{"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_minor":4,"nbformat":4,"cells":[{"cell_type":"markdown","source":"## (In Progress)","metadata":{}},{"cell_type":"markdown","source":"\n# Hello everybody! As a basis I used this incredible notebook: https://www.kaggle.com/ks2019/happywhale-arcface-baseline-tpu\n\n# In this notebook, I used EfficientNetB6 as the base model. \n# In the original notebook, we made predictions using only one model trained on one fold. I changed the original code and now we make predictions based on 5 trained models. I trained each model separately, because it's the fastest.\n# The use of 5 models increased the accuracy by about 5%, which is a great result","metadata":{}},{"cell_type":"markdown","source":"### Note: The code is setup in a way that you can easily run the notebook on colab with minimal changes\n### TFRecords Dataset: https://www.kaggle.com/ks2019/happywhale-tfrecords-v1\n### Code for generating TFRecords: https://www.kaggle.com/ks2019/happywhale-tfrecords","metadata":{}},{"cell_type":"markdown","source":"\nVersion changes:\n\nVersion 1: Quick Save (I always forget about the settings for TPU:-))\n\nVersion 2: (EFF_NET = 6, KNN = 50, Public Score=0.583)\n\nVersion 3: Quick Save (I always forget about the settings for TPU:-))\n\nVersion 4: (EFF_NET = 6, KNN = 100, Public Score=0.584)\n\nVersion 5: (EFF_NET = 6, KNN = 200, Public Score=0.583)\n\nVersion 6: Quick Save (I always forget about the settings for TPU:-))\n\nVersion 7: (EFF_NET = 5, KNN = 200, Public Score=0.586)\n\nVersion 8: Quick Save :-)\n\nVersion 9: ................\n\nVersion 10: (EFF_NET = 5, KNN = 100, IMAGE_SIZE = 768, Public Score=)","metadata":{}},{"cell_type":"code","source":"import os\nIS_COLAB = not os.path.exists('/kaggle/input')\nprint(IS_COLAB) ","metadata":{"execution":{"iopub.status.busy":"2022-02-23T19:35:33.936849Z","iopub.execute_input":"2022-02-23T19:35:33.937136Z","iopub.status.idle":"2022-02-23T19:35:33.942524Z","shell.execute_reply.started":"2022-02-23T19:35:33.937109Z","shell.execute_reply":"2022-02-23T19:35:33.941547Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import tensorflow as tf\ntry:\n    # TPU detection. No parameters necessary if TPU_NAME environment variable is\n    # set: this is always the case on Kaggle.\n    tpu = tf.distribute.cluster_resolver.TPUClusterResolver()\n    print('Running on TPU ', tpu.master())\nexcept ValueError:\n    tpu = None\n\nif tpu:\n    tf.config.experimental_connect_to_cluster(tpu)\n    tf.tpu.experimental.initialize_tpu_system(tpu)\n    strategy = tf.distribute.TPUStrategy(tpu)\nelse:\n    # Default distribution strategy in Tensorflow. Works on CPU and single GPU.\n    strategy = tf.distribute.get_strategy()\n\nAUTO = tf.data.experimental.AUTOTUNE\nprint(\"REPLICAS: \", strategy.num_replicas_in_sync)","metadata":{"execution":{"iopub.status.busy":"2022-02-23T19:35:33.944602Z","iopub.execute_input":"2022-02-23T19:35:33.945414Z","iopub.status.idle":"2022-02-23T19:35:33.956377Z","shell.execute_reply.started":"2022-02-23T19:35:33.945264Z","shell.execute_reply":"2022-02-23T19:35:33.955541Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"if IS_COLAB:\n  from google.colab import drive\n  drive.mount('/content/drive')\nelse:\n  from kaggle_datasets import KaggleDatasets","metadata":{"execution":{"iopub.status.busy":"2022-02-23T19:35:33.958144Z","iopub.execute_input":"2022-02-23T19:35:33.958571Z","iopub.status.idle":"2022-02-23T19:35:33.965689Z","shell.execute_reply.started":"2022-02-23T19:35:33.958535Z","shell.execute_reply":"2022-02-23T19:35:33.964775Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"!pip install -q efficientnet\n!pip install tensorflow_addons\nimport re\nimport os\nimport numpy as np\nimport pandas as pd\nimport random\nimport math\nimport tensorflow as tf\nimport efficientnet.tfkeras as efn\nfrom sklearn import metrics\nfrom sklearn.model_selection import KFold, train_test_split\nfrom tensorflow.keras import backend as K\nimport tensorflow_addons as tfa\nfrom tqdm.auto import tqdm\nimport matplotlib.pyplot as plt\nimport pickle\nimport json\nimport tensorflow_hub as tfhub\nfrom datetime import datetime","metadata":{"execution":{"iopub.status.busy":"2022-02-23T19:35:33.967370Z","iopub.execute_input":"2022-02-23T19:35:33.968667Z","iopub.status.idle":"2022-02-23T19:35:47.208603Z","shell.execute_reply.started":"2022-02-23T19:35:33.968629Z","shell.execute_reply":"2022-02-23T19:35:47.207754Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Config","metadata":{}},{"cell_type":"code","source":"save_dir = '.'\nEXPERIMENT = 0\nrun_ts = datetime.now().strftime('%Y%m%d-%H%M%S')\nprint(run_ts)\nif IS_COLAB:\n    save_dir = f'/content/drive/MyDrive/Kaggle/HappyWhale-2022/experiments-{EXPERIMENT}/{run_ts}'\n    !mkdir -p {save_dir}","metadata":{"execution":{"iopub.status.busy":"2022-02-23T19:35:47.211497Z","iopub.execute_input":"2022-02-23T19:35:47.211732Z","iopub.status.idle":"2022-02-23T19:35:47.218143Z","shell.execute_reply.started":"2022-02-23T19:35:47.211708Z","shell.execute_reply":"2022-02-23T19:35:47.217080Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"class config:\n    \n    \n    SEED = 42\n    FOLD_TO_RUN = 0#In this notebook, we do not train models \n    FOLDS = 5\n    DEBUG = False\n    EVALUATE = True\n    RESUME = False\n    RESUME_EPOCH = None\n    \n    \n    ### Dataset\n    BATCH_SIZE = 32 * strategy.num_replicas_in_sync\n    IMAGE_SIZE = 128\n    N_CLASSES = 15587\n    \n    ### Model\n    model_type = 'effnetv1'  \n    EFF_NET = 5\n    EFF_NETV2 = 's-21k-ft1k'\n    FREEZE_BATCH_NORM = False\n    head = 'arcface' \n    EPOCHS = 20\n    LR = 0.001\n    message='baseline'\n    \n    ### Augmentations\n    CUTOUT = False\n    \n    ### Save-Directory\n    save_dir = save_dir\n    \n    ### Inference\n    KNN = 1000\n    \ndef count_data_items(filenames):\n    n = [int(re.compile(r\"-([0-9]*)\\.\").search(filename).group(1)) \n         for filename in filenames]\n    return np.sum(n)\n\n# Function to seed everything\ndef seed_everything(seed):\n    random.seed(seed)\n    np.random.seed(seed)\n    os.environ['PYTHONHASHSEED'] = str(seed)\n    tf.random.set_seed(seed)\n    \ndef is_interactive():\n    return 'runtime'    in get_ipython().config.IPKernelApp.connection_file\nIS_INTERACTIVE = is_interactive()\nprint(IS_INTERACTIVE)","metadata":{"execution":{"iopub.status.busy":"2022-02-23T19:35:47.219955Z","iopub.execute_input":"2022-02-23T19:35:47.220404Z","iopub.status.idle":"2022-02-23T19:35:47.235257Z","shell.execute_reply.started":"2022-02-23T19:35:47.220369Z","shell.execute_reply":"2022-02-23T19:35:47.234466Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"MODEL_NAME = None\nif config.model_type == 'effnetv1':\n    MODEL_NAME = f'effnetv1_b{config.EFF_NET}'\nelif config.model_type == 'effnetv2':\n    MODEL_NAME = f'effnetv2_{config.EFF_NETV2}'\n\nconfig.MODEL_NAME = MODEL_NAME\nprint(MODEL_NAME)","metadata":{"execution":{"iopub.status.busy":"2022-02-23T19:35:47.236699Z","iopub.execute_input":"2022-02-23T19:35:47.237362Z","iopub.status.idle":"2022-02-23T19:35:47.245445Z","shell.execute_reply.started":"2022-02-23T19:35:47.237325Z","shell.execute_reply":"2022-02-23T19:35:47.244508Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"with open(config.save_dir+'/config.json', 'w') as fp:\n    json.dump({x:dict(config.__dict__)[x] for x in dict(config.__dict__) if not x.startswith('_')}, fp)","metadata":{"execution":{"iopub.status.busy":"2022-02-23T19:35:47.247096Z","iopub.execute_input":"2022-02-23T19:35:47.247652Z","iopub.status.idle":"2022-02-23T19:35:47.257477Z","shell.execute_reply.started":"2022-02-23T19:35:47.247613Z","shell.execute_reply":"2022-02-23T19:35:47.256624Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"GCS_PATH = 'gs://kds-d916c3252bf3bc5b3500b904f05f51ce57c8df85221d11b7711bcda9'  # Get GCS Path from kaggle notebook if GCS Path is expired\nif not IS_COLAB:\n    GCS_PATH = KaggleDatasets().get_gcs_path('happywhale-tfrecords-v1')\n    \ntrain_files = np.sort(np.array(tf.io.gfile.glob(GCS_PATH + '/happywhale-2022-train*.tfrec')))\ntest_files = np.sort(np.array(tf.io.gfile.glob(GCS_PATH + '/happywhale-2022-test*.tfrec')))\nprint(GCS_PATH)\nprint(len(train_files),len(test_files),count_data_items(train_files),count_data_items(test_files))","metadata":{"execution":{"iopub.status.busy":"2022-02-23T19:35:47.259215Z","iopub.execute_input":"2022-02-23T19:35:47.259886Z","iopub.status.idle":"2022-02-23T19:35:47.727183Z","shell.execute_reply.started":"2022-02-23T19:35:47.259849Z","shell.execute_reply":"2022-02-23T19:35:47.726463Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Data","metadata":{}},{"cell_type":"code","source":"def arcface_format(posting_id, image, label_group, matches):\n    return posting_id, {'inp1': image, 'inp2': label_group}, label_group, matches\n\ndef arcface_inference_format(posting_id, image, label_group, matches):\n    return image,posting_id\n\ndef arcface_eval_format(posting_id, image, label_group, matches):\n    return image,label_group\n\n# Data augmentation function\ndef data_augment(posting_id, image, label_group, matches):\n\n    ### CUTOUT\n    if tf.random.uniform([])>0.5 and config.CUTOUT:\n      N_CUTOUT = 6\n      for cutouts in range(N_CUTOUT):\n        if tf.random.uniform([])>0.5:\n           DIM = config.IMAGE_SIZE\n           CUTOUT_LENGTH = DIM//8\n           x1 = tf.cast( tf.random.uniform([],0,DIM-CUTOUT_LENGTH),tf.int32)\n           x2 = tf.cast( tf.random.uniform([],0,DIM-CUTOUT_LENGTH),tf.int32)\n           filter_ = tf.concat([tf.zeros((x1,CUTOUT_LENGTH)),tf.ones((CUTOUT_LENGTH,CUTOUT_LENGTH)),tf.zeros((DIM-x1-CUTOUT_LENGTH,CUTOUT_LENGTH))],axis=0)\n           filter_ = tf.concat([tf.zeros((DIM,x2)),filter_,tf.zeros((DIM,DIM-x2-CUTOUT_LENGTH))],axis=1)\n           cutout = tf.reshape(1-filter_,(DIM,DIM,1))\n           image = cutout*image\n\n    image = tf.image.random_flip_left_right(image)\n    # image = tf.image.random_flip_up_down(image)\n    image = tf.image.random_hue(image, 0.01)\n    image = tf.image.random_saturation(image, 0.70, 1.30)\n    image = tf.image.random_contrast(image, 0.80, 1.20)\n    image = tf.image.random_brightness(image, 0.10)\n    return posting_id, image, label_group, matches\n\n# Function to decode our images\ndef decode_image(image_data):\n    image = tf.image.decode_jpeg(image_data, channels = 3)\n    image = tf.image.resize(image, [config.IMAGE_SIZE,config.IMAGE_SIZE])\n    image = tf.cast(image, tf.float32) / 255.0\n    return image\n\n# This function parse our images and also get the target variable\ndef read_labeled_tfrecord(example):\n    LABELED_TFREC_FORMAT = {\n        \"image_name\": tf.io.FixedLenFeature([], tf.string),\n        \"image\": tf.io.FixedLenFeature([], tf.string),\n        \"target\": tf.io.FixedLenFeature([], tf.int64),\n#         \"matches\": tf.io.FixedLenFeature([], tf.string)\n    }\n\n    example = tf.io.parse_single_example(example, LABELED_TFREC_FORMAT)\n    posting_id = example['image_name']\n    image = decode_image(example['image'])\n#     label_group = tf.one_hot(tf.cast(example['label_group'], tf.int32), depth = N_CLASSES)\n    label_group = tf.cast(example['target'], tf.int32)\n#     matches = example['matches']\n    matches = 1\n    return posting_id, image, label_group, matches\n\n# This function loads TF Records and parse them into tensors\ndef load_dataset(filenames, ordered = False):\n    \n    ignore_order = tf.data.Options()\n    if not ordered:\n        ignore_order.experimental_deterministic = False \n        \n    dataset = tf.data.TFRecordDataset(filenames, num_parallel_reads = AUTO)\n#     dataset = dataset.cache()\n    dataset = dataset.with_options(ignore_order)\n    dataset = dataset.map(read_labeled_tfrecord, num_parallel_calls = AUTO) \n    return dataset\n\n# This function is to get our training tensors\ndef get_training_dataset(filenames):\n    dataset = load_dataset(filenames, ordered = False)\n    dataset = dataset.map(data_augment, num_parallel_calls = AUTO)\n    dataset = dataset.map(arcface_format, num_parallel_calls = AUTO)\n    dataset = dataset.map(lambda posting_id, image, label_group, matches: (image, label_group))\n    dataset = dataset.repeat()\n    dataset = dataset.shuffle(2048)\n    dataset = dataset.batch(config.BATCH_SIZE)\n    dataset = dataset.prefetch(AUTO)\n    return dataset\n\n# This function is to get our training tensors\ndef get_val_dataset(filenames):\n    dataset = load_dataset(filenames, ordered = True)\n    dataset = dataset.map(data_augment, num_parallel_calls = AUTO)\n    dataset = dataset.map(arcface_format, num_parallel_calls = AUTO)\n    dataset = dataset.map(lambda posting_id, image, label_group, matches: (image, label_group))\n    dataset = dataset.batch(config.BATCH_SIZE)\n    dataset = dataset.prefetch(AUTO)\n    return dataset\n\n# This function is to get our training tensors\ndef get_eval_dataset(filenames, get_targets = True):\n    dataset = load_dataset(filenames, ordered = True)\n    dataset = dataset.map(data_augment, num_parallel_calls = AUTO)\n    dataset = dataset.map(arcface_eval_format, num_parallel_calls = AUTO)\n    if not get_targets:\n        dataset = dataset.map(lambda image, target: image)\n    dataset = dataset.batch(config.BATCH_SIZE)\n    dataset = dataset.prefetch(AUTO)\n    return dataset\n\n# This function is to get our training tensors\ndef get_test_dataset(filenames, get_names = True):\n    dataset = load_dataset(filenames, ordered = True)\n    dataset = dataset.map(data_augment, num_parallel_calls = AUTO)\n    dataset = dataset.map(arcface_inference_format, num_parallel_calls = AUTO)\n    if not get_names:\n        dataset = dataset.map(lambda image, posting_id: image)\n    dataset = dataset.batch(config.BATCH_SIZE)\n    dataset = dataset.prefetch(AUTO)\n    return dataset","metadata":{"execution":{"iopub.status.busy":"2022-02-23T19:35:47.728515Z","iopub.execute_input":"2022-02-23T19:35:47.730924Z","iopub.status.idle":"2022-02-23T19:35:47.765309Z","shell.execute_reply.started":"2022-02-23T19:35:47.730886Z","shell.execute_reply":"2022-02-23T19:35:47.764624Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"row = 10; col = 8;\nrow = min(row,config.BATCH_SIZE//col)\nN_TRAIN = count_data_items(train_files)\nprint(N_TRAIN)\nds = get_training_dataset(train_files)\n\nfor (sample,label) in ds:\n    img = sample['inp1']\n    plt.figure(figsize=(25,int(25*row/col)))\n    for j in range(row*col):\n        plt.subplot(row,col,j+1)\n        plt.title(label[j].numpy())\n        plt.axis('off')\n        plt.imshow(img[j,])\n    plt.show()\n    break\nprint(img.shape)","metadata":{"execution":{"iopub.status.busy":"2022-02-23T19:35:47.766548Z","iopub.execute_input":"2022-02-23T19:35:47.768874Z","iopub.status.idle":"2022-02-23T19:36:34.575980Z","shell.execute_reply.started":"2022-02-23T19:35:47.768836Z","shell.execute_reply":"2022-02-23T19:36:34.575009Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"row = 10; col = 8;\nrow = min(row,config.BATCH_SIZE//col)\nN_TEST = count_data_items(test_files)\nprint(N_TEST)\nds = get_test_dataset(test_files)\n\nfor (img,label) in ds:\n    plt.figure(figsize=(25,int(25*row/col)))\n    for j in range(row*col):\n        plt.subplot(row,col,j+1)\n        plt.title(label[j].numpy())\n        plt.axis('off')\n        plt.imshow(img[j,])\n    plt.show()\n    break\nprint(img.shape)","metadata":{"execution":{"iopub.status.busy":"2022-02-23T19:36:34.577877Z","iopub.execute_input":"2022-02-23T19:36:34.578127Z","iopub.status.idle":"2022-02-23T19:36:39.569773Z","shell.execute_reply.started":"2022-02-23T19:36:34.578096Z","shell.execute_reply":"2022-02-23T19:36:39.569068Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Model","metadata":{}},{"cell_type":"code","source":"# Arcmarginproduct class keras layer\nclass ArcMarginProduct(tf.keras.layers.Layer):\n    '''\n    Implements large margin arc distance.\n\n    Reference:\n        https://arxiv.org/pdf/1801.07698.pdf\n        https://github.com/lyakaap/Landmark2019-1st-and-3rd-Place-Solution/\n            blob/master/src/modeling/metric_learning.py\n    '''\n    def __init__(self, n_classes, s=30, m=0.50, easy_margin=False,\n                 ls_eps=0.0, **kwargs):\n\n        super(ArcMarginProduct, self).__init__(**kwargs)\n\n        self.n_classes = n_classes\n        self.s = s\n        self.m = m\n        self.ls_eps = ls_eps\n        self.easy_margin = easy_margin\n        self.cos_m = tf.math.cos(m)\n        self.sin_m = tf.math.sin(m)\n        self.th = tf.math.cos(math.pi - m)\n        self.mm = tf.math.sin(math.pi - m) * m\n\n    def get_config(self):\n\n        config = super().get_config().copy()\n        config.update({\n            'n_classes': self.n_classes,\n            's': self.s,\n            'm': self.m,\n            'ls_eps': self.ls_eps,\n            'easy_margin': self.easy_margin,\n        })\n        return config\n\n    def build(self, input_shape):\n        super(ArcMarginProduct, self).build(input_shape[0])\n\n        self.W = self.add_weight(\n            name='W',\n            shape=(int(input_shape[0][-1]), self.n_classes),\n            initializer='glorot_uniform',\n            dtype='float32',\n            trainable=True,\n            regularizer=None)\n\n    def call(self, inputs):\n        X, y = inputs\n        y = tf.cast(y, dtype=tf.int32)\n        cosine = tf.matmul(\n            tf.math.l2_normalize(X, axis=1),\n            tf.math.l2_normalize(self.W, axis=0)\n        )\n        sine = tf.math.sqrt(1.0 - tf.math.pow(cosine, 2))\n        phi = cosine * self.cos_m - sine * self.sin_m\n        if self.easy_margin:\n            phi = tf.where(cosine > 0, phi, cosine)\n        else:\n            phi = tf.where(cosine > self.th, phi, cosine - self.mm)\n        one_hot = tf.cast(\n            tf.one_hot(y, depth=self.n_classes),\n            dtype=cosine.dtype\n        )\n        if self.ls_eps > 0:\n            one_hot = (1 - self.ls_eps) * one_hot + self.ls_eps / self.n_classes\n\n        output = (one_hot * phi) + ((1.0 - one_hot) * cosine)\n        output *= self.s\n        return output","metadata":{"execution":{"iopub.status.busy":"2022-02-23T19:36:39.571189Z","iopub.execute_input":"2022-02-23T19:36:39.571472Z","iopub.status.idle":"2022-02-23T19:36:39.591884Z","shell.execute_reply.started":"2022-02-23T19:36:39.571440Z","shell.execute_reply":"2022-02-23T19:36:39.591001Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"EFNS = [efn.EfficientNetB0, efn.EfficientNetB1, efn.EfficientNetB2, efn.EfficientNetB3, \n        efn.EfficientNetB4, efn.EfficientNetB5, efn.EfficientNetB6, efn.EfficientNetB7]\n\ndef freeze_BN(model):\n    # Unfreeze layers while leaving BatchNorm layers frozen\n    for layer in model.layers:\n        if not isinstance(layer, tf.keras.layers.BatchNormalization):\n            layer.trainable = True\n        else:\n            layer.trainable = False\n\n# Function to create our EfficientNetB3 model\ndef get_model():\n\n    if config.head=='arcface':\n        head = ArcMarginProduct\n    else:\n        assert 1==2, \"INVALID HEAD\"\n    \n    with strategy.scope():\n        \n        margin = head(\n            n_classes = config.N_CLASSES, \n            s = 30, \n            m = 0.3, \n            name=f'head/{config.head}', \n            dtype='float32'\n            )\n\n        inp = tf.keras.layers.Input(shape = [config.IMAGE_SIZE, config.IMAGE_SIZE, 3], name = 'inp1')\n        label = tf.keras.layers.Input(shape = (), name = 'inp2')\n        \n        if config.model_type == 'effnetv1':\n            x = EFNS[config.EFF_NET](weights = 'noisy-student', include_top = False)(inp)\n            embed = tf.keras.layers.GlobalAveragePooling2D()(x)\n        elif config.model_type == 'effnetv2':\n            FEATURE_VECTOR = f'{EFFNETV2_ROOT}/tfhub_models/efficientnetv2-{config.EFF_NETV2}/feature_vector'\n            embed = tfhub.KerasLayer(FEATURE_VECTOR, trainable=True)(inp)\n            \n        embed = tf.keras.layers.Dropout(0.2)(embed)\n        embed = tf.keras.layers.Dense(512)(embed)\n        x = margin([embed, label])\n        \n        output = tf.keras.layers.Softmax(dtype='float32')(x)\n        \n        model = tf.keras.models.Model(inputs = [inp, label], outputs = [output])\n        embed_model = tf.keras.models.Model(inputs = inp, outputs = embed)  \n        \n        opt = tf.keras.optimizers.Adam(learning_rate = config.LR)\n        if config.FREEZE_BATCH_NORM:\n            freeze_BN(model)\n\n        model.compile(\n            optimizer = opt,\n            loss = [tf.keras.losses.SparseCategoricalCrossentropy()],\n            metrics = [tf.keras.metrics.SparseCategoricalAccuracy(),tf.keras.metrics.SparseTopKCategoricalAccuracy(k=5)]\n            ) \n        \n        return model,embed_model","metadata":{"execution":{"iopub.status.busy":"2022-02-23T19:36:39.597297Z","iopub.execute_input":"2022-02-23T19:36:39.598224Z","iopub.status.idle":"2022-02-23T19:36:39.618376Z","shell.execute_reply.started":"2022-02-23T19:36:39.598189Z","shell.execute_reply":"2022-02-23T19:36:39.617793Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def get_lr_callback(plot=False):\n    lr_start   = 0.000001\n    lr_max     = 0.000005 * config.BATCH_SIZE  \n    lr_min     = 0.000001\n    lr_ramp_ep = 4\n    lr_sus_ep  = 0\n    lr_decay   = 0.9\n   \n    def lrfn(epoch):\n        if config.RESUME:\n            epoch = epoch + config.RESUME_EPOCH\n        if epoch < lr_ramp_ep:\n            lr = (lr_max - lr_start) / lr_ramp_ep * epoch + lr_start\n            \n        elif epoch < lr_ramp_ep + lr_sus_ep:\n            lr = lr_max\n            \n        else:\n            lr = (lr_max - lr_min) * lr_decay**(epoch - lr_ramp_ep - lr_sus_ep) + lr_min\n            \n        return lr\n        \n    if plot:\n        epochs = list(range(config.EPOCHS))\n        learning_rates = [lrfn(x) for x in epochs]\n        plt.scatter(epochs,learning_rates)\n        plt.show()\n\n    lr_callback = tf.keras.callbacks.LearningRateScheduler(lrfn, verbose=False)\n    return lr_callback\n\nget_lr_callback(plot=True)","metadata":{"execution":{"iopub.status.busy":"2022-02-23T19:36:39.620060Z","iopub.execute_input":"2022-02-23T19:36:39.620767Z","iopub.status.idle":"2022-02-23T19:36:39.859656Z","shell.execute_reply.started":"2022-02-23T19:36:39.620719Z","shell.execute_reply":"2022-02-23T19:36:39.859077Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"class Snapshot(tf.keras.callbacks.Callback):\n    \n    def __init__(self,fold,snapshot_epochs=[]):\n        super(Snapshot, self).__init__()\n        self.snapshot_epochs = snapshot_epochs\n        self.fold = fold\n        \n        \n    def on_epoch_end(self, epoch, logs=None):\n        # logs is a dictionary\n#         print(f\"epoch: {epoch}, train_acc: {logs['acc']}, valid_acc: {logs['val_acc']}\")\n        if epoch in self.snapshot_epochs: # your custom condition         \n            self.model.save_weights(config.save_dir+f\"/EF{config.MODEL_NAME}_epoch{epoch}.h5\")\n        self.model.save_weights(config.save_dir+f\"/{config.MODEL_NAME}_last.h5\")","metadata":{"execution":{"iopub.status.busy":"2022-02-23T19:36:39.861103Z","iopub.execute_input":"2022-02-23T19:36:39.861675Z","iopub.status.idle":"2022-02-23T19:36:39.869041Z","shell.execute_reply.started":"2022-02-23T19:36:39.861642Z","shell.execute_reply":"2022-02-23T19:36:39.868110Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Train","metadata":{}},{"cell_type":"code","source":"TRAINING_FILENAMES = [x for i,x in enumerate(train_files) if i%config.FOLDS!=config.FOLD_TO_RUN]\nVALIDATION_FILENAMES = [x for i,x in enumerate(train_files) if i%config.FOLDS==config.FOLD_TO_RUN]\nprint(len(TRAINING_FILENAMES),len(VALIDATION_FILENAMES),count_data_items(TRAINING_FILENAMES),count_data_items(VALIDATION_FILENAMES))","metadata":{"execution":{"iopub.status.busy":"2022-02-23T19:36:39.871086Z","iopub.execute_input":"2022-02-23T19:36:39.871898Z","iopub.status.idle":"2022-02-23T19:36:39.880864Z","shell.execute_reply.started":"2022-02-23T19:36:39.871824Z","shell.execute_reply":"2022-02-23T19:36:39.880067Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"if config.DEBUG:\n    TRAINING_FILENAMES = [TRAINING_FILENAMES[0]]\n    VALIDATION_FILENAMES = [VALIDATION_FILENAMES[0]]\n    print(len(TRAINING_FILENAMES),len(VALIDATION_FILENAMES),count_data_items(TRAINING_FILENAMES),count_data_items(VALIDATION_FILENAMES))\n    test_files = [test_files[0]]","metadata":{"execution":{"iopub.status.busy":"2022-02-23T19:36:39.882832Z","iopub.execute_input":"2022-02-23T19:36:39.883897Z","iopub.status.idle":"2022-02-23T19:36:39.890788Z","shell.execute_reply.started":"2022-02-23T19:36:39.883868Z","shell.execute_reply":"2022-02-23T19:36:39.889847Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"seed_everything(config.SEED)\nVERBOSE = 1\ntrain_dataset = get_training_dataset(TRAINING_FILENAMES)\nval_dataset = get_val_dataset(VALIDATION_FILENAMES)\nSTEPS_PER_EPOCH = count_data_items(TRAINING_FILENAMES) // config.BATCH_SIZE\ntrain_logger = tf.keras.callbacks.CSVLogger(config.save_dir+'/training-log-fold-%i.h5.csv'%config.FOLD_TO_RUN)\n# SAVE BEST MODEL EACH FOLD        \nsv_loss = tf.keras.callbacks.ModelCheckpoint(\n    config.save_dir+f\"/{config.MODEL_NAME}_loss_{config.FOLD_TO_RUN}.h5\", monitor='val_loss', verbose=0, save_best_only=True,\n    save_weights_only=True, mode='min', save_freq='epoch')\n# BUILD MODEL\nK.clear_session()\nmodel,embed_model = get_model()\nsnap = Snapshot(fold=config.FOLD_TO_RUN,snapshot_epochs=[5,8])\nmodel.summary()\n\nif config.RESUME:   \n    model.load_weights(config.resume_model_wts)","metadata":{"execution":{"iopub.status.busy":"2022-02-23T19:36:39.892682Z","iopub.execute_input":"2022-02-23T19:36:39.893568Z","iopub.status.idle":"2022-02-23T19:36:45.414533Z","shell.execute_reply.started":"2022-02-23T19:36:39.893523Z","shell.execute_reply":"2022-02-23T19:36:45.413799Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print('#### Image Size %i with EfficientNet B%i and batch_size %i'%\n      (config.IMAGE_SIZE,config.EFF_NET,config.BATCH_SIZE))\n\"\"\"#In this notebook, we do not train models \nhistory = model.fit(train_dataset,\n                validation_data = val_dataset,\n                steps_per_epoch = STEPS_PER_EPOCH,\n                epochs = config.EPOCHS,\n                callbacks = [snap,get_lr_callback(),train_logger,sv_loss], \n                verbose = VERBOSE)\n                \n\"\"\"","metadata":{"execution":{"iopub.status.busy":"2022-02-23T19:36:45.416416Z","iopub.execute_input":"2022-02-23T19:36:45.417714Z","iopub.status.idle":"2022-02-23T19:36:45.425953Z","shell.execute_reply.started":"2022-02-23T19:36:45.417677Z","shell.execute_reply":"2022-02-23T19:36:45.425222Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#with open(config.save_dir+f'train_{filename.split(\"/\")[-1]}_{config.FOLD_TO_RUN}.npy', 'rb') as f:\n","metadata":{"execution":{"iopub.status.busy":"2022-02-23T19:36:45.427348Z","iopub.execute_input":"2022-02-23T19:36:45.428061Z","iopub.status.idle":"2022-02-23T19:36:45.435185Z","shell.execute_reply.started":"2022-02-23T19:36:45.428024Z","shell.execute_reply":"2022-02-23T19:36:45.434500Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#model.load_weights(config.save_dir+f\"/{config.MODEL_NAME}_loss.h5\")\n#embed_models=[]\n#for i in range(5):\n #   model,embed_model = get_model()\n #   embed_models.append((model.load_weights(f\"../input/happywhale-arcface-eff5-768/effnetv1_b5_loss_{i}.h5\"),embed_model))\n    ","metadata":{"execution":{"iopub.status.busy":"2022-02-23T19:36:45.436550Z","iopub.execute_input":"2022-02-23T19:36:45.437117Z","iopub.status.idle":"2022-02-23T19:36:45.445892Z","shell.execute_reply.started":"2022-02-23T19:36:45.437083Z","shell.execute_reply":"2022-02-23T19:36:45.445005Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import os","metadata":{"execution":{"iopub.status.busy":"2022-02-23T19:36:45.447688Z","iopub.execute_input":"2022-02-23T19:36:45.447980Z","iopub.status.idle":"2022-02-23T19:36:45.455607Z","shell.execute_reply.started":"2022-02-23T19:36:45.447947Z","shell.execute_reply":"2022-02-23T19:36:45.454723Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Evaluation","metadata":{}},{"cell_type":"code","source":"def better_than_median(inputs, axis):\n    \"\"\"Compute the mean of the predictions if there are no outliers,\n    or the median if there are outliers.\n\n    Parameter: inputs = ndarray of shape (n_samples, n_folds)\"\"\"\n    spread = inputs.max(axis=axis) - inputs.min(axis=axis) \n    spread_lim = 0.45\n    print(f\"Inliers:  {(spread < spread_lim).sum():7} -> compute mean\")\n    print(f\"Outliers: {(spread >= spread_lim).sum():7} -> compute median\")\n    print(f\"Total:    {len(inputs):7}\")\n    return np.where(spread < spread_lim,\n                    np.mean(inputs, axis=axis),\n                    np.median(inputs, axis=axis))","metadata":{"execution":{"iopub.status.busy":"2022-02-23T19:36:45.457549Z","iopub.execute_input":"2022-02-23T19:36:45.457819Z","iopub.status.idle":"2022-02-23T19:36:45.466327Z","shell.execute_reply.started":"2022-02-23T19:36:45.457786Z","shell.execute_reply":"2022-02-23T19:36:45.465457Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def get_ids(filename):\n    ds = get_test_dataset([filename],get_names=True).map(lambda image, image_name: image_name).unbatch()\n    NUM_IMAGES = count_data_items([filename])\n    ids = next(iter(ds.batch(NUM_IMAGES))).numpy().astype('U')\n    return ids\n\ndef get_targets(filename):\n    ds = get_eval_dataset([filename],get_targets=True).map(lambda image, target: target).unbatch()\n    NUM_IMAGES = count_data_items([filename])\n    ids = next(iter(ds.batch(NUM_IMAGES))).numpy()\n    return ids\n\ndef get_embeddings(filename):\n    ds = get_test_dataset([filename],get_names=False)\n    embeddings = np.mean(np.stack([embed_models[x][1].predict(ds,verbose=0) for x in range(5)]), axis=0)\n    #print (embeddings.shape)\n    return embeddings\n\ndef get_embeddings_np(filename,data_types='train',kfold_list=[x for x in range(5)],dataset='../input/eff7-new-768'):#x for x in range(6)\n    #ds = get_test_dataset([filename],get_names=False)\n    #embeddings = np.mean(np.stack([embed_models[x][1].predict(ds,verbose=0) for x in range(5)]), axis=0)\n    #print (embeddings.shape)\n    val_train={'train':'val','val':'train','test':'test'}\n    embeddings=[]\n    for kfold in kfold_list:\n        path=f'{dataset}/{data_types}_{filename.split(\"/\")[-1]}_{kfold}.npy'\n        if os.path.exists(path):\n            print(path)\n            with open(path, 'rb') as f:\n                embeddings.append(np.load(f))\n        else:\n            path=f'{dataset}/{val_train[data_types]}_{filename.split(\"/\")[-1]}_{kfold}.npy'\n            if os.path.exists(path):\n                print(path)\n                with open(path, 'rb') as f:\n                    embeddings.append(np.load(f))\n                \n                \n    print (len(embeddings))\n    embeddings = np.mean(np.stack(embeddings), axis=0)\n    #embeddings = np.median(np.stack(embeddings), axis=0)\n    #embeddings = better_than_median(np.stack(embeddings), axis=0)\n    \n    return embeddings\n\ndef get_predictions(test_df,threshold=0.2):\n    predictions = {}\n    for i,row in tqdm(test_df.iterrows()):\n        if row.image in predictions:\n            if len(predictions[row.image])==5:\n                continue\n            predictions[row.image].append(row.target)\n        elif row.confidence>threshold:\n            predictions[row.image] = [row.target,'new_individual']\n        else:\n            predictions[row.image] = ['new_individual',row.target]\n\n    for x in tqdm(predictions):\n        if len(predictions[x])<5:\n            remaining = [y for y in sample_list if y not in predictions]\n            predictions[x] = predictions[x]+remaining\n            predictions[x] = predictions[x][:5]\n        \n    return predictions\n\ndef map_per_image(label, predictions):\n    \"\"\"Computes the precision score of one image.\n\n    Parameters\n    ----------\n    label : string\n            The true label of the image\n    predictions : list\n            A list of predicted elements (order does matter, 5 predictions allowed per image)\n\n    Returns\n    -------\n    score : double\n    \"\"\"    \n    try:\n        return 1 / (predictions[:5].index(label) + 1)\n    except ValueError:\n        return 0.0\n    \nf = open ('../input/happywhale-splits/individual_ids.json', \"r\")\ntarget_encodings = json.loads(f.read())\ntarget_encodings = {target_encodings[x]:x for x in target_encodings}\nsample_list = ['938b7e931166', '5bf17305f073', '7593d2aee842', '7362d7a01d00','956562ff2888']","metadata":{"execution":{"iopub.status.busy":"2022-02-23T19:36:45.468356Z","iopub.execute_input":"2022-02-23T19:36:45.468648Z","iopub.status.idle":"2022-02-23T19:36:45.517451Z","shell.execute_reply.started":"2022-02-23T19:36:45.468617Z","shell.execute_reply":"2022-02-23T19:36:45.516789Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_targets = []\ntrain_embeddings = []\nfor filename in tqdm(TRAINING_FILENAMES):#TRAINING_FILENAMES\n    embeddings = get_embeddings_np(filename)\n    targets = get_targets(filename)\n    train_embeddings.append(embeddings)\n    train_targets.append(targets)\ntrain_embeddings = np.concatenate(train_embeddings)\ntrain_targets = np.concatenate(train_targets)","metadata":{"execution":{"iopub.status.busy":"2022-02-23T19:36:45.518455Z","iopub.execute_input":"2022-02-23T19:36:45.519149Z","iopub.status.idle":"2022-02-23T19:53:17.645417Z","shell.execute_reply.started":"2022-02-23T19:36:45.519114Z","shell.execute_reply":"2022-02-23T19:53:17.644396Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from sklearn.neighbors import NearestNeighbors\nneigh = NearestNeighbors(n_neighbors=config.KNN,metric='cosine')\nneigh.fit(train_embeddings)","metadata":{"execution":{"iopub.status.busy":"2022-02-23T19:53:17.653804Z","iopub.execute_input":"2022-02-23T19:53:17.661865Z","iopub.status.idle":"2022-02-23T19:53:17.774273Z","shell.execute_reply.started":"2022-02-23T19:53:17.661827Z","shell.execute_reply":"2022-02-23T19:53:17.773472Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test_ids = []\ntest_nn_distances = []\ntest_nn_idxs = []\nval_targets = []\nval_embeddings = []\nfor filename in tqdm(VALIDATION_FILENAMES):#(VALIDATION_FILENAMES):\n    embeddings = get_embeddings_np(filename,'val')\n    targets = get_targets(filename)\n    ids = get_ids(filename)\n    distances,idxs = neigh.kneighbors(embeddings, config.KNN, return_distance=True)\n    test_ids.append(ids)\n    test_nn_idxs.append(idxs)\n    test_nn_distances.append(distances)\n    val_embeddings.append(embeddings)\n    val_targets.append(targets)\ntest_nn_distances = np.concatenate(test_nn_distances)\ntest_nn_idxs = np.concatenate(test_nn_idxs)\ntest_ids = np.concatenate(test_ids)\nval_embeddings = np.concatenate(val_embeddings)\nval_targets = np.concatenate(val_targets)","metadata":{"execution":{"iopub.status.busy":"2022-02-23T19:53:17.775934Z","iopub.execute_input":"2022-02-23T19:53:17.776784Z","iopub.status.idle":"2022-02-23T20:01:26.982053Z","shell.execute_reply.started":"2022-02-23T19:53:17.776731Z","shell.execute_reply":"2022-02-23T20:01:26.981314Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"allowed_targets = set([target_encodings[x] for x in np.unique(train_targets)])\nval_targets_df = pd.DataFrame(np.stack([test_ids,val_targets],axis=1),columns=['image','target'])\nval_targets_df['target'] = val_targets_df['target'].astype(int).map(target_encodings)\nval_targets_df.loc[~val_targets_df.target.isin(allowed_targets),'target'] = 'new_individual'\nval_targets_df.target.value_counts()","metadata":{"execution":{"iopub.status.busy":"2022-02-23T20:01:26.983289Z","iopub.execute_input":"2022-02-23T20:01:26.983592Z","iopub.status.idle":"2022-02-23T20:01:27.072760Z","shell.execute_reply.started":"2022-02-23T20:01:26.983555Z","shell.execute_reply":"2022-02-23T20:01:27.071976Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test_df = []\nfor i in tqdm(range(len(test_ids))):\n    id_ = test_ids[i]\n    targets = train_targets[test_nn_idxs[i]]\n    distances = test_nn_distances[i]\n    subset_preds = pd.DataFrame(np.stack([targets,distances],axis=1),columns=['target','distances'])\n    subset_preds['image'] = id_\n    test_df.append(subset_preds)\ntest_df = pd.concat(test_df).reset_index(drop=True)\ntest_df['confidence'] = 1-test_df['distances']\ntest_df = test_df.groupby(['image','target']).confidence.max().reset_index()\ntest_df = test_df.sort_values('confidence',ascending=False).reset_index(drop=True)\ntest_df['target'] = test_df['target'].map(target_encodings)\ntest_df.to_csv('val_neighbors.csv')\ntest_df.image.value_counts().value_counts()","metadata":{"execution":{"iopub.status.busy":"2022-02-23T20:01:27.073903Z","iopub.execute_input":"2022-02-23T20:01:27.074518Z","iopub.status.idle":"2022-02-23T20:02:05.964819Z","shell.execute_reply.started":"2022-02-23T20:01:27.074475Z","shell.execute_reply":"2022-02-23T20:02:05.963686Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"## Compute CV\nbest_th = 0\nbest_cv = 0\nfor th in [0.1*x for x in range(11)]:\n    all_preds = get_predictions(test_df,threshold=th)\n    cv = 0\n    for i,row in val_targets_df.iterrows():\n        target = row.target\n        preds = all_preds[row.image]\n        val_targets_df.loc[i,th] = map_per_image(target,preds)\n    cv = val_targets_df[th].mean()\n    print(f\"CV at threshold {th}: {cv}\")\n    if cv>best_cv:\n        best_th = th\n        best_cv = cv","metadata":{"execution":{"iopub.status.busy":"2022-02-23T20:02:05.966547Z","iopub.execute_input":"2022-02-23T20:02:05.967229Z","iopub.status.idle":"2022-02-23T21:15:54.815302Z","shell.execute_reply.started":"2022-02-23T20:02:05.967191Z","shell.execute_reply":"2022-02-23T21:15:54.814542Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print(\"Best threshold\",best_th)\nprint(\"Best cv\",best_cv)\nval_targets_df.describe()","metadata":{"execution":{"iopub.status.busy":"2022-02-23T21:15:54.816615Z","iopub.execute_input":"2022-02-23T21:15:54.817052Z","iopub.status.idle":"2022-02-23T21:15:54.873766Z","shell.execute_reply.started":"2022-02-23T21:15:54.817013Z","shell.execute_reply":"2022-02-23T21:15:54.872969Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"## Adjustment: Since Public lb has nearly 10% 'new_individual' (Be Careful for private LB)\nval_targets_df['is_new_individual'] = val_targets_df.target=='new_individual'\nprint(val_targets_df.is_new_individual.value_counts().to_dict())\nval_scores = val_targets_df.groupby('is_new_individual').mean().T\nval_scores['adjusted_cv'] = val_scores[True]*0.1+val_scores[False]*0.9\nbest_threshold_adjusted = val_scores['adjusted_cv'].idxmax()\nprint(\"best_threshold\",best_threshold_adjusted)\nval_scores","metadata":{"execution":{"iopub.status.busy":"2022-02-23T21:15:54.875235Z","iopub.execute_input":"2022-02-23T21:15:54.875585Z","iopub.status.idle":"2022-02-23T21:15:54.907144Z","shell.execute_reply.started":"2022-02-23T21:15:54.875529Z","shell.execute_reply":"2022-02-23T21:15:54.906452Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Inference","metadata":{}},{"cell_type":"code","source":"train_embeddings = np.concatenate([train_embeddings,val_embeddings])\ntrain_targets = np.concatenate([train_targets,val_targets])\nprint(train_embeddings.shape,train_targets.shape)","metadata":{"execution":{"iopub.status.busy":"2022-02-23T21:15:54.908504Z","iopub.execute_input":"2022-02-23T21:15:54.911224Z","iopub.status.idle":"2022-02-23T21:15:55.077407Z","shell.execute_reply.started":"2022-02-23T21:15:54.911151Z","shell.execute_reply":"2022-02-23T21:15:55.076672Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from sklearn.neighbors import NearestNeighbors\nneigh = NearestNeighbors(n_neighbors=config.KNN,metric='cosine')\nneigh.fit(train_embeddings)","metadata":{"execution":{"iopub.status.busy":"2022-02-23T21:15:55.078898Z","iopub.execute_input":"2022-02-23T21:15:55.079327Z","iopub.status.idle":"2022-02-23T21:15:55.178533Z","shell.execute_reply.started":"2022-02-23T21:15:55.079288Z","shell.execute_reply":"2022-02-23T21:15:55.177840Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test_ids = []\ntest_nn_distances = []\ntest_nn_idxs = []\nfor filename in tqdm(test_files):\n    embeddings = get_embeddings_np(filename,'test')\n    ids = get_ids(filename)\n    distances,idxs = neigh.kneighbors(embeddings, config.KNN, return_distance=True)\n    test_ids.append(ids)\n    test_nn_idxs.append(idxs)\n    test_nn_distances.append(distances)\ntest_nn_distances = np.concatenate(test_nn_distances)\ntest_nn_idxs = np.concatenate(test_nn_idxs)\ntest_ids = np.concatenate(test_ids)","metadata":{"execution":{"iopub.status.busy":"2022-02-23T21:15:55.179764Z","iopub.execute_input":"2022-02-23T21:15:55.180146Z","iopub.status.idle":"2022-02-23T21:28:47.006460Z","shell.execute_reply.started":"2022-02-23T21:15:55.180113Z","shell.execute_reply":"2022-02-23T21:28:47.005676Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"sample_submission = pd.read_csv('../input/happy-whale-and-dolphin/sample_submission.csv',index_col='image')\nprint(len(test_ids),len(sample_submission))\ntest_df = []\nfor i in tqdm(range(len(test_ids))):\n    id_ = test_ids[i]\n    targets = train_targets[test_nn_idxs[i]]\n    distances = test_nn_distances[i]\n    subset_preds = pd.DataFrame(np.stack([targets,distances],axis=1),columns=['target','distances'])\n    subset_preds['image'] = id_\n    test_df.append(subset_preds)\ntest_df = pd.concat(test_df).reset_index(drop=True)\ntest_df['confidence'] = 1-test_df['distances']\ntest_df = test_df.groupby(['image','target']).confidence.max().reset_index()\ntest_df = test_df.sort_values('confidence',ascending=False).reset_index(drop=True)\ntest_df['target'] = test_df['target'].map(target_encodings)\ntest_df.to_csv('test_neighbors.csv')\ntest_df.image.value_counts().value_counts()","metadata":{"execution":{"iopub.status.busy":"2022-02-23T21:28:47.007963Z","iopub.execute_input":"2022-02-23T21:28:47.008552Z","iopub.status.idle":"2022-02-23T21:30:32.568381Z","shell.execute_reply.started":"2022-02-23T21:28:47.008435Z","shell.execute_reply":"2022-02-23T21:30:32.567699Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"sample_list = ['938b7e931166', '5bf17305f073', '7593d2aee842', '7362d7a01d00','956562ff2888']","metadata":{"execution":{"iopub.status.busy":"2022-02-23T21:30:32.569974Z","iopub.execute_input":"2022-02-23T21:30:32.571016Z","iopub.status.idle":"2022-02-23T21:30:32.575145Z","shell.execute_reply.started":"2022-02-23T21:30:32.570973Z","shell.execute_reply":"2022-02-23T21:30:32.574337Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"predictions = {}\nfor i,row in tqdm(test_df.iterrows()):\n    if row.image in predictions:\n        if len(predictions[row.image])==5:\n            continue\n        predictions[row.image].append(row.target)\n    elif row.confidence>best_threshold_adjusted:#best_threshold_adjusted\n        predictions[row.image] = [row.target,'new_individual']\n    else:\n        predictions[row.image] = ['new_individual',row.target]\n        \nfor x in tqdm(predictions):\n    if len(predictions[x])<5:\n        remaining = [y for y in sample_list if y not in predictions]\n        predictions[x] = predictions[x]+remaining\n        predictions[x] = predictions[x][:5]\n    predictions[x] = ' '.join(predictions[x])\n    \npredictions = pd.Series(predictions).reset_index()\npredictions.columns = ['image','predictions']\npredictions.to_csv('submission.csv',index=False)\npredictions.head()","metadata":{"execution":{"iopub.status.busy":"2022-02-23T21:30:32.576462Z","iopub.execute_input":"2022-02-23T21:30:32.576864Z","iopub.status.idle":"2022-02-23T21:48:09.070593Z","shell.execute_reply.started":"2022-02-23T21:30:32.576830Z","shell.execute_reply":"2022-02-23T21:48:09.069842Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print (test_df)","metadata":{"execution":{"iopub.status.busy":"2022-02-23T21:48:09.072319Z","iopub.execute_input":"2022-02-23T21:48:09.072939Z","iopub.status.idle":"2022-02-23T21:48:09.084041Z","shell.execute_reply.started":"2022-02-23T21:48:09.072902Z","shell.execute_reply":"2022-02-23T21:48:09.083254Z"},"trusted":true},"execution_count":null,"outputs":[]}]}