飞桨常规赛：PALM眼底彩照中黄斑中央凹定位-7月第3名方案

import osimport pandas as pdimport numpy as npimport paddleimport paddle.vision.transforms as Tfrom paddle.io import Datasetfrom PIL import Image

! unzip -oq data/data100179/常规赛：PALM眼底彩照中黄斑中央凹定位.zip! rm -rf __MACOSX
! mv 常规赛：PALM眼底彩照中黄斑中央凹定位 PLAM

import warnings
warnings.filterwarnings("ignore") #拒绝烦人的警告信息

from paddle.io import DataLoader

tpsize = 256 split = 0.9batch_size = 16class PLAMDatas(Dataset):
    def __init__(self, data_path, class_xls, mode='train', transforms=None, re_size=tpsize):
        super(PLAMDatas, self).__init__()
        self.data_path = data_path
        self.name_label = (pd.read_excel(class_xls)).values
        lens = len(self.name_label)        if mode == 'train':
            self.name_label = self.name_label[:int(split*lens)]        else:
            self.name_label = self.name_label[int(split*lens):]
        self.transforms = transforms
        self.re_size = re_size        
    def __getitem__(self, index):
        name, x, y = self.name_label[index] # 得到的数据赋值一下
        data_path = os.path.join(self.data_path, name) # 文件系统路径+图片的name=图片的路径
        data = np.asarray(Image.open(data_path).convert('RGB'))
        H, W, _ = data.shape        if self.transforms is not None:
            data = self.transforms(data)
        data = data.astype('float32')
        
        label = np.array([x * self.re_size / W, y * self.re_size / H]).astype('float32') # 图片大小变了，对应的坐标自然也要改变
        return data, label        
    def __len__(self):
        return len(self.name_label)# 配置数据增广train_transforms = T.Compose([
    T.Resize((tpsize, tpsize), interpolation='bicubic'), #都调整到1800 选用bicubic，放大不至于太失真
   	T.ToTensor()
])

val_transforms = T.Compose([
    T.Resize((tpsize, tpsize), interpolation='bicubic'),
    T.ToTensor()
])# 配置数据集train_dataset = PLAMDatas(data_path='PLAM/Train/fundus_image', class_xls='PLAM/Train/Fovea_Location_train.xlsx', mode='train', transforms=train_transforms)
val_dataset = PLAMDatas(data_path='PLAM/Train/fundus_image', class_xls='PLAM/Train/Fovea_Location_train.xlsx', mode='test', transforms=val_transforms)

train_dataloader = DataLoader(dataset=train_dataset, 
                              batch_size=batch_size,
                              shuffle=True, drop_last=False)
dev_dataloader = DataLoader( dataset=val_dataset, 
                             batch_size=batch_size,
                             shuffle=True, drop_last=False)

print(len(train_dataset), len(val_dataset))print(len(train_dataloader), len(dev_dataloader))

import paddleimport paddle.nn as nnfrom paddle.vision.models import resnet50# 模型定义# pre_params = paddle.load('resnet_50_save_models/final.pdparams')# model.set_state_dict(pre_params)model = nn.Sequential(
    resnet50(pretrained=True),
    nn.LeakyReLU(),
    nn.Linear(1000, 2)  # 坐标定位)
paddle.summary(model, (1, 3, tpsize, tpsize))
model = paddle.Model(model)

2021-07-23 14:09:08,122 - INFO - unique_endpoints {''}2021-07-23 14:09:08,124 - INFO - Downloading resnet50.pdparams from https://paddle-hapi.bj.bcebos.com/models/resnet50.pdparams100%|██████████| 151272/151272 [00:02<00:00, 61339.97it/s]2021-07-23 14:09:10,837 - INFO - File /home/aistudio/.cache/paddle/hapi/weights/resnet50.pdparams md5 checking...-------------------------------------------------------------------------------
   Layer (type)         Input Shape          Output Shape         Param #    
===============================================================================
     Conv2D-1        [[1, 3, 256, 256]]   [1, 64, 128, 128]        9,408     
   BatchNorm2D-1    [[1, 64, 128, 128]]   [1, 64, 128, 128]         256      
      ReLU-1        [[1, 64, 128, 128]]   [1, 64, 128, 128]          0       
    MaxPool2D-1     [[1, 64, 128, 128]]    [1, 64, 64, 64]           0       
     Conv2D-3        [[1, 64, 64, 64]]     [1, 64, 64, 64]         4,096     --------------------------------省略-------------------------------------------BottleneckBlock-16   [[1, 2048, 8, 8]]     [1, 2048, 8, 8]           0       AdaptiveAvgPool2D-1  [[1, 2048, 8, 8]]     [1, 2048, 1, 1]           0       
     Linear-1           [[1, 2048]]           [1, 1000]          2,049,000   
     ResNet-1        [[1, 3, 256, 256]]       [1, 1000]              0       
    LeakyReLU-1         [[1, 1000]]           [1, 1000]              0       
     Linear-2           [[1, 1000]]             [1, 2]             2,002     ===============================================================================
Total params: 25,612,154Trainable params: 25,505,914Non-trainable params: 106,240-------------------------------------------------------------------------------Input size (MB): 0.75Forward/backward pass size (MB): 341.54Params size (MB): 97.70Estimated Total Size (MB): 439.99-------------------------------------------------------------------------------

# 自定义损失import paddleimport paddle.nn as nnimport paddle.nn.functional as Fclass FocusBCELoss(nn.Layer):
    '''
        本赛题的任务损失函数
    '''
    def __init__(self, weights=[0.5, 0.5]):
        super(FocusBCELoss, self).__init__()
        self.weights = weights  # 损失权重

    def forward(self, predict, label):
        # MSE均方误差
        mse_loss_x = paddle.nn.functional.mse_loss(predict[:, 0], label[:, 0], reduction='mean')
        mse_loss_y = paddle.nn.functional.mse_loss(predict[:, 1], label[:, 1], reduction='mean')
        mse_loss = 0.5 * mse_loss_x + 0.5 * mse_loss_y        # 欧氏距离
        distance_loss = paddle.subtract(predict, label)
        distance_loss = paddle.square(distance_loss)
        distance_loss = paddle.sum(distance_loss, axis=-1)
        distance_loss = paddle.sqrt(distance_loss)
        distance_loss = paddle.sum(distance_loss, axis=0) / predict.shape[0]   # predict.shape[0] == batch_size
        
        alpha1, alpha2 = self.weights
        all_loss = alpha1*mse_loss + alpha2*distance_loss        return all_loss, mse_loss, distance_loss

# 模型准备epochs = 1000lr = paddle.optimizer.lr.PolynomialDecay(learning_rate=2e-3, decay_steps=int(800*tpsize))
opt = paddle.optimizer.Adam(learning_rate=lr, parameters=model.parameters(), weight_decay=paddle.regularizer.L2Decay(5e-6))
loss  = FocusBCELoss(weights=[0.4, 0.6])   # weights，不同类别的损失权重model.prepare(
    optimizer = opt, 
    loss = loss
    )
visualdl=paddle.callbacks.VisualDL(log_dir='visual_log')#在使用GPU机器时，可以将use_gpu变量设置成Trueuse_gpu = Truepaddle.set_device('gpu:0') if use_gpu else paddle.set_device('cpu')# 模型微调model.fit(
    train_data=train_dataset, 
    eval_data=val_dataset, 
    batch_size=batch_size, 
    epochs=epochs, 
    eval_freq=10, 
    log_freq=1, 
    save_dir='resnet_50_save_models_256_0.9_16', 
    save_freq=10, 
    verbose=1, 
    drop_last=False, 
    shuffle=True, 
    num_workers=0,
    callbacks=[visualdl]
)

Epoch 993/1000step 45/45 [==============================] - loss: 0.7025 0.5066 0.8331 - 1s/step        Epoch 994/1000step 45/45 [==============================] - loss: 1.8822 2.1647 1.6938 - 1s/step        Epoch 995/1000step 45/45 [==============================] - loss: 2.5339 2.9379 2.2646 - 1s/step         Epoch 996/1000step 45/45 [==============================] - loss: 1.3060 1.2016 1.3756 - 1s/step         Epoch 997/1000step 45/45 [==============================] - loss: 0.7337 0.4999 0.8896 - 1s/step         Epoch 998/1000step 45/45 [==============================] - loss: 1.0640 0.8573 1.2018 - 1s/step        Epoch 999/1000step 45/45 [==============================] - loss: 1.3307 1.1557 1.4473 - 1s/step        Epoch 1000/1000step 45/45 [==============================] - loss: 0.5870 0.3452 0.7482 - 1s/step

import osimport numpy as npimport pandas as pdfrom PIL import Imageimport paddle.vision.transforms as Timport paddleimport paddle.nn as nnimport paddle.nn.functional as Ffrom paddle.vision.models import resnet50

save_path = 'Fovea_Localization_Results.csv'file_path = 'PLAM/PALM-Testing400-Images'imgs_name = os.listdir(file_path)

model = nn.Sequential(
    resnet50(pretrained=False),
    nn.LeakyReLU(),
    nn.Linear(1000, 2)
)
params = paddle.load('resnet_50_save_models_256_0.9_16/final.pdparams')
model.set_state_dict(params)
model.eval()

inf_transforms = T.Compose([
    T.Resize((tpsize, tpsize), interpolation='bicubic'),
    T.ToTensor()
])

pre_data = []for img_name in imgs_name:
    data_path = os.path.join(file_path, img_name)
    data = np.asarray(Image.open(data_path).convert('RGB'))
    H, W, _ = data.shape
    data = inf_transforms(data)
    data = data.astype('float32').reshape([1, 3, tpsize, tpsize])
    pred = model(data)
    pre = [None] * 2
    # 还原坐标
    pre[0] = pred.numpy()[0][0] * W / tpsize
    pre[1] = pred.numpy()[0][1] * H / tpsize    print(img_name, pre)
    pre_data.append([img_name, pre[0], pre[1]])

df = pd.DataFrame(pre_data, columns=['FileName', 'Fovea_X', 'Fovea_Y'])
df.sort_values(by="FileName",inplace=True,ascending=True)  #千万记得排序！df.to_csv(save_path, index=None)

df

import osimport numpy as npimport pandas as pdfrom PIL import Imageimport matplotlib.pyplot as plt

%matplotlib inline

path = 'PLAM/PALM-Testing400-Images'flrs = np.array(pd.read_csv('Fovea_Localization_Results.csv'))for flr in flrs:
    img = np.array(Image.open(os.path.join(path, flr[0])))
    x, y = flr[1:]
    plt.imshow(img.astype('uint8'))
    plt.plot(x, y, 'or')
    plt.show()    break