eta=3:14:53
2024-09-05 14:19:02 [INFO]	[TRAIN] Epoch=1/100, Step=90/90, loss=0.112567, lr=0.001000, time_each_step=1.22s, eta=3:2:6
2024-09-05 14:19:03 [INFO]	[TRAIN] Epoch 1 finished, loss=0.15933047160506247 .
2024-09-05 14:19:44 [INFO]	[TRAIN] Epoch=2/100, Step=30/90, loss=0.141528, lr=0.001000, time_each_step=1.36s, eta=3:22:2
2024-09-05 14:20:20 [INFO]	[TRAIN] Epoch=2/100, Step=60/90, loss=0.165187, lr=0.001000, time_each_step=1.22s, eta=3:0:42
2024-09-05 14:20:57 [INFO]	[TRAIN] Epoch=2/100, Step=90/90, loss=0.145009, lr=0.001000, time_each_step=1.22s, eta=2:59:1
2024-09-05 14:20:58 [INFO]	[TRAIN] Epoch 2 finished, loss=0.1168842613697052 .
2024-09-05 14:21:39 [INFO]	[TRAIN] Epoch=3/100, Step=30/90, loss=0.126603, lr=0.001000, time_each_step=1.38s, eta=3:22:13
2024-09-05 14:22:16 [INFO]	[TRAIN] Epoch=3/100, Step=60/90, loss=0.117296, lr=0.001000, time_each_step=1.22s, eta=2:58:14
2024-09-05 14:22:53 [INFO]	[TRAIN] Epoch=3/100, Step=90/90, loss=0.072859, lr=0.001000, time_each_step=1.23s, eta=2:58:46
2024-09-05 14:22:53 [INFO]	[TRAIN] Epoch 3 finished, loss=0.10787189056475957 .
2024-09-05 14:23:34 [INFO]	[TRAIN] Epoch=4/100, Step=30/90, loss=0.081685, lr=0.001000, time_each_step=1.37s, eta=3:18:39
2024-09-05 14:24:11 [INFO]	[TRAIN] Epoch=4/100, Step=60/90, loss=0.087735, lr=0.001000, time_each_step=1.23s, eta=2:57:28
2024-09-05 14:24:48 [INFO]	[TRAIN] Epoch=4/100, Step=90/90, loss=0.084795, lr=0.001000, time_each_step=1.22s, eta=2:55:44
2024-09-05 14:24:49 [INFO]	[TRAIN] Epoch 4 finished, loss=0.10476481277081702 .
2024-09-05 14:25:30 [INFO]	[TRAIN] Epoch=5/100, Step=30/90, loss=0.098625, lr=0.001000, time_each_step=1.37s, eta=3:16:59
2024-09-05 14:26:07 [INFO]	[TRAIN] Epoch=5/100, Step=60/90, loss=0.078188, lr=0.001000, time_each_step=1.24s, eta=2:57:12
2024-09-05 14:26:43 [INFO]	[TRAIN] Epoch=5/100, Step=90/90, loss=0.098015, lr=0.001000, time_each_step=1.21s, eta=2:52:11
2024-09-05 14:26:44 [INFO]	[TRAIN] Epoch 5 finished, loss=0.10311256903741095 .
2024-09-05 14:27:25 [INFO]	[TRAIN] Epoch=6/100, Step=30/90, loss=0.109136, lr=0.001000, time_each_step=1.38s, eta=3:16:8
...
2024-09-05 15:39:38 [INFO]	Start to evaluate (total_samples=81, total_steps=81)...
2024-09-05 15:40:14 [INFO]	[EVAL] Finished, Epoch=40, miou=0.716638, category_iou=[0.96831487 0.46496069], oacc=0.969164, category_acc=[0.97447995 0.81316509], kappa=0.619485, category_F1-score=[0.98390241 0.63477565] .
2024-09-05 15:40:14 [INFO]	Current evaluated best model on eval_dataset is epoch_10, miou=0.7255623401044613
2024-09-05 15:40:18 [INFO]	Model saved in /home/aistudio/exp/epoch_40.

（七) 测试集预测结果：

# 构建测试集
test_dataset = pdrs.datasets.SegDataset(data_dir=DATA_DIR,file_list=TEST_FILE_LIST_PATH,label_list=LABEL_LIST_PATH,transforms=eval_transforms,num_workers=0,shuffle=False
)# 为模型加载历史最佳权重
state_dict = paddle.load(osp.join(EXP_DIR, 'best_model/model.pdparams'))
model.net.set_state_dict(state_dict)# 执行测试
test_result = model.evaluate(test_dataset)
print("测试集上指标：IoU为{:.2f}，Acc为{:.2f}，Kappa系数为{:.2f}, F1为{:.2f}".format(test_result['category_iou'][1], test_result['category_acc'][1],test_result['kappa'],test_result['category_F1-score'][1])
)

2024-09-05 20:07:40 [INFO]	13 samples in file /home/aistudio/massroad/test.txt
2024-09-05 20:07:41 [INFO]	Start to evaluate (total_samples=13, total_steps=13)...
测试集上指标：IoU为0.47，Acc为0.82，Kappa系数为0.62, F1为0.64

（八）预测结果可视化情况：

# 预测结果可视化
# 重复运行本单元可以查看不同结果def read_image(path):im = cv2.imread(path)return im[...,::-1]def show_images_in_row(ims, fig, title='', quantize=False):n = len(ims)fig.suptitle(title)axs = fig.subplots(nrows=1, ncols=n)for idx, (im, ax) in enumerate(zip(ims, axs)):# 去掉刻度线和边框ax.spines['top'].set_visible(False)ax.spines['right'].set_visible(False)ax.spines['bottom'].set_visible(False)ax.spines['left'].set_visible(False)ax.get_xaxis().set_ticks([])ax.get_yaxis().set_ticks([])if isinstance(im, str):im = read_image(im)if quantize:im = (im*255).astype('uint8')if im.ndim == 2:im = np.tile(im[...,np.newaxis], [1,1,3])ax.imshow(im)# 需要展示的样本个数
num_imgs_to_show = 4
# 随机抽取样本
chosen_indices = random.choices(range(len(test_dataset)), k=num_imgs_to_show)# 参考 https://stackoverflow.com/a/68209152
fig = plt.figure(constrained_layout=True)
fig.suptitle("Test Results")subfigs = fig.subfigures(nrows=3, ncols=1)# 读取输入影像并显示
im_paths = [test_dataset.file_list[idx]['image'] for idx in chosen_indices]
show_images_in_row(im_paths, subfigs[0], title='Image')# 获取模型预测输出
with paddle.no_grad():model.net.eval()preds = []for idx in chosen_indices:input, mask = test_dataset[idx]input = paddle.to_tensor(input["image"]).unsqueeze(0)logits, *_ = model.net(input)pred = paddle.argmax(logits[0], axis=0)preds.append(pred.numpy())
show_images_in_row(preds, subfigs[1], title='Pred', quantize=True)# 读取真值标签并显示
im_paths = [test_dataset.file_list[idx]['mask'] for idx in chosen_indices]
show_images_in_row(im_paths, subfigs[2], title='GT', quantize=True)# 渲染结果
fig.canvas.draw()
Image.frombytes('RGB', fig.canvas.get_width_height(), fig.canvas.tostring_rgb())

(九) 导出静态模型
训练后保存的模型为动态模型，布署发布模型为静态模型，因此需要导出操作

import matplotlib.pyplot as plt
import random
import cv2
import numpy as np
import paddle
import paddlers as pdrs
from PIL import Imageimport os
from paddlers.tasks import load_modelmodel_path =  './exp/best_model'img_14="i:/cwgis_ai/cup/mass_road/road_segmentation_ideal/testing/input/img-14.png"
img_10="i:/cwgis_ai/cup/mass_road/road_segmentation_ideal/testing/input/img-10.png"#save_dir="./models/road_infer_model_100"
save_dir="./models/road_infer_model_100_custom"# export model OK
# Set environment variables
os.environ['PADDLEX_EXPORT_STAGE'] = 'True'
os.environ['PADDLESEG_EXPORT_STAGE'] = 'True'# Load model from directory
model = load_model(model_path)#fixed_input_shape = None
#fixed_input_shape = [1500,1500]
fixed_input_shape = [17761,25006]      #[w,h]# Do dynamic-to-static cast   动态到静态的转换
# XXX: Invoke a protected (single underscore) method outside of subclasses.
model.export_inference_model(save_dir, fixed_input_shape)

（十) 预测单张图片代码

import matplotlib.pyplot as plt
import random
import cv2
import numpy as np
import paddle
import paddlers as pdrs
from PIL import Imageimport os
from paddlers.tasks import load_model# 因为`sys.path`可能没有及时更新，这里选择手动更新
import sys
sys.path.append('/home/aistudio/external-libraries')
sys.path.append('/home/aistudio/PaddleRS')img_14="./massroad/road_segmentation_ideal/testing/input/img-14.png"
img_10="./massroad/road_segmentation_ideal/testing/input/img-10.png"
img_5="./massroad/road_segmentation_ideal/testing/input/img-5.png"customImg="./customImage/DeepLearning_Image.png"    #file tif to png #model_dir="./models/road_infer_model_100"
#model_dir="./models/road_infer_model_100_None"
model_dir="./models/road_infer_model_100_custom"#model = pdrs.deploy.Predictor(model_dir)
model = pdrs.deploy.Predictor(model_dir,use_gpu=True)# 读取输入影像并显示
im_paths = [customImg]
im_lis = []
for name in im_paths:print(name)img = cv2.imread(name)      print(img.shape) #img = paddle.to_tensor(img) #.unsqueeze(0)   #标量输入im_lis.append(img)
# 获取模型预测输出img_file=img_10
preds = []
results = model.predict(im_lis)
#print(results)label_map=results[0]["label_map"]
#print(label_map)
label_map[label_map>0] = 255
cv2.imwrite('./outImage/label_map_custom.png', label_map)score_map=results[0]["score_map"]
#cv2.imwrite('./outImage/score_map.png', score_map[0])
print(score_map)print("预测完成")

本blog地址：https://blog.csdn.net/hsg77