追梦小狂魔的博客

from pathlib import Path from fastai import * from fastai.vision import * import torch import os !pip install efficientnet-pytorch from efficientnet_pytorch import EfficientNet # for dirname, _, filenames in os.walk('/kaggle/input'): # for filename

挂载硬盘。两行就够了，没那么多花里胡哨的，第一次会出现个链接，点进去允许之后，会给一堆码，复制到程序空白光标哪里就行了。 from google.colab import drive drive.mount('/content/gdrive') 路径有点不一样，不是当前的路径，读取数据要改一下路径 程序是102fastai.ipynb，数据在同级目录下，但是要读取数据要用绝对路径 ...

callbacks = [ # callbacks.EarlyStoppingCallback(learn, min_delta=1e-5, patience=5), callbacks.SaveModelCallback(learn) ] learn.callbacks = callbacks 这个是最有用的配合这句 learn.load('bestmodel') 训练结束后...

!pip install efficientnet-pytorch from fastai import * from fastai.vision import * from efficientnet_pytorch import EfficientNet path = untar_data(URLs.PETS) path_anno = path/'annotations' path_img ...

对于这类平台环境都是配置好的，只是代码上传然后训练，和kaggle这种不一样，是py的不是ipynb所以代码稍微有点不同 建立一个sh文件 使用fast.vision时候会报错，要加上这句，主要是因为不支持可视化 mkdir -p /root/.config/matplotlib/ \ && echo "backend : Agg" > /root/.confi...

try: os.makedirs('/root/.cache/torch/checkpoints') except: print(111) !cp /kaggle/input/resnet5019c8e357/resnet50-19c8e357.pth /root/.cache/torch/checkpoints/resnet50-19c8e357.pth

#%% # This Python 3 environment comes with many helpful analytics libraries installed # It is defined by the kaggle/python docker image: https://github.com/kaggle/docker-python # For example, here's ...

get_transforms( do_flip:bool=True, # 是否进行水平翻转 flip_vert:bool=False, #是否进行垂直翻转 max_rotate:float=10.0, max_zoom:float=1.1, max_lighting:float=0.2, max_warp:float=0.2, p_affine:float...