{"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 in \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 \"../input/\" directory.\n# For example, running this (by clicking run or pressing Shift+Enter) will list the files in the input directory\n\nimport os\nprint(os.listdir(\"../input\"))\n\n# Any results you write to the current directory are saved as output.","execution_count":null,"outputs":[]},{"metadata":{"_kg_hide-output":true,"trusted":true},"cell_type":"code","source":"!pip install imgaug --upgrade","execution_count":null,"outputs":[]},{"metadata":{"_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","trusted":true},"cell_type":"code","source":"import os, sys\nimport numpy as np\nimport pandas as pd\nimport matplotlib.pyplot as plt\nimport skimage.io\nfrom skimage.transform import resize\nfrom imgaug import augmenters as iaa\nfrom tqdm import tqdm\nimport PIL\nfrom PIL import Image, ImageOps\nimport cv2\nfrom sklearn.utils import class_weight, shuffle\nfrom keras.losses import binary_crossentropy\nfrom keras.applications.resnet50 import preprocess_input\nimport keras.backend as K\nimport tensorflow as tf\nfrom sklearn.metrics import f1_score, fbeta_score\nfrom keras.utils import Sequence\nWORKERS = 2\nCHANNEL = 3\n\nimport warnings\nwarnings.filterwarnings(\"ignore\")\nSIZE = 300\nNUM_CLASSES = 1103\nbeta_f2=2","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from keras.legacy import interfaces\nfrom keras.optimizers import Optimizer\nfrom keras import backend as K\n\n\nclass AdamAccumulate_v1(Optimizer):\n    def __init__(self, lr=0.001, beta_1=0.9, beta_2=0.999,\n                 epsilon=None, decay=0., amsgrad=False, accum_iters=20, **kwargs):\n        super(AdamAccumulate, self).__init__(**kwargs)\n        with K.name_scope(self.__class__.__name__):\n            self.iterations = K.variable(0, dtype='int64', name='iterations')\n            self.effective_iterations = K.variable(0, dtype='int64', name='effective_iterations')\n\n            self.lr = K.variable(lr, name='lr')\n            self.beta_1 = K.variable(beta_1, name='beta_1')\n            self.beta_2 = K.variable(beta_2, name='beta_2')\n            self.decay = K.variable(decay, name='decay')\n        if epsilon is None:\n            epsilon = K.epsilon()\n        self.epsilon = epsilon\n        self.initial_decay = decay\n        self.amsgrad = amsgrad\n        self.accum_iters = K.variable(accum_iters, dtype='int64')\n\n    @interfaces.legacy_get_updates_support\n    def get_updates(self, loss, params):\n        grads = self.get_gradients(loss, params)\n\n        self.updates = [K.update(self.iterations, self.iterations + 1)]\n\n        flag = K.equal(self.iterations % self.accum_iters, self.accum_iters - 1)\n        flag = K.cast(flag, K.floatx())\n\n        self.updates.append(K.update(self.effective_iterations,\n                                     self.effective_iterations + K.cast(flag, 'int64')))\n\n        lr = self.lr\n        if self.initial_decay > 0:\n            lr = lr * (1. / (1. + self.decay * K.cast(self.effective_iterations,\n                                                      K.dtype(self.decay))))\n\n        t = K.cast(self.effective_iterations, K.floatx()) + 1\n\n        lr_t = lr * (K.sqrt(1. - K.pow(self.beta_2, t)) /\n                     (1. - K.pow(self.beta_1, t)))\n\n        ms = [K.zeros(K.int_shape(p), dtype=K.dtype(p)) for p in params]\n        vs = [K.zeros(K.int_shape(p), dtype=K.dtype(p)) for p in params]\n        gs = [K.zeros(K.int_shape(p), dtype=K.dtype(p)) for p in params]\n\n        if self.amsgrad:\n            vhats = [K.zeros(K.int_shape(p), dtype=K.dtype(p)) for p in params]\n        else:\n            vhats = [K.zeros(1) for _ in params]\n        self.weights = [self.iterations] + ms + vs + vhats\n\n        for p, g, m, v, vhat, gg in zip(params, grads, ms, vs, vhats, gs):\n\n            gg_t = (1 - flag) * (gg + g)\n            m_t = (self.beta_1 * m) + (1. - self.beta_1) * (gg + flag * g) / K.cast(self.accum_iters, K.floatx())\n            v_t = (self.beta_2 * v) + (1. - self.beta_2) * K.square(\n                (gg + flag * g) / K.cast(self.accum_iters, K.floatx()))\n\n            if self.amsgrad:\n                vhat_t = K.maximum(vhat, v_t)\n                p_t = p - flag * lr_t * m_t / (K.sqrt(vhat_t) + self.epsilon)\n                self.updates.append(K.update(vhat, vhat_t))\n            else:\n                p_t = p - flag * lr_t * m_t / (K.sqrt(v_t) + self.epsilon)\n\n            self.updates.append((m, flag * m_t + (1 - flag) * m))\n            self.updates.append((v, flag * v_t + (1 - flag) * v))\n            self.updates.append((gg, gg_t))\n            new_p = p_t\n\n            # Apply constraints.\n            if getattr(p, 'constraint', None) is not None:\n                new_p = p.constraint(new_p)\n\n            self.updates.append(K.update(p, new_p))\n        return self.updates\n\n    def get_config(self):\n        config = {'lr': float(K.get_value(self.lr)),\n                  'beta_1': float(K.get_value(self.beta_1)),\n                  'beta_2': float(K.get_value(self.beta_2)),\n                  'decay': float(K.get_value(self.decay)),\n                  'epsilon': self.epsilon,\n                  'amsgrad': self.amsgrad}\n        base_config = super(AdamAccumulate, self).get_config()\n        return dict(list(base_config.items()) + list(config.items()))\n\n\nclass AdamAccumulate(Optimizer):\n    def __init__(self, lr=0.001, beta_1=0.9, beta_2=0.999,\n                 epsilon=None, decay=0., amsgrad=False, accum_iters=1, **kwargs):\n        if accum_iters < 1:\n            raise ValueError('accum_iters must be >= 1')\n        super(AdamAccumulate, self).__init__(**kwargs)\n        with K.name_scope(self.__class__.__name__):\n            self.iterations = K.variable(0, dtype='int64', name='iterations')\n            self.lr = K.variable(lr, name='lr')\n            self.beta_1 = K.variable(beta_1, name='beta_1')\n            self.beta_2 = K.variable(beta_2, name='beta_2')\n            self.decay = K.variable(decay, name='decay')\n        if epsilon is None:\n            epsilon = K.epsilon()\n        self.epsilon = epsilon\n        self.initial_decay = decay\n        self.amsgrad = amsgrad\n        self.accum_iters = K.variable(accum_iters, K.dtype(self.iterations))\n        self.accum_iters_float = K.cast(self.accum_iters, K.floatx())\n\n    @interfaces.legacy_get_updates_support\n    def get_updates(self, loss, params):\n        grads = self.get_gradients(loss, params)\n        self.updates = [K.update_add(self.iterations, 1)]\n\n        lr = self.lr\n\n        completed_updates = K.cast(K.tf.floor(self.iterations / self.accum_iters), K.floatx())\n\n        if self.initial_decay > 0:\n            lr = lr * (1. / (1. + self.decay * completed_updates))\n\n        t = completed_updates + 1\n\n        lr_t = lr * (K.sqrt(1. - K.pow(self.beta_2, t)) / (1. - K.pow(self.beta_1, t)))\n\n        # self.iterations incremented after processing a batch\n        # batch:              1 2 3 4 5 6 7 8 9\n        # self.iterations:    0 1 2 3 4 5 6 7 8\n        # update_switch = 1:        x       x    (if accum_iters=4)\n        update_switch = K.equal((self.iterations + 1) % self.accum_iters, 0)\n        update_switch = K.cast(update_switch, K.floatx())\n\n        ms = [K.zeros(K.int_shape(p), dtype=K.dtype(p)) for p in params]\n        vs = [K.zeros(K.int_shape(p), dtype=K.dtype(p)) for p in params]\n        gs = [K.zeros(K.int_shape(p), dtype=K.dtype(p)) for p in params]\n\n        if self.amsgrad:\n            vhats = [K.zeros(K.int_shape(p), dtype=K.dtype(p)) for p in params]\n        else:\n            vhats = [K.zeros(1) for _ in params]\n\n        self.weights = [self.iterations] + ms + vs + vhats\n\n        for p, g, m, v, vhat, tg in zip(params, grads, ms, vs, vhats, gs):\n\n            sum_grad = tg + g\n            avg_grad = sum_grad / self.accum_iters_float\n\n            m_t = (self.beta_1 * m) + (1. - self.beta_1) * avg_grad\n            v_t = (self.beta_2 * v) + (1. - self.beta_2) * K.square(avg_grad)\n\n            if self.amsgrad:\n                vhat_t = K.maximum(vhat, v_t)\n                p_t = p - lr_t * m_t / (K.sqrt(vhat_t) + self.epsilon)\n                self.updates.append(K.update(vhat, (1 - update_switch) * vhat + update_switch * vhat_t))\n            else:\n                p_t = p - lr_t * m_t / (K.sqrt(v_t) + self.epsilon)\n\n            self.updates.append(K.update(m, (1 - update_switch) * m + update_switch * m_t))\n            self.updates.append(K.update(v, (1 - update_switch) * v + update_switch * v_t))\n            self.updates.append(K.update(tg, (1 - update_switch) * sum_grad))\n            new_p = p_t\n\n            # Apply constraints.\n            if getattr(p, 'constraint', None) is not None:\n                new_p = p.constraint(new_p)\n\n            self.updates.append(K.update(p, (1 - update_switch) * p + update_switch * new_p))\n        return self.updates\n\n    def get_config(self):\n        config = {'lr': float(K.get_value(self.lr)),\n                  'beta_1': float(K.get_value(self.beta_1)),\n                  'beta_2': float(K.get_value(self.beta_2)),\n                  'decay': float(K.get_value(self.decay)),\n                  'epsilon': self.epsilon,\n                  'amsgrad': self.amsgrad}\n        base_config = super(AdamAccumulate, self).get_config()\n        return dict(list(base_config.items()) + list(config.items()))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Load dataset info\npath_to_train = '../input/imet-2019-fgvc6/train/'\ndata = pd.read_csv('../input/imet-2019-fgvc6/train.csv')\n\ntrain_dataset_info = []\nfor name, labels in zip(data['id'], data['attribute_ids'].str.split(' ')):\n    train_dataset_info.append({\n        'path':os.path.join(path_to_train, name),\n        'labels':np.array([int(label) for label in labels])})\ntrain_dataset_info = np.array(train_dataset_info)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"gamma = 2.0\nepsilon = K.epsilon()\ndef focal_loss(y_true, y_pred):\n    pt = y_pred * y_true + (1-y_pred) * (1-y_true)\n    pt = K.clip(pt, epsilon, 1-epsilon)\n    CE = -K.log(pt)\n    FL = K.pow(1-pt, gamma) * CE\n    loss = K.sum(FL, axis=1)\n    return loss","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sometimes = lambda aug: iaa.Sometimes(0.5, aug)\n\nclass data_generator(Sequence):\n    \n    def mix_up(x, y):\n        x = np.array(x, np.float32)\n        lam = np.random.beta(0.2, 0.4)\n        ori_index = np.arange(int(len(x)))\n        index_array = np.arange(int(len(x)))\n        np.random.shuffle(index_array)        \n        \n        mixed_x = lam * x[ori_index] + (1 - lam) * x[index_array]\n        mixed_y = lam * y[ori_index] + (1 - lam) * y[index_array]\n        \n        return mixed_x, mixed_y\n    \n    def create_train(dataset_info, batch_size, shape, augument=True, mix=False):\n        assert shape[2] == 3\n        while True:\n            dataset_info = shuffle(dataset_info)\n            for start in range(0, len(dataset_info), batch_size):\n                end = min(start + batch_size, len(dataset_info))\n                batch_images = []\n                X_train_batch = dataset_info[start:end]\n                batch_labels = np.zeros((len(X_train_batch), NUM_CLASSES))\n                for i in range(len(X_train_batch)):\n                    image = data_generator.load_image(\n                        X_train_batch[i]['path'], augument)\n                    batch_images.append(preprocess_input(image))\n                    batch_labels[i][X_train_batch[i]['labels']] = 1\n                if(mix):\n                    batch_images, batch_labels = data_generator.mix_up(batch_images, batch_labels)    \n                yield np.array(batch_images, np.float32), batch_labels\n\n    def create_valid(dataset_info, batch_size, shape, augument=False):\n        assert shape[2] == 3\n        while True:\n            # dataset_info = shuffle(dataset_info)\n            for start in range(0, len(dataset_info), batch_size):\n                end = min(start + batch_size, len(dataset_info))\n                batch_images = []\n                X_train_batch = dataset_info[start:end]\n                batch_labels = np.zeros((len(X_train_batch), NUM_CLASSES))\n                for i in range(len(X_train_batch)):\n                    image = data_generator.load_image(\n                        X_train_batch[i]['path'], augument)\n                    batch_images.append(preprocess_input(image))\n                    batch_labels[i][X_train_batch[i]['labels']] = 1\n                yield np.array(batch_images, np.float32), batch_labels\n\n    def load_image(path, augument=False):\n        image = cv2.imread(path+'.png')\n        h, w, _ = image.shape\n        image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)\n        if augument:\n            image = iaa.CropToFixedSize(height=min(SIZE*2, h),\n                            width=min(SIZE*2, w),\n                           position='uniform').augment_image(image)\n            image = data_generator.augment(image)\n        else:\n            image = iaa.CropToFixedSize(height=min(SIZE*2, h),\n                            width=min(SIZE*2, w),\n                           position='center').augment_image(image)\n        return cv2.resize(image, (SIZE, SIZE))\n\n    def augment(image):\n        augment_img = iaa.Sequential([\n        iaa.OneOf([\n            iaa.Affine(rotate=0),\n            iaa.Affine(rotate=90),\n#             iaa.Affine(rotate=180),\n#             iaa.Affine(rotate=270)\n        ]),\n        iaa.OneOf([\n            iaa.Fliplr(0.5),\n        ])], random_order=True)\n\n        image_aug = augment_img.augment_image(image)\n        return image_aug\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from keras.preprocessing.image import ImageDataGenerator\nfrom keras.models import Sequential, load_model\nfrom keras.layers import (Activation, Dropout, Flatten, Dense, GlobalMaxPooling2D,\n                          BatchNormalization, Input, Conv2D, GlobalAveragePooling2D)\nfrom keras.applications.resnet50 import ResNet50\nfrom keras.callbacks import ModelCheckpoint\nfrom keras import metrics\nfrom keras.optimizers import Adam \nfrom keras import backend as K\nimport keras\nfrom keras.models import Model","execution_count":null,"outputs":[]},{"metadata":{"_kg_hide-input":true,"trusted":true},"cell_type":"code","source":"from keras_applications import imagenet_utils as utils\n\ndef ResNet(stack_fn,\n           preact,\n           use_bias,\n           model_name='resnet',\n           include_top=True,\n           weights='imagenet',\n           input_tensor=None,\n           input_shape=None,\n           pooling=None,\n           classes=1000,\n           **kwargs):\n    \"\"\"Instantiates the ResNet, ResNetV2, and ResNeXt architecture.\n    Optionally loads weights pre-trained on ImageNet.\n    Note that the data format convention used by the model is\n    the one specified in your Keras config at `~/.keras/keras.json`.\n    # Arguments\n        stack_fn: a function that returns output tensor for the\n            stacked residual blocks.\n        preact: whether to use pre-activation or not\n            (True for ResNetV2, False for ResNet and ResNeXt).\n        use_bias: whether to use biases for convolutional layers or not\n            (True for ResNet and ResNetV2, False for ResNeXt).\n        model_name: string, model name.\n        include_top: whether to include the fully-connected\n            layer at the top of the network.\n        weights: one of `None` (random initialization),\n              'imagenet' (pre-training on ImageNet),\n              or the path to the weights file to be loaded.\n        input_tensor: optional Keras tensor\n            (i.e. output of `layers.Input()`)\n            to use as image input for the model.\n        input_shape: optional shape tuple, only to be specified\n            if `include_top` is False (otherwise the input shape\n            has to be `(224, 224, 3)` (with `channels_last` data format)\n            or `(3, 224, 224)` (with `channels_first` data format).\n            It should have exactly 3 inputs channels.\n        pooling: optional pooling mode for feature extraction\n            when `include_top` is `False`.\n            - `None` means that the output of the model will be\n                the 4D tensor output of the\n                last convolutional layer.\n            - `avg` means that global average pooling\n                will be applied to the output of the\n                last convolutional layer, and thus\n                the output of the model will be a 2D tensor.\n            - `max` means that global max pooling will\n                be applied.\n        classes: optional number of classes to classify images\n            into, only to be specified if `include_top` is True, and\n            if no `weights` argument is specified.\n    # Returns\n        A Keras model instance.\n    # Raises\n        ValueError: in case of invalid argument for `weights`,\n            or invalid input shape.\n    \"\"\"\n    global backend, layers, models, keras_utils\n    # backend, layers, models, keras_utils = get_submodules_from_kwargs(kwargs)\n    backend, layers, models, keras_utils = keras.backend, keras.layers, keras.models, keras.utils\n\n    if not (weights in {'imagenet', None} or os.path.exists(weights)):\n        raise ValueError('The `weights` argument should be either '\n                         '`None` (random initialization), `imagenet` '\n                         '(pre-training on ImageNet), '\n                         'or the path to the weights file to be loaded.')\n\n    if weights == 'imagenet' and include_top and classes != 1000:\n        raise ValueError('If using `weights` as `\"imagenet\"` with `include_top`'\n                         ' as true, `classes` should be 1000')\n\n    # Determine proper input shape\n    input_shape = utils._obtain_input_shape(input_shape,\n                                          default_size=224,\n                                          min_size=32,\n                                          data_format=backend.image_data_format(),\n                                          require_flatten=include_top,\n                                          weights=weights)\n\n    if input_tensor is None:\n        img_input = layers.Input(shape=input_shape)\n    else:\n        if not backend.is_keras_tensor(input_tensor):\n            img_input = layers.Input(tensor=input_tensor, shape=input_shape)\n        else:\n            img_input = input_tensor\n\n    bn_axis = 3 if backend.image_data_format() == 'channels_last' else 1\n\n    x = layers.ZeroPadding2D(padding=((3, 3), (3, 3)), name='conv1_pad')(img_input)\n    x = layers.Conv2D(64, 7, strides=2, use_bias=use_bias, name='conv1_conv')(x)\n\n    if preact is False:\n        x = layers.BatchNormalization(axis=bn_axis, epsilon=1.001e-5,\n                                      name='conv1_bn')(x)\n        x = layers.Activation('relu', name='conv1_relu')(x)\n\n    x = layers.ZeroPadding2D(padding=((1, 1), (1, 1)), name='pool1_pad')(x)\n    x = layers.MaxPooling2D(3, strides=2, name='pool1_pool')(x)\n\n    x = stack_fn(x)\n\n    if preact is True:\n        x = layers.BatchNormalization(axis=bn_axis, epsilon=1.001e-5,\n                                      name='post_bn')(x)\n        x = layers.Activation('relu', name='post_relu')(x)\n\n    if include_top:\n        x = layers.GlobalAveragePooling2D(name='avg_pool')(x)\n        x = layers.Dense(classes, activation='softmax', name='probs')(x)\n    else:\n        if pooling == 'avg':\n            x = layers.GlobalAveragePooling2D(name='avg_pool')(x)\n        elif pooling == 'max':\n            x = layers.GlobalMaxPooling2D(name='max_pool')(x)\n\n    # Ensure that the model takes into account\n    # any potential predecessors of `input_tensor`.\n    if input_tensor is not None:\n        inputs = keras_utils.get_source_inputs(input_tensor)\n    else:\n        inputs = img_input\n\n    # Create model.\n    model = models.Model(inputs, x, name=model_name)\n\n    # Load weights.\n    if (weights == 'imagenet') and (model_name in WEIGHTS_HASHES):\n        if include_top:\n            file_name = model_name + '_weights_tf_dim_ordering_tf_kernels.h5'\n            file_hash = WEIGHTS_HASHES[model_name][0]\n        else:\n            file_name = model_name + '_weights_tf_dim_ordering_tf_kernels_notop.h5'\n            file_hash = WEIGHTS_HASHES[model_name][1]\n        weights_path = keras_utils.get_file(file_name,\n                                            BASE_WEIGHTS_PATH + file_name,\n                                            cache_subdir='models',\n                                            file_hash=file_hash)\n        model.load_weights(weights_path)\n    elif weights is not None:\n        model.load_weights(weights)\n\n    return model","execution_count":null,"outputs":[]},{"metadata":{"_kg_hide-input":true,"trusted":true},"cell_type":"code","source":"from __future__ import absolute_import\nfrom __future__ import division\nfrom __future__ import print_function\n\ndef block2(x, filters, kernel_size=3, stride=1,\n           conv_shortcut=False, name=None):\n    \"\"\"A residual block.\n    # Arguments\n        x: input tensor.\n        filters: integer, filters of the bottleneck layer.\n        kernel_size: default 3, kernel size of the bottleneck layer.\n        stride: default 1, stride of the first layer.\n        conv_shortcut: default False, use convolution shortcut if True,\n            otherwise identity shortcut.\n        name: string, block label.\n    # Returns\n        Output tensor for the residual block.\n    \"\"\"\n    bn_axis = 3 if backend.image_data_format() == 'channels_last' else 1\n\n    preact = layers.BatchNormalization(axis=bn_axis, epsilon=1.001e-5,\n                                       name=name + '_preact_bn')(x)\n    preact = layers.Activation('relu', name=name + '_preact_relu')(preact)\n\n    if conv_shortcut is True:\n        shortcut = layers.Conv2D(4 * filters, 1, strides=stride,\n                                 name=name + '_0_conv')(preact)\n    else:\n        shortcut = layers.MaxPooling2D(1, strides=stride)(x) if stride > 1 else x\n\n    x = layers.Conv2D(filters, 1, strides=1, use_bias=False,\n                      name=name + '_1_conv')(preact)\n    x = layers.BatchNormalization(axis=bn_axis, epsilon=1.001e-5,\n                                  name=name + '_1_bn')(x)\n    x = layers.Activation('relu', name=name + '_1_relu')(x)\n\n    x = layers.ZeroPadding2D(padding=((1, 1), (1, 1)), name=name + '_2_pad')(x)\n    x = layers.Conv2D(filters, kernel_size, strides=stride,\n                      use_bias=False, name=name + '_2_conv')(x)\n    x = layers.BatchNormalization(axis=bn_axis, epsilon=1.001e-5,\n                                  name=name + '_2_bn')(x)\n    x = layers.Activation('relu', name=name + '_2_relu')(x)\n\n    x = layers.Conv2D(4 * filters, 1, name=name + '_3_conv')(x)\n    x = layers.Add(name=name + '_out')([shortcut, x])\n    return x\n\n\ndef stack2(x, filters, blocks, stride1=2, name=None):\n    \"\"\"A set of stacked residual blocks.\n    # Arguments\n        x: input tensor.\n        filters: integer, filters of the bottleneck layer in a block.\n        blocks: integer, blocks in the stacked blocks.\n        stride1: default 2, stride of the first layer in the first block.\n        name: string, stack label.\n    # Returns\n        Output tensor for the stacked blocks.\n    \"\"\"\n    x = block2(x, filters, conv_shortcut=True, name=name + '_block1')\n    for i in range(2, blocks):\n        x = block2(x, filters, name=name + '_block' + str(i))\n    x = block2(x, filters, stride=stride1, name=name + '_block' + str(blocks))\n    return x\n\ndef ResNet50V2(include_top=True,\n               weights='imagenet',\n               input_tensor=None,\n               input_shape=None,\n               pooling=None,\n               classes=1000,\n               **kwargs):\n    def stack_fn(x):\n        x = stack2(x, 64, 3, name='conv2')\n        x = stack2(x, 128, 4, name='conv3')\n        x = stack2(x, 256, 6, name='conv4')\n        x = stack2(x, 512, 3, stride1=1, name='conv5')\n        return x\n    return ResNet(stack_fn, True, True, 'resnet50v2',\n                  include_top, weights,\n                  input_tensor, input_shape,\n                  pooling, classes,\n                  **kwargs)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_kg_hide-input":true},"cell_type":"code","source":"# reference link: https://gist.github.com/drscotthawley/d1818aabce8d1bf082a6fb37137473ae\nfrom keras.callbacks import Callback\n\ndef get_1cycle_schedule(lr_max=1e-3, n_data_points=8000, epochs=200, batch_size=40, verbose=0):          \n    \"\"\"\n    Creates a look-up table of learning rates for 1cycle schedule with cosine annealing\n    See @sgugger's & @jeremyhoward's code in fastai library: https://github.com/fastai/fastai/blob/master/fastai/train.py\n    Wrote this to use with my Keras and (non-fastai-)PyTorch codes.\n    Note that in Keras, the LearningRateScheduler callback (https://keras.io/callbacks/#learningratescheduler) only operates once per epoch, not per batch\n      So see below for Keras callback\n\n    Keyword arguments:\n    lr_max            chosen by user after lr_finder\n    n_data_points     data points per epoch (e.g. size of training set)\n    epochs            number of epochs\n    batch_size        batch size\n    Output:  \n    lrs               look-up table of LR's, with length equal to total # of iterations\n    Then you can use this in your PyTorch code by counting iteration number and setting\n          optimizer.param_groups[0]['lr'] = lrs[iter_count]\n    \"\"\"\n    if verbose > 0:\n        print(\"Setting up 1Cycle LR schedule...\")\n    pct_start, div_factor = 0.3, 25.        # @sgugger's parameters in fastai code\n    lr_start = lr_max/div_factor\n    lr_end = lr_start/1e4\n    n_iter = (n_data_points * epochs // batch_size) + 1    # number of iterations\n    a1 = int(n_iter * pct_start)\n    a2 = n_iter - a1\n\n    # make look-up table\n    lrs_first = np.linspace(lr_start, lr_max, a1)            # linear growth\n    lrs_second = (lr_max-lr_end)*(1+np.cos(np.linspace(0,np.pi,a2)))/2 + lr_end  # cosine annealing\n    lrs = np.concatenate((lrs_first, lrs_second))\n    return lrs\n\n\nclass OneCycleScheduler(Callback):\n    \"\"\"My modification of Keras' Learning rate scheduler to do 1Cycle learning\n       which increments per BATCH, not per epoch\n    Keyword arguments\n        **kwargs:  keyword arguments to pass to get_1cycle_schedule()\n        Also, verbose: int. 0: quiet, 1: update messages.\n\n    Sample usage (from my train.py):\n        lrsched = OneCycleScheduler(lr_max=1e-4, n_data_points=X_train.shape[0],\n        epochs=epochs, batch_size=batch_size, verbose=1)\n    \"\"\"\n    def __init__(self, **kwargs):\n        super(OneCycleScheduler, self).__init__()\n        self.verbose = kwargs.get('verbose', 0)\n        self.lrs = get_1cycle_schedule(**kwargs)\n        self.iteration = 0\n\n    def on_batch_begin(self, batch, logs=None):\n        lr = self.lrs[self.iteration]\n        K.set_value(self.model.optimizer.lr, lr)         # here's where the assignment takes place\n        if self.verbose > 0:\n            print('\\nIteration %06d: OneCycleScheduler setting learning '\n                  'rate to %s.' % (self.iteration, lr))\n        self.iteration += 1\n\n    def on_epoch_end(self, epoch, logs=None):  # this is unchanged from Keras LearningRateScheduler\n        logs = logs or {}\n        logs['lr'] = K.get_value(self.model.optimizer.lr)\n        # self.iteration = 0\n\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from keras.regularizers import l2\n\ndef create_model(input_shape, n_out):\n    input_tensor = Input(shape=input_shape)\n    base_model = ResNet50V2(include_top=False,\n                   weights=None,\n                   input_tensor=input_tensor)\n    base_model.load_weights('../input/keras-pretrain-model-weights/resnet50v2_weights_tf_dim_ordering_tf_kernels_notop.h5')\n#     x = Conv2D(32, kernel_size=(1,1), activation='relu')(base_model.output)\n#     x = Flatten()(x)\n    x = GlobalAveragePooling2D()(base_model.output)\n    x = Dropout(0.3)(x)\n    x = Dense(1024, activation='relu')(x)\n    x = Dropout(0.3)(x)\n#     x = Dense(1024, activation='relu')(x)\n#     x = Dropout(0.3)(x)\n    final_output = Dense(n_out, activation='sigmoid', name='final_output')(x)\n    model = Model(input_tensor, final_output)\n    \n    return model","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# create callbacks list\nfrom keras.callbacks import (ModelCheckpoint, LearningRateScheduler,\n                             EarlyStopping, ReduceLROnPlateau,CSVLogger)\n                             \nfrom sklearn.model_selection import train_test_split\n\nepochs = 20; batch_size = 64\ncheckpoint = ModelCheckpoint('../working/Resnet50_focal.h5', monitor='val_loss', verbose=1, \n                             save_best_only=True, mode='min', save_weights_only = True)\nreduceLROnPlat = ReduceLROnPlateau(monitor='val_loss', factor=0.5, patience=2, \n                                   verbose=1, mode='auto', epsilon=0.0001)\nearly = EarlyStopping(monitor=\"val_loss\", \n                      mode=\"min\", \n                      patience=7)\n\ncsv_logger = CSVLogger(filename='../working/training_log.csv',\n                       separator=',',\n                       append=True)\n\n\n# split data into train, valid\nindexes = np.arange(train_dataset_info.shape[0])\ntrain_indexes, valid_indexes = train_test_split(indexes, test_size=0.15, random_state=8)\n\n# create train and valid datagens\ntrain_generator = data_generator.create_train(\n    train_dataset_info[train_indexes], batch_size, (SIZE,SIZE,3), augument=True, mix=False)\ntrain_mixup = data_generator.create_train(\n    train_dataset_info[train_indexes], batch_size, (SIZE,SIZE,3), augument=True, mix=True)\ntrain_generator_warmup = data_generator.create_train(\n    train_dataset_info[train_indexes], batch_size, (SIZE,SIZE,3), augument=False)\nvalidation_generator = data_generator.create_valid(\n    train_dataset_info[valid_indexes], batch_size, (SIZE,SIZE,3), augument=False)\n\nlrsched = OneCycleScheduler(lr_max=1e-3, n_data_points=len(train_indexes),\n        epochs=epochs, batch_size=batch_size, verbose=0)\n# callbacks_list = [checkpoint, csv_logger, lrsched]\ncallbacks_list = [checkpoint, csv_logger, reduceLROnPlat]\n# callbacks_list = [checkpoint, csv_logger]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import matplotlib.pyplot as plt\n    \nlrs = get_1cycle_schedule(lr_max=1e-3, n_data_points=len(train_indexes), epochs=20, batch_size=64, verbose=0)\nepoch_list = np.linspace(0,epochs,len(lrs))\nplt.plot(epoch_list,lrs)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model = create_model(\n    input_shape=(SIZE,SIZE,3), \n    n_out=NUM_CLASSES)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# warm up model\nfor layer in model.layers:\n    layer.trainable = False\n\nfor i in range(-3,0):\n    model.layers[i].trainable = True\n\nmodel.compile(\n    loss='binary_crossentropy',\n    optimizer=Adam(1e-3))\n    # optimizer=AdamAccumulate(lr=1e-3, accum_iters=2))\n\nmodel.fit_generator(\n    train_generator_warmup,\n    steps_per_epoch=np.ceil(float(len(train_indexes)) / float(batch_size)),\n    epochs=2,\n    max_queue_size=16, workers=WORKERS, use_multiprocessing=True,\n    verbose=1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# train all layers\nfor layer in model.layers:\n    layer.trainable = True\n\ncallbacks_list = [checkpoint, csv_logger, lrsched]\nmodel.compile(loss='binary_crossentropy',\n            # loss=focal_loss,\n            optimizer=Adam(lr=1e-3,decay=3e-4))\n            # optimizer=AdamAccumulate(lr=2e-4, accum_iters=2))\n\nmodel.fit_generator(\n    # train_generator,\n    train_mixup,\n    steps_per_epoch=np.ceil(float(len(train_indexes)) / float(batch_size)),\n    validation_data=validation_generator,\n    validation_steps=np.ceil(float(len(valid_indexes)) / float(batch_size)),\n    epochs=epochs,\n    verbose=1,\n    max_queue_size=16, workers=WORKERS, use_multiprocessing=True,\n    callbacks=callbacks_list)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# model.compile(loss='binary_crossentropy',\n#             # loss=focal_loss,\n#             optimizer=Adam(lr=1e-4))\n#             # optimizer=AdamAccumulate(lr=1e-4, accum_iters=4))\n\n# callbacks_list = [checkpoint, csv_logger, reduceLROnPlat]\n\n# model.fit_generator(\n#     train_generator,\n#     steps_per_epoch=np.ceil(float(len(train_indexes)) / float(batch_size)),\n#     validation_data=validation_generator,\n#     validation_steps=np.ceil(float(len(valid_indexes)) / float(batch_size)),\n#     epochs=epochs,\n#     verbose=1,\n#     max_queue_size=16, workers=WORKERS, use_multiprocessing=True,\n#     callbacks=callbacks_list)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print(os.listdir('../working/'))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"submit = pd.read_csv('../input/imet-2019-fgvc6/sample_submission.csv')\nmodel.load_weights('../working/Resnet50_focal.h5')\npredicted = []","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"'''Search for the best threshold regarding the validation set'''\n\nBATCH = 512\nfullValGen = data_generator.create_valid(\n    train_dataset_info[valid_indexes], BATCH, (SIZE,SIZE,3))\n\nn_val = round(train_dataset_info.shape[0]*0.15)//BATCH\nprint(n_val)\n\nlastFullValPred = np.empty((0, NUM_CLASSES))\nlastFullValLabels = np.empty((0, NUM_CLASSES))\nfor i in tqdm(range(n_val+1)): \n    im, lbl = next(fullValGen)\n    scores = model.predict(im)\n    lastFullValPred = np.append(lastFullValPred, scores, axis=0)\n    lastFullValLabels = np.append(lastFullValLabels, lbl, axis=0)\nprint(lastFullValPred.shape, lastFullValLabels.shape)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def my_f2(y_true, y_pred):\n    assert y_true.shape[0] == y_pred.shape[0]\n\n    tp = np.sum((y_true == 1) & (y_pred == 1), axis=1)\n    tn = np.sum((y_true == 0) & (y_pred == 0), axis=1)\n    fp = np.sum((y_true == 0) & (y_pred == 1), axis=1)\n    fn = np.sum((y_true == 1) & (y_pred == 0), axis=1)\n\n    p = tp / (tp + fp + K.epsilon())\n    r = tp / (tp + fn + K.epsilon())\n\n    f2 = (1+beta_f2**2)*p*r / (p*beta_f2**2 + r + 1e-15)\n\n    return np.mean(f2)\n\ndef find_best_fixed_threshold(preds, targs, do_plot=True):\n    score = []\n    thrs = np.arange(0, 0.5, 0.01)\n    for thr in tqdm(thrs):\n        score.append(my_f2(targs, (preds > thr).astype(int) ))\n    score = np.array(score)\n    pm = score.argmax()\n    best_thr, best_score = thrs[pm], score[pm].item()\n    print(f'thr={best_thr:.3f}', f'F2={best_score:.3f}')\n    if do_plot:\n        plt.plot(thrs, score)\n        plt.vlines(x=best_thr, ymin=score.min(), ymax=score.max())\n        plt.text(best_thr+0.03, best_score-0.01, f'$F_{2}=${best_score:.3f}', fontsize=14);\n        plt.show()\n    return best_thr, best_score","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"best_thr, best_score = find_best_fixed_threshold(lastFullValPred, lastFullValLabels, do_plot=True)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# for i, name in tqdm(enumerate(submit['id'])):\n#     path = os.path.join('../input/imet-2019-fgvc6/test/', name)\n#     image = data_generator.load_image(path, (SIZE,SIZE,3))\n#     score_predict = model.predict(preprocess_input(image[np.newaxis]))\n#     # score_predict = model.predict((image[np.newaxis])/255)\n#     # print(score_predict)\n#     label_predict = np.arange(NUM_CLASSES)[score_predict[0]>=best_thr]\n#     # print(label_predict)\n#     str_predict_label = ' '.join(str(l) for l in label_predict)\n#     predicted.append(str_predict_label)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# submit['attribute_ids'] = predicted\n# submit.to_csv('submission.csv', index=False)","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}