[pytorch] 图像目标检测框架【Efficientnet0/1/2/3/4/5/6/7】

MachineLP

发布于 2020-10-29 02:19:46

73400

代码可运行

文章被收录于专栏：小鹏的专栏小鹏的专栏

运行总次数：0

代码可运行

以kaggle的SIIM-ISIC Melanoma Classification比赛：https://www.kaggle.com/c/global-wheat-detection ；介绍efficientnet模型在目标检测任务上的使用。

数据链接：https://www.kaggle.com/c/global-wheat-detection/data

代码如下：（加入mixup/cutmix）

import sys
sys.path.insert(0, "./timm-efficientdet-pytorch")
sys.path.insert(0, "./omegaconf")

import torch
import os
from datetime import datetime
import time
import random
import cv2
import pandas as pd
import numpy as np
import albumentations as A
import matplotlib.pyplot as plt
from albumentations.pytorch.transforms import ToTensorV2
from albumentations.core.transforms_interface import DualTransform
from albumentations.augmentations import functional as F
from sklearn.model_selection import StratifiedKFold
from torch.utils.data import Data