{"cells":[{"metadata":{},"cell_type":"markdown","source":"# This is a baseline model showing FastAI library to solve the leaf disease classification problem"},{"metadata":{"trusted":true},"cell_type":"code","source":"#Check for presence of GPU\n!nvidia-smi","execution_count":null,"outputs":[]},{"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\n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\nimport glob\nfrom fastai.vision.all import *\n\n# Input data files are available in the read-only \"../input/\" directory\n# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory\n\nimport os\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n    for filename in filenames:\n        print(os.path.join(dirname, filename))\n\n# You can write up to 20GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using \"Save & Run All\" \n# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"#Check for shape of training data\ntrain = pd.read_csv('/kaggle/input/cassava-leaf-disease-classification/train.csv')\ntrain.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#Let's see how the training data looks\ntrain.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Check if there is class imbalance\ntrain['label'].value_counts().plot(kind='bar')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#Validate if training images directory contain all the files\ntrain_fns = glob.glob('/kaggle/input/cassava-leaf-disease-classification/train_images/*.*')\nlen(train_fns)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#Check sample submission file\nss = pd.read_csv('/kaggle/input/cassava-leaf-disease-classification/sample_submission.csv')\nss.head()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# **Fastai dataloaders**"},{"metadata":{"trusted":true},"cell_type":"code","source":"img2lbl = dict()\nfor k,v in zip(train.image_id.values,train.label.values):\n    img2lbl[k] = v  ","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def get_items(_):\n    return train.image_id.values","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def get_x(fn):\n    img = Image.open('/kaggle/input/cassava-leaf-disease-classification/train_images/' + fn)\n    return np.array(img)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def get_y(fn):\n    return img2lbl[fn]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"db = DataBlock(blocks = (ImageBlock, CategoryBlock),\n               get_items = get_items,\n               get_x = get_x,\n               get_y     = get_y,\n               splitter  = RandomSplitter(),\n               item_tfms = Resize(224),\n               batch_tfms= [Normalize.from_stats(*imagenet_stats),*aug_transforms(size=224)]\n              )\n\ndls = db.dataloaders('',bs=64)\ndls.show_batch()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Creating a learner using Resnet34 model and train"},{"metadata":{"trusted":true},"cell_type":"code","source":"learn = cnn_learner(dls,resnet34,CrossEntropyLossFlat,metrics=[accuracy]).to_fp16()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"learn.fine_tune(5)","execution_count":null,"outputs":[]}],"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"pygments_lexer":"ipython3","nbconvert_exporter":"python","version":"3.6.4","file_extension":".py","codemirror_mode":{"name":"ipython","version":3},"name":"python","mimetype":"text/x-python"}},"nbformat":4,"nbformat_minor":4}