vsay01

import com.bumptech.glide.annotation.GlideModule;
import com.bumptech.glide.module.AppGlideModule;

@GlideModule
public final class MyAppGlideModule extends AppGlideModule {}

vsay01

# Mount Google Drive
from google.colab import drive # import drive from google colab

ROOT = "/content/drive"     # default location for the drive
print(ROOT)                 # print content of ROOT (Optional)

drive.mount(ROOT)           # we mount the google drive at /content/drive

vsay01

# Clone github repository setup
# import join used to join ROOT path and MY_GOOGLE_DRIVE_PATH
from os.path import join  

# path to your project on Google Drive
MY_GOOGLE_DRIVE_PATH = 'My Drive/MyDrive/Udacity/deep-learning-v2-pytorch' 
# replace with your Github username 
GIT_USERNAME = "vsay01" 
# definitely replace with your
GIT_TOKEN = "{YOUR_GITHUB_TOKEN}"  

vsay01

!git clone "{GIT_PATH}" ./temp      # clone github repository to temp folder
!mv ./temp/* "{PROJECT_PATH}"       # move all files/folders in temp folder to folder defined in project path
!rm -rf ./temp                      # remove all the files/folders in temp folder
!rsync -aP --exclude=data/ "{PROJECT_PATH}"/*  ./   # use remote sync to copy from google drive to local runtime google colab
                                                    # but exclude data folder
                                                    # https://www.computerhope.com/unix/rsync.htm

vsay01

#Import drive
from google.colab import drive
#Mount Google Drive
drive.mount("/content/drive")


%cd './drive/My Drive/MyDrive/Udacity/deep-learning-v2-pytorch/intro-to-pytorch/'
%pwd

#import helper.py

vsay01

%cd "{PROJECT_PATH}"    # Change directory to the location defined in project_path
!git clone "{GIT_PATH}" # clone the github repository

vsay01

!git add -u

vsay01

!git add .

vsay01

# uncomment if you want to create directory checkpoint, best_model
%mkdir checkpoint best_model

vsay01

%matplotlib inline
%config InlineBackend.figure_format = 'retina'

import matplotlib.pyplot as plt
import torch
import shutil
from torch import nn
from torch import optim
import torch.nn.functional as F
from torchvision import datasets, transforms