{"cells":[{"metadata":{},"cell_type":"markdown","source":"**BEFORE YOU FORK, PLEASE SUPPORT AND UPVOTE**"},{"metadata":{},"cell_type":"markdown","source":"Original Kernel taken from https://www.kaggle.com/tanlikesmath/intro-aptos-diabetic-retinopathy-eda-starter\n\nChanges done:\n\n1. Change image size to 256\n2. Fix TTA\n3. Add stratified KFold splitting"},{"metadata":{"trusted":true},"cell_type":"code","source":"%reload_ext autoreload\n%autoreload 2\n%matplotlib inline","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"from fastai import *\nfrom fastai.vision import *\nimport pandas as pd\nimport matplotlib.pyplot as plt","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"if not os.path.exists('models/'):\n        os.makedirs('models')\n\n!cp '../input/aptosresnet152/resnet50-3.pth' 'models/resnet50.pth'\n!cp '../input/aptosresnet152/stage-2.pth' 'models/resnet152.pth'","execution_count":null,"outputs":[]},{"metadata":{"_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","trusted":true},"cell_type":"code","source":"import os\nos.listdir('.')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def seed_everything(seed):\n    random.seed(seed)\n    os.environ['PYTHONHASHSEED'] = str(seed)\n    np.random.seed(seed)\n    torch.manual_seed(seed)\n    torch.cuda.manual_seed(seed)\n    torch.backends.cudnn.deterministic = True\n\nSEED = 999\nseed_everything(SEED)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"base_image_dir = os.path.join('..', 'input/aptos2019-blindness-detection/')\ntrain_dir = os.path.join(base_image_dir,'train_images/')\ndf = pd.read_csv(os.path.join(base_image_dir, 'train.csv'))\ndf['path'] = df['id_code'].map(lambda x: os.path.join(train_dir,'{}.png'.format(x)))\ndf = df.drop(columns=['id_code'])\ndf = df.sample(frac=1).reset_index(drop=True) #shuffle dataframe\ndf.head(10)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"len_df = len(df)\nprint(f\"There are {len_df} images\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"folds = pd.read_csv('../input/atposfolds/folds.csv')","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"The images are actually quite big. We will resize to a much smaller size."},{"metadata":{"trusted":true},"cell_type":"code","source":"fold_num = 1\nval_idxs = folds[folds['folds'] == fold_num].index.values","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"bs = 64 #smaller batch size is better for training, but may take longer\nsz=256","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"tfms = get_transforms(do_flip=True, flip_vert=True, max_rotate=360, max_warp=0,\n                      max_zoom=1.1, max_lighting=0.1, p_lighting=0.5)\n\nsrc = (ImageList.from_df(df=df,path='./',cols='path')\n        .split_by_idx(val_idxs)\n        .label_from_df(cols='diagnosis', label_cls=FloatList)\n      )\n\ndata= (src.transform(tfms,size=sz,resize_method=ResizeMethod.SQUISH,padding_mode='zeros')\n       .databunch(bs=bs,num_workers=4)\n       .normalize(imagenet_stats) #Normalize     \n       )","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.metrics import cohen_kappa_score\ndef quadratic_kappa(y_hat, y):\n    return torch.tensor(cohen_kappa_score(torch.round(y_hat), y, weights='quadratic'),device='cuda:0')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"learn = cnn_learner(data, base_arch=models.resnet50, metrics = [quadratic_kappa], pretrained=False)\nlearn.load('resnet50')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"learn_2 = cnn_learner(data, base_arch=models.resnet152, metrics = [quadratic_kappa], pretrained=False)\nlearn_2.load('resnet152')","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"Inference"},{"metadata":{"trusted":true},"cell_type":"code","source":"interp = ClassificationInterpretation.from_learner(learn)\n\nlosses,idxs = interp.top_losses()\n\nlen(data.valid_ds)==len(losses)==len(idxs)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import numpy as np\nimport pandas as pd\nimport os\nimport scipy as sp\nfrom functools import partial\nfrom sklearn import metrics\nfrom collections import Counter\nimport json","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"class OptimizedRounder(object):\n    def __init__(self):\n        self.coef_ = 0\n\n    def _kappa_loss(self, coef, X, y):\n        X_p = np.copy(X)\n        for i, pred in enumerate(X_p):\n            if pred < coef[0]:\n                X_p[i] = 0\n            elif pred >= coef[0] and pred < coef[1]:\n                X_p[i] = 1\n            elif pred >= coef[1] and pred < coef[2]:\n                X_p[i] = 2\n            elif pred >= coef[2] and pred < coef[3]:\n                X_p[i] = 3\n            else:\n                X_p[i] = 4\n\n        ll = metrics.cohen_kappa_score(y, X_p, weights='quadratic')\n        return -ll\n\n    def fit(self, X, y):\n        loss_partial = partial(self._kappa_loss, X=X, y=y)\n        initial_coef = [0.5, 1.5, 2.5, 3.5]\n        self.coef_ = sp.optimize.minimize(loss_partial, initial_coef, method='nelder-mead')\n        print(-loss_partial(self.coef_['x']))\n\n    def predict(self, X, coef):\n        X_p = np.copy(X)\n        for i, pred in enumerate(X_p):\n            if pred < coef[0]:\n                X_p[i] = 0\n            elif pred >= coef[0] and pred < coef[1]:\n                X_p[i] = 1\n            elif pred >= coef[1] and pred < coef[2]:\n                X_p[i] = 2\n            elif pred >= coef[2] and pred < coef[3]:\n                X_p[i] = 3\n            else:\n                X_p[i] = 4\n        return X_p\n\n    def coefficients(self):\n        return self.coef_['x']","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"optR = OptimizedRounder()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# coefficients = optR.coefficients()\n# coefficients = [0.535809, 1.569422, 2.61038,  3.090442]\ncoefficients = [0.499944, 1.577832, 2.627495, 3.263393]\ncoefficients_2 = [0.54458,  1.570697, 2.664879, 2.892028]\n\nprint(coefficients)\nprint(coefficients_2)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Submission\nLet's now create a submission"},{"metadata":{"trusted":true},"cell_type":"code","source":"sample_df = pd.read_csv('../input/aptos2019-blindness-detection/sample_submission.csv')\nsample_df.head()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"### ResNet50"},{"metadata":{"trusted":true},"cell_type":"code","source":"learn.data.add_test(ImageList.from_df(sample_df,'../input/aptos2019-blindness-detection',folder='test_images',suffix='.png'))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"preds,y = learn.get_preds(ds_type=DatasetType.Test)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"### ResNet152"},{"metadata":{"trusted":true},"cell_type":"code","source":"learn_2.data.add_test(ImageList.from_df(sample_df,'../input/aptos2019-blindness-detection',folder='test_images',suffix='.png'))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"preds_2, y_2 = learn_2.get_preds(ds_type=DatasetType.Test)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"### Ensembling"},{"metadata":{"trusted":true},"cell_type":"code","source":"preds_avg = (preds * 0.6 + preds_2 * 0.4)\ntest_predictions = optR.predict(preds_avg, coefficients)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sample_df.diagnosis = test_predictions.astype(int)\nsample_df.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sample_df.to_csv('submission.csv',index=False)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sample_df.diagnosis.value_counts()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","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}