飞桨常规赛：PALM病理性近视病灶检测与分割 - 5月第六名方案

1. 包准备

既然是分割任务，首先想到的是PaddleSeg。那就直接搞起来就对了。这里想到之前遥感分割中用到patta还挺不错的，这里也弄进来一起搅。

! git clone https://gitee.com/paddlepaddle/PaddleSeg.git
! pip -q install pattaimport sys

sys.path.append('PaddleSeg')

2. 数据准备

2.1解压数据集

这个没啥好写的。

! unzip -oq /home/aistudio/data/data85135/常规赛：PALM病理性近视病灶检测与分割.zip! rm -rf __MACOSX
! mv 常规赛：PALM病理性近视病灶检测与分割 dataset

2.2 生成数据列表

老套路了，这里按0.9进行划分的，0.9的训练数据，0.1的验证数据。只是这里将两个数据分开进行处理，分别生成数据列表。这里我做点改变就是针对有一个任务标签很少的情况，每当读到它有标签的图像，就写50次进来，希望正负样本可以更加均衡。

UP简历

基于AI技术的免费在线简历制作工具

下载

import osimport randomdef create_list(lab_class='Detachment', s_rate=9, ex_num=50):
    file_path = 'dataset/Train/fundus_image'
    imgs_name = os.listdir(file_path)
    random.shuffle(imgs_name)    with open('dataset/Train/' + lab_class + '_train.txt', 'w') as tf:        with open('dataset/Train/' + lab_class + '_val.txt', 'w') as ef:            for idx, img_name in enumerate(imgs_name):
                img_path = os.path.join('fundus_image', img_name)
                lab_path = img_exist('dataset/Train', \
                					 img_path.replace('fundus_image', ('Lesion_Masks/' + \
                                     lab_class)).replace('jpg', 'bmp'))                if (idx % 10 + 1) < s_rate:                    if lab_class == 'Detachment' and lab_path != 'None':                        for _ in range(ex_num):
                            tf.write(img_path + ' ' + lab_path + '\n')                    else:
                    	tf.write(img_path + ' ' + lab_path + '\n')                else:
                    ef.write(img_path + ' ' + lab_path + '\n')def img_exist(path, name):
    p = os.path.join(path, name)    if os.path.exists(p):        return name    else:        return 'None'def shuffle_txt(path, save_path):
    out = open(save_path,'w')
    lines = []    with open(path, 'r') as infile:        for line in infile:
            lines.append(line)
        random.shuffle(lines)        for line in lines:
            out.write(line)
    out.close()

create_list('Detachment', s_rate=8)
create_list('Atrophy')
shuffle_txt('dataset/Train/Detachment_train.txt', \		   'dataset/Train/Detachment_train_shuffle.txt')

2.3 构建数据集

构建数据集也是套路的seg的方案，只是也是分别进行了处理。

from paddleseg.datasets import Datasetimport paddleseg.transforms as T# 构建训练集train_transforms = [
    T.RandomHorizontalFlip(),  # 水平翻转
    T.RandomRotation(),  # detachment
    T.Resize(target_size=(1024, 1024)),  # 修改大小
    T.Normalize()  # 归一化]

d_train_dataset = Dataset(
    transforms=train_transforms,
    dataset_root='dataset/Train',
    num_classes=2,
    mode='train',
    train_path='dataset/Train/Detachment_train_shuffle.txt',
    separator=' ',
)

a_train_dataset = Dataset(
    transforms=train_transforms,
    dataset_root='dataset/Train',
    num_classes=2,
    mode='train',
    train_path='dataset/Train/Atrophy_train.txt',
    separator=' ',
)# 构建验证集val_transforms = [
    T.Resize(target_size=(1024, 1024)),
    T.Normalize()
]

d_val_dataset = Dataset(
    transforms=val_transforms,
    dataset_root='dataset/Train',
    num_classes=2,
    mode='val',
    val_path='dataset/Train/Detachment_val.txt',
    separator=' ',
)

a_val_dataset = Dataset(
    transforms=val_transforms,
    dataset_root='dataset/Train',
    num_classes=2,
    mode='val',
    val_path='dataset/Train/Atrophy_val.txt',
    separator=' ',
)

这里也是输出测试一下，看看数据读取有没有什么问题。避免后面报一堆错不知道哪儿去找问题。还可以看看图像是否正确。

# import numpy as np# import matplotlib# import matplotlib.pyplot as plt# %matplotlib inline# for img, lab in d_train_dataset:#     print(img.shape, lab.shape)#     plt.subplot(121);plt.imshow(img.transpose((1, 2, 0)))#     plt.subplot(122);plt.imshow(lab)#     plt.show()#     break

3. 模型训练

3.1 训练准备

这里选了一个我从来没用过的网路SFNet，不过有一次就会有下一次，所以就尝试下没用过的。损失混合了三种损失，两个任务需要分别进行训练。

import paddlefrom paddleseg.models import SFNetfrom paddleseg.models.backbones import ResNet50_vdfrom paddleseg.models.losses import BCELoss, DiceLoss, LovaszHingeLoss, MixedLoss# 模型url = 'a_save_output/best_model/model.pdparams'model = SFNet(num_classes=2, backbone=ResNet50_vd(output_stride=8), \
			  backbone_indices=[0, 1, 2, 3], pretrained=url)# 训练参数epochs = 10batch_size = 4iters = epochs * len(d_train_dataset) // batch_size# 损失函数mix_losses = [BCELoss(), DiceLoss(), LovaszHingeLoss()]
mix_coef = [1, 1, 1]
mixloss = MixedLoss(mix_losses, mix_coef)
losses = {}
losses['types'] = [mixloss]
losses['coef'] = [1]# 学习率及优化器base_lr = 3e-4# lr = paddle.optimizer.lr.CosineAnnealingDecay(base_lr, T_max=(iters // 5))lr = paddle.optimizer.lr.PolynomialDecay(base_lr, 4277 // 2, end_lr=3e-8)
optimizer = paddle.optimizer.Adam(lr, parameters=model.parameters(), weight_decay=paddle.regularizer.L2Decay(1e-9))

2021-05-24 18:50:46 [INFO]	No pretrained model to load, ResNet_vd will be trained from scratch.
2021-05-24 18:50:46 [INFO]	Loading pretrained model from a_save_output/best_model/model.pdparams
2021-05-24 18:50:47 [INFO]	There are 354/354 variables loaded into SFNet.

3.2 模型训练

分别调用train即可。

from paddleseg.core import train

train(
    model=model,
    train_dataset=d_train_dataset,
    val_dataset=d_val_dataset,
    optimizer=optimizer,
    save_dir='d_save_output',
    iters=iters,
    batch_size=batch_size,
    save_interval=int(iters / 10),
    log_iters=10,
    num_workers=0,
    losses=losses,
    use_vdl=True)

4. 模型预测

预测这里主要是两个问题。

1. 由于图像缩小到了1120，所以预测得到的结果需要resize到原大小才行。
2. 不知道是不是图像太大的问题，一使用patta就GPU炸了，所以这里的结果是没用TTA的结果。

import paddlefrom paddleseg.models import SFNetfrom paddleseg.models.backbones import ResNet50_vdimport paddleseg.transforms as Tfrom paddleseg.core import inferimport osimport cv2from tqdm import tqdmfrom PIL import Imageimport numpy as npimport patta as ttadef nn_infer(model, model_path, imgs_path, class_name='Atrophy', is_tta=True):
    params = paddle.load(model_path)
    model.set_dict(params)
    model.eval()    if not os.path.exists('Lesion_Segmentation'):
        os.mkdir('Lesion_Segmentation')    if not os.path.exists(os.path.join('Lesion_Segmentation', class_name)):
        os.mkdir(os.path.join('Lesion_Segmentation', class_name))    # 预测结果
    transforms = T.Compose([
        T.Resize(target_size=(1024, 1024)),
        T.Normalize()
    ])    # 循环预测和保存
    for img_path in tqdm(imgs_path):
        H, W, _ = np.asarray(Image.open(img_path)).shape
        img, _ = transforms(img_path)  # 进行数据预处理
        img = paddle.to_tensor(img[np.newaxis, :])  # C,H,W -> 1,C,H,W
        # TTA
        if is_tta == True:
            tta_pres = paddle.zeros([1, 2, 1024, 1024])            for tta_transform in tta.aliases.flip_transform():
                tta_img = tta_transform.augment_image(img)  # TTA_transforms
                tta_pre = infer.inference(model, tta_img)  # 预测
                deaug_pre = tta_transform.deaugment_mask(tta_pre)
                tta_pres += deaug_pre
            pre = tta_pres / 2.
        else:
            pre = infer.inference(model, img)  # 预测
        pred = paddle.argmax(pre, axis=1).numpy().reshape((1024, 1024)).astype('uint8') * 255
        pred = cv2.resize(pred, (W, H), interpolation=cv2.INTER_NEAREST)
        pil_img = Image.fromarray(pred)
        pil_img.save(os.path.join(('Lesion_Segmentation/' + class_name), img_path.split('/')[-1].replace('jpg', 'png')), 'png')# 网络准备a_model_path='a_save_output/best_model/model.pdparams'd_model_path='d_save_output/best_model/model.pdparams'model = SFNet(num_classes=2, backbone=ResNet50_vd(output_stride=8), \
			  backbone_indices=[0, 1, 2, 3], pretrained=None)# 预测文件set_path = 'dataset/PALM-Testing400-Images'names = os.listdir(set_path)
imgs_path = []for name in names:
    imgs_path.append(os.path.join(set_path, name))# 预测nn_infer(model, a_model_path, imgs_path, class_name='Atrophy', is_tta=False)
nn_infer(model, d_model_path, imgs_path, class_name='Detachment', is_tta=False)

5. 结果展示

可以用matplotlib显示一下分割的结果看看。

import numpy as npfrom PIL import Imageimport matplotlib.pyplot as plt

%matplotlib inline

img_path = 'dataset/PALM-Testing400-Images/T0225.jpg'inf_a_path = 'Lesion_Segmentation/Atrophy/T0225.png'inf_d_path = 'Lesion_Segmentation/Detachment/T0225.png'img = Image.open(img_path)
inf_a = Image.open(inf_a_path)
inf_d = Image.open(inf_d_path)
plt.figure(figsize=(15, 5))
plt.subplot(131);plt.imshow(img);plt.title('img')
plt.subplot(132);plt.imshow(inf_a);plt.title('inf_a')
plt.subplot(133);plt.imshow(inf_d);plt.title('inf_d')
plt.show()