{"cells":[{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"from fastai import *\nfrom fastai.vision import *\nimport numpy as np\nimport scipy as sp\nfrom sklearn import metrics\nimport cv2\nimport PIL","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"path = Path('/kaggle/input/aptos2019-blindness-detection')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"path.ls()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df = pd.read_csv(path/'train.csv')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df.diagnosis.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df.diagnosis.value_counts()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def crop_image1(img,tol=7):\n    # img is image data\n    # tol  is tolerance\n        \n    mask = img>tol\n    return img[np.ix_(mask.any(1),mask.any(0))]\n\ndef crop_image_from_gray(img,tol=7):\n    if img.ndim ==2:\n        mask = img>tol\n        return img[np.ix_(mask.any(1),mask.any(0))]\n    elif img.ndim==3:\n        gray_img = cv2.cvtColor(img, cv2.COLOR_RGB2GRAY)\n        mask = gray_img>tol\n        \n        check_shape = img[:,:,0][np.ix_(mask.any(1),mask.any(0))].shape[0]\n        if (check_shape == 0): # image is too dark so that we crop out everything,\n            return img # return original image\n        else:\n            img1=img[:,:,0][np.ix_(mask.any(1),mask.any(0))]\n            img2=img[:,:,1][np.ix_(mask.any(1),mask.any(0))]\n            img3=img[:,:,2][np.ix_(mask.any(1),mask.any(0))]\n    #         print(img1.shape,img2.shape,img3.shape)\n            img = np.stack([img1,img2,img3],axis=-1)\n    #         print(img.shape)\n        return img\n\ndef load_ben_color(path, sigmaX=10):\n    image = cv2.imread(path)\n    image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)\n    image = crop_image_from_gray(image)\n    image = cv2.resize(image, (IMG_SIZE, IMG_SIZE))\n    image=cv2.addWeighted ( image,4, cv2.GaussianBlur( image , (0,0) , sigmaX) ,-4 ,128)\n        \n    return image","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"IMG_SIZE = 512\n\ndef _load_format(path, convert_mode, after_open)->Image:\n    image = cv2.imread(path)\n    image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)\n    image = crop_image_from_gray(image)\n    image = cv2.resize(image, (IMG_SIZE, IMG_SIZE))\n    image=cv2.addWeighted ( image,4, cv2.GaussianBlur( image , (0,0), 10) ,-4 ,128)\n                    \n    return Image(pil2tensor(image, np.float32).div_(255)) #return fastai Image format\n\nvision.data.open_image = _load_format\n    \nsrc = (\n    ImageList.from_df(df,path,folder='train_images',suffix='.png')\n        .split_by_rand_pct(0.2, seed=42)\n        .label_from_df(cols='diagnosis',label_cls=FloatList)    \n    )\nsrc","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"!ls ../input/resnet152/","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"Path('/tmp/.cache/torch/checkpoints/').mkdir(exist_ok=True, parents=True)\n!cp '../input/resnet152/resnet152.pth' '/tmp/.cache/torch/checkpoints/resnet152-b121ed2d.pth'","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"tfms = get_transforms(do_flip=True, flip_vert=True,max_warp=0., xtra_tfms =[crop_pad(),symmetric_warp()])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"data = (\n    src.transform(tfms,size=128)\n    .databunch()\n    .normalize(imagenet_stats)\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')\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"learn = cnn_learner(data,models.resnet152,metrics=[quadratic_kappa],model_dir='/kaggle',pretrained=True)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"learn.lr_find()\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"learn.recorder.plot()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"lr=1e-2\nlearn.fit_one_cycle(3,lr)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"learn.data = data = (src.transform(tfms,size=256).databunch().normalize(imagenet_stats))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"learn.lr_find()\nlearn.recorder.plot()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"learn.fit_one_cycle(5,max_lr=slice(1e-4))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"learn.unfreeze()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"learn.lr_find()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"learn.recorder.plot()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"learn.fit_one_cycle(5,max_lr=9e-04)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"valid_preds = learn.get_preds(ds_type = DatasetType.Valid)","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()\noptR.fit(valid_preds[0],valid_preds[1])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"coefficients = optR.coefficients()\nprint(coefficients)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sample_df = pd.read_csv(path/'sample_submission.csv')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sample_df.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"learn.data.add_test(ImageList.from_df(sample_df,path,folder='test_images',suffix='.png'))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"preds,y = learn.get_preds(DatasetType.Test)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_predictions = optR.predict(preds,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":{"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":1}