{"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\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 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 5GB 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":"import pandas as pd\nfrom tensorflow.keras.applications.mobilenet import MobileNet, preprocess_input\nfrom pydicom import dcmread\nimport cv2\nimport numpy as np\nfrom sklearn.svm import SVC\nfrom sklearn import metrics\n\n\nProject_path ='../input/rsna-pneumonia-detection-challenge/'\n\nTrain_Image_path = Project_path + 'stage_2_train_images/'\n\nTrain_Lables= pd.read_csv('../input/rsna-pneumonia-detection-challenge/stage_2_train_labels.csv')\n\nTrain_Lables.head()\n\npatient_id = Train_Lables['patientId'].values.tolist()\nTarget_Label = Train_Lables['Target'].values.tolist()\nlen(Target_Label)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from tensorflow.keras.models import Sequential\nfrom tensorflow.keras.layers import ZeroPadding2D, Convolution2D, MaxPooling2D, Dropout, Flatten, Activation\n\ndef vgg_face():\t\n    model = Sequential()\n    model.add(ZeroPadding2D((1,1),input_shape=(224,224, 3)))\n    model.add(Convolution2D(64, (3, 3), activation='relu'))\n    model.add(ZeroPadding2D((1,1)))\n    model.add(Convolution2D(64, (3, 3), activation='relu'))\n    model.add(MaxPooling2D((2,2), strides=(2,2)))\n    \n    model.add(ZeroPadding2D((1,1)))\n    model.add(Convolution2D(128, (3, 3), activation='relu'))\n    model.add(ZeroPadding2D((1,1)))\n    model.add(Convolution2D(128, (3, 3), activation='relu'))\n    model.add(MaxPooling2D((2,2), strides=(2,2)))\n    \n    model.add(ZeroPadding2D((1,1)))\n    model.add(Convolution2D(256, (3, 3), activation='relu'))\n    model.add(ZeroPadding2D((1,1)))\n    model.add(Convolution2D(256, (3, 3), activation='relu'))\n    model.add(ZeroPadding2D((1,1)))\n    model.add(Convolution2D(256, (3, 3), activation='relu'))\n    model.add(MaxPooling2D((2,2), strides=(2,2)))\n    \n    model.add(ZeroPadding2D((1,1)))\n    model.add(Convolution2D(512, (3, 3), activation='relu'))\n    model.add(ZeroPadding2D((1,1)))\n    model.add(Convolution2D(512, (3, 3), activation='relu'))\n    model.add(ZeroPadding2D((1,1)))\n    model.add(Convolution2D(512, (3, 3), activation='relu'))\n    model.add(MaxPooling2D((2,2), strides=(2,2)))\n    \n    model.add(ZeroPadding2D((1,1)))\n    model.add(Convolution2D(512, (3, 3), activation='relu'))\n    model.add(ZeroPadding2D((1,1)))\n    model.add(Convolution2D(512, (3, 3), activation='relu'))\n    model.add(ZeroPadding2D((1,1)))\n    model.add(Convolution2D(512, (3, 3), activation='relu'))\n    model.add(MaxPooling2D((2,2), strides=(2,2)))\n    \n    model.add(Convolution2D(4096, (7, 7), activation='relu'))\n    model.add(Dropout(0.5))\n    model.add(Convolution2D(4096, (1, 1), activation='relu'))\n    model.add(Dropout(0.5))\n    model.add(Convolution2D(2622, (1, 1)))\n    model.add(Flatten())\n    model.add(Activation('softmax'))\n    return model","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"patients=len(patient_id)\n\nTrain_Data=[]\nVal_Data=[]\n\nTrain_Lables=[]\nVal_Labels=[]\n\n\nfor i in range(patients):\n    Image_name = Train_Image_path + patient_id[i] +'.dcm'\n    Image=dcmread(Image_name)\n    rs = cv2.resize(Image.pixel_array,(224,224))\n    print(i)\n    if i<24182:\n        Train_Data.append(rs)\n        Train_Lables.append(Target_Label[i])\n        \n    else:\n        Val_Data.append(rs)\n        Val_Labels.append(Target_Label[i])\n        ","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print(len(Train_Lables))\nprint(len(Val_Labels))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import numpy as np\ndef Batch_Generator_Train(Batch_no):\n    Batch_Size= 226\n    batch_images_train = np.zeros((Batch_Size, 224, 224, 3), dtype=np.float32)\n\n    Batch_no = Batch_no\n    batch_index_initializer= Batch_no * 226\n\n    for i in range(0,225):\n        batch_images_train[i][:,:,0]= preprocess_input(np.array(Train_Data[i+batch_index_initializer], dtype=np.float32))\n        batch_images_train[i][:,:,1]= preprocess_input(np.array(Train_Data[i+batch_index_initializer], dtype=np.float32))\n        batch_images_train[i][:,:,2]= preprocess_input(np.array(Train_Data[i+batch_index_initializer], dtype=np.float32))\n    return batch_images_train\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def Val_Data_Generator(Batch_no):\n    Batch_Size=195\n    batch_images_val = np.zeros((Batch_Size, 224, 224, 3), dtype=np.float32)\n    Batch_no = Batch_no\n    batch_index_initializer= Batch_no * 195\n    for i in range(0,194):\n        batch_images_val[i][:,:,0]= preprocess_input(np.array(Val_Data[i+batch_index_initializer], dtype=np.float32))\n        batch_images_val[i][:,:,1]= preprocess_input(np.array(Val_Data[i+batch_index_initializer], dtype=np.float32))\n        batch_images_val[i][:,:,2]= preprocess_input(np.array(Val_Data[i+batch_index_initializer], dtype=np.float32))\n        \n    return batch_images_val","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def Label_Generator_Train(Batch_no):\n    Batch_size=226\n    index_initializer = Batch_no * Batch_size\n    Start_index = index_initializer - Batch_size\n    End_index = Start_index + Batch_size\n    Batch_Label_train=Train_Lables[Start_index:End_index]\n    return Batch_Label_train\n    ","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def Label_Generator_Val(Batch_no):\n    Batch_size=195\n    index_initializer = Batch_no * Batch_size\n    Start_index = index_initializer - Batch_size\n    End_index = Start_index + Batch_size\n    Batch_Label_val=Val_Labels[Start_index:End_index]\n    return Batch_Label_val\n    ","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model = vgg_face()\nfrom tensorflow.keras.models import Model\nvgg_face_descriptor = Model(inputs=model.layers[0].input, outputs=model.layers[-2].output)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def Generate_Embeddings_Train(batch_images_train):\n    embeddings=[]\n    for i in range(0,226):\n        embedding_vector = vgg_face_descriptor.predict(np.expand_dims(batch_images_train[i], axis=0))[0]\n        embeddings.append(embedding_vector)\n    return embeddings","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def Generate_Embeddings_Val(batch_images_val):\n    embeddings=[]\n    for i in range(0,195):\n        embedding_vector = vgg_face_descriptor.predict(np.expand_dims(batch_images_val[i], axis=0))[0]\n        embeddings.append(embedding_vector)\n    return embeddings","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Training \nclassifier= SVC(kernel='rbf')\nfor i in range(1,10):\n    print(\"Training Batch ->\",i)\n    X=Batch_Generator_Train(i)\n    \n    X_train=Generate_Embeddings_Train(X)\n    \n    X_train=np.array(X_train)\n    \n    y_train=Label_Generator_Train(i)\n    \n    #SVM\n    classifier.fit(X_train,y_train)\n    ","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X=Val_Data_Generator(2)\n    \nX_val=Generate_Embeddings_Val(X)\n    \nX_val=np.array(X_val)\n    \ny_val=Label_Generator_Val(2)\n    \ny_pred_train=classifier.predict(X_train)\ny_pred_val=classifier.predict(X_val)\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print(\"Train_Accuracy=\",metrics.accuracy_score(y_train,y_pred_train))\nprint(\"Val_Accuracy=\",metrics.accuracy_score(y_val,y_pred_val))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"\n","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}