阿里天池比赛——地表建筑物识别

阿里天池比赛——地表建筑物识别

记录一下之前参加的阿里天池比赛，方便以后查看。

策略：
1.多模型训练
2.多模型测试
3.数据增强
4.预训练/冻结训练
5.迁移学习
6.TTA
7.后处理
8.finetue

阿里天池比赛
我的代码连接
链接：https://pan.baidu.com/s/1Bwvjflov0O1O6RBD898-5g
提取码：fasf

部分代码如下，想玩这个项目的可以看我的代码，里面包含所有代码、数据、技巧。

#!/usr/bin/env python
# coding: utf-8

import numpy as np
import pandas as pd
import pathlib, sys, os, random, time
import numba, cv2, gc
#from tqdm import tqdm_notebook
from tqdm import tqdm
import matplotlib.pyplot as plt
#get_ipython().run_line_magic('matplotlib', 'inline')

import warnings
warnings.filterwarnings('ignore')
from sklearn.model_selection import KFold
import albumentations as A
import segmentation_models_pytorch as smp
import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.utils.data as D

import torchvision
from torchvision import transforms as T

from SegLoss.hausdorff import HausdorffDTLoss
from SegLoss.lovasz_loss import LovaszSoftmax


EPOCHES = 120
BATCH_SIZE = 8
IMAGE_SIZE = 512
DEVICE = 'cuda' if torch.cuda.is_available() else 'cpu'


import logging

logging.basicConfig(filename='log_unetplusplus_sh_fold_3_continue2.log',
                    format='%(asctime)s - %(name)s - %(levelname)s -%(module)s:  %(message)s',
                    datefmt='%Y-%m-%d %H:%M:%S ',
                    level=logging.INFO)

def set_seeds(seed=42):
    random.seed(seed)
    os.environ['PYTHONHASHSEED'] = str(seed)
    np.random.seed(seed)
    torch.manual_seed(seed)
    torch.cuda.manual_seed(seed)
    torch.cuda.manual_seed_all(seed)
    torch.backends.cudnn.deterministic = True
    torch.backends.cudnn.benchmark = False

set_seeds()

def rle_encode(im):
    '''
    im: numpy array, 1 - mask, 0 - background
    Returns run length as string formated
    '''
    pixels = im.flatten(order = 'F')
    pixels = np.concatenate([[0], pixels, [0]])
    runs = np.where(pixels[1:] != pixels[:-1])[0] + 1
    runs[1::2] -= runs[::2]
    return ' '.join(str(x) for x in runs)

def rle_decode(mask_rle, shape=(512, 512)):
    '''
    mask_rle: run-length as string formated (start length)
    shape: (height,width) of array to return 
    Returns numpy array, 1 - mask, 0 - background

    '''
    s = mask_rle.split()
    starts, lengths = [np.asarray(x, dtype=int) for x in (s[0:][::2], s[1:][::2])]
    starts -= 1
    ends = starts + lengths
    img = np.zeros(shape[0]*shape[1], dtype=np.uint8)
    for lo, hi