{"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 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":{"trusted":true},"cell_type":"code","source":"import pandas as pd\nimport numpy as np\nimport matplotlib.pyplot as plt\n%matplotlib inline","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"import pandas as pd\nimport seaborn as sns\nimport matplotlib.pyplot as plt \nimport plotly.express as px\nimport os\nimport cv2\nfrom PIL import Image\nimport keras\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.metrics import accuracy_score\nimport tensorflow as tf\nfrom tensorflow.keras import models, layers\nfrom tensorflow.keras.preprocessing import image\nfrom tensorflow.keras.preprocessing.image import ImageDataGenerator\nfrom tensorflow.keras.callbacks import ModelCheckpoint, EarlyStopping, ReduceLROnPlateau\nfrom tensorflow.keras.applications import EfficientNetB0, Xception\nfrom tensorflow.keras.optimizers import Adam","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"input_dir = \"../input/d-tribe-hackathon-2020\"\n\ntrain_images_path = os.path.join(input_dir,\"train_images\")\ntest_images_path = os.path.join(input_dir,'test_images')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_map=pd.read_csv(r'../input/d-tribe-hackathon-2020/train/train map.csv')\ntrain_map.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sample=pd.read_csv(r'../input/d-tribe-hackathon-2020/sample submission.csv')\nsample.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print(train_map.shape)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"image_list = train_map['IMAGE'].to_list()\nlabel_list = train_map['LABEL'].to_list()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"data_dir = '../input/d-tribe-hackathon-2020'","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import torch\nfrom torch import nn, optim\nimport numpy as np\nimport os\nfrom torchvision import datasets, models, transforms\nfrom torch.utils.data.sampler import SubsetRandomSampler\nfrom collections import OrderedDict\nimport matplotlib.pyplot as plt\nfrom glob import glob\nfrom PIL import Image\nimport matplotlib.image as mpimg","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"data_transforms = {\n    'train': transforms.Compose([\n        transforms.RandomRotation(45),\n        transforms.RandomResizedCrop(224),\n        transforms.RandomHorizontalFlip(),\n        transforms.ToTensor(),\n        transforms.Normalize([0.485, 0.456, 0.406],\n                            [0.229, 0.224, 0.225])\n    ]),\n    'valid': transforms.Compose([\n        transforms.Resize(224 + 32),\n        transforms.CenterCrop(224),\n        transforms.ToTensor(),\n        transforms.Normalize([0.485, 0.456, 0.406],\n                             [0.229, 0.224, 0.225])\n    ])\n}\n\nimage_datasets=dict()\nimage_datasets['train']=datasets.ImageFolder(data_dir,transform=data_transforms['train'])\nimage_datasets['valid']=datasets.ImageFolder(data_dir,transform=data_transforms['valid'])\n\n# number of subprocesses to use for data loading\nnum_workers = 0\n# how many samples per batch to load\nbatch_size = 20\n# percentage of training set to use as validation\nvalid_size = 0.2\n\n\n# obtain training indices to use for validation\nnum_train = len(image_datasets['train'])\nindices = list(range(num_train))\nnp.random.shuffle(indices)\nsplit = int(np.floor(valid_size * num_train))\ntrain_idx, valid_idx = indices[split:], indices[:split]\n\n# define samplers for obtaining training and validation batches\ntrain_sampler = SubsetRandomSampler(train_idx)\nvalid_sampler = SubsetRandomSampler(valid_idx)\n\n# create dataloaders\ntrain_loader = torch.utils.data.DataLoader(image_datasets['train'], batch_size=batch_size, sampler=train_sampler, num_workers=num_workers)\nvalid_loader = torch.utils.data.DataLoader(image_datasets['valid'], batch_size=batch_size, sampler=valid_sampler, num_workers=num_workers)\ndataloaders = {}\ndataloaders['train'] = train_loader\ndataloaders['valid'] = valid_loader\ndataset_sizes = {x: len(image_datasets[x]) for x in ['train', 'valid']}\n\n\n# specify class names\nclass_names = image_datasets['train'].classes","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# helper function to un-normalize and display image\ndef imshow(img):\n  img = img / 2 + 0.5\n  plt.imshow(np.transpose(img, (1, 2, 0))) #convert from tensor image\n\n# obtain one batch of training images\ndataiter = iter(train_loader)\nimages, labels = dataiter.next()\nimages = images.numpy()\n\n# plot the images in batch with their labels\nfig = plt.figure(figsize=(25, 2))\n# display 20 images\nfor idx in np.arange(20):\n  ax = fig.add_subplot(2, 20/2, idx+1, xticks=[], yticks=[])\n  imshow(images[idx])\n # ax.set_title(class_names[labels[idx]])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n\nimport os\nimport matplotlib.pyplot as plt\n\nimport tensorflow as tf\nimport keras\nfrom keras.models import Sequential\nfrom keras.layers import Dense, Dropout, Flatten\nfrom keras.layers import Conv2D, MaxPooling2D\nfrom keras.utils import to_categorical\nfrom keras.preprocessing import image\nimport numpy as np\nimport pandas as pd\nimport matplotlib.pyplot as plt\nfrom sklearn.model_selection import train_test_split\nfrom tqdm import tqdm\n%matplotlib inline","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_map.columns","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n\nimport os\nimport matplotlib.pyplot as plt\n\nimport tensorflow as tf#Clear any previous model from memory\ntf.keras.backend.clear_session()\n\n#Initialize model\nmodel = tf.keras.models.Sequential()\n\n#normalize data\nmodel.add(tf.keras.layers.InputLayer(input_shape=(image_size,image_size,3,)))\n\n#Add Conv Layer\nmodel.add(tf.keras.layers.Conv2D(64, kernel_size=(3,3),strides = (2,2), activation='relu'))\n\n#normalize data\nmodel.add(tf.keras.layers.BatchNormalization())\n\n#Add Conv Layer\nmodel.add(tf.keras.layers.Conv2D(64, kernel_size=(3,3), strides = (1,1), activation='relu'))\n\n#Add Max Pool layer\nmodel.add(tf.keras.layers.MaxPool2D(pool_size = (2,2)))\n\n#normalize data\nmodel.add(tf.keras.layers.BatchNormalization())\n\n#Add Conv Layer\nmodel.add(tf.keras.layers.Conv2D(128, kernel_size=(3,3), strides = (1,1), activation='relu'))\n\n#Add Max Pool layer\nmodel.add(tf.keras.layers.MaxPool2D(pool_size = (3,3)))\n\n#normalize data\nmodel.add(tf.keras.layers.BatchNormalization())\n\n#Add Max Pool layer\nmodel.add(tf.keras.layers.GlobalMaxPool2D())\n\n#Add Dense Layers after flattening the data\nmodel.add(tf.keras.layers.Flatten())\n\nmodel.add(tf.keras.layers.Dense(256, activation='relu'))\n\n#Add Dropout\nmodel.add(tf.keras.layers.Dropout(0.5))\n\nmodel.add(tf.keras.layers.Dense(256, activation='relu'))\n\n#Add Dropout\nmodel.add(tf.keras.layers.Dropout(0.4))\n\n#Add Output Layer\nmodel.add(tf.keras.layers.Dense(12, activation='softmax'))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def prepareImages(data, m, dataset):\n    print(\"Preparing images\")\n    X_train = np.zeros((m, 100, 100, 3))\n    count = 0\n    \n    for fig in data['IMAGE']:\n        #load images into images of size 100x100x3\n        img = image.load_img(\"../input/d-tribe-hackathon-2020\"+dataset+\"/\"+fig, target_size=(100, 100, 3))\n        x = image.img_to_array(img)\n        x = preprocess_input(x)\n\n        X_train[count] = x\n        if (count%500 == 0):\n            print(\"Processing image: \", count+1, \", \", fig)\n        count += 1\n    \n    return X_train","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"base_path = \"/kaggle/input/d-tribe-hackathon-2020/\"\ntrain = base_path + \"train/train\"\ntest = base_path + \"test\"","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from skimage.io import imread\n# loading training images\ntrain_img = []\nfor img_name in tqdm(train_map['IMAGE']):\n    # defining the image path\n    image_path = './training_dataset' + str(img_name) \n    # reading the image\n    img = imread(image_path, as_gray=True)\n    # normalizing the pixel values\n    img /= 255.0\n    # converting the type of pixel to float 32\n    img = img.astype('float32')\n    # appending the image into the list\n    train_img.append(img)\n\n# converting the list to numpy array\ntrain_x = np.array(train_img)\n# defining the target\ntrain_y = train['label'].values\ntrain_x.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","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}