{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"# This Python 3 environment comes with many helpful analytics libraries installed\n# It is defined by the kaggle/python docker image: https://github.com/kaggle/docker-python\n# For example, here's several helpful packages to load in \n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n\n# Input data files are available in the \"../input/\" directory.\n# For example, running this (by clicking run or pressing Shift+Enter) will list the files in the input directory\n\nimport os\nprint(os.listdir(\"../input\"))\n\n# Any results you write to the current directory are saved as output.","execution_count":null,"outputs":[]},{"metadata":{"_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","trusted":true},"cell_type":"code","source":"from fastai.vision import *\nimport torchvision\nfrom torch import nn\n\nPATH = '../input'\ndf_train = pd.read_csv(PATH+'/labels.csv', dtype={'id':str, 'breed':str})\n\nnorm_values = ([0.485, 0.456, 0.406],[0.229, 0.224, 0.225])\ndevice = torch.device(\"cuda:0\" if torch.cuda.is_available() else \"cpu\")\ndataBunch = ImageDataBunch.from_df(path=PATH,df=df_train,folder='train',suffix='.jpg',size=224,\n                                   test = 'test',\n                                   #ds_tfms=get_transforms(do_flip=True,flip_vert=True,max_warp=0),                                                         \n                                   bs=32,device=device).normalize(norm_values)\nmodel = torchvision.models.resnext101_32x8d(pretrained=True)\nfor param in model.parameters():\n    param.requires_grad = False\n\nclassifier = nn.Sequential(nn.Dropout(p=0.7),\n                          nn.Linear(2048,1024),\n                          nn.BatchNorm1d(1024),\n                         nn.ReLU(),\n                          nn.Linear(1024,120),\n                          nn.LogSoftmax(dim=1))\nmodel.fc = classifier\n\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"learn = Learner(data=dataBunch,model=model,model_dir='/tmp/models',metrics=[accuracy])\nlearn.lr_find()\nlearn.recorder.plot(suggestion=True)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"learn.fit_one_cycle(8,7e-02)","execution_count":null,"outputs":[]}],"metadata":{"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"},"language_info":{"name":"python","version":"3.6.4","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"}},"nbformat":4,"nbformat_minor":1}