{"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":"# Intro\nInference notebook for [Hotel-ID starter - similarity - training](https://www.kaggle.com/basneeleman/hotel-id-krypton-similarity-training/)\n\nUsing model and embeddings from the training notebook to generate embeddings for test data and find similar images.","metadata":{"id":"DAY5rHgTm7e8","papermill":{"duration":0.024896,"end_time":"2022-03-24T14:00:54.588459","exception":false,"start_time":"2022-03-24T14:00:54.563563","status":"completed"},"tags":[]}},{"cell_type":"markdown","source":"# Setup","metadata":{}},{"cell_type":"code","source":"import sys\nsys.path.append('../input/timm-pytorch-image-models/pytorch-image-models-master')","metadata":{"executionInfo":{"elapsed":16271,"status":"ok","timestamp":1619310548121,"user":{"displayName":"Jeom Jin-Ho","photoUrl":"","userId":"00155613517919499503"},"user_tz":-120},"id":"alleged-legislation","outputId":"c6541e5f-ffb4-4609-d6c6-39784e6a07b1","papermill":{"duration":0.036572,"end_time":"2022-03-24T14:00:54.649254","exception":false,"start_time":"2022-03-24T14:00:54.612682","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2022-05-25T21:13:11.38194Z","iopub.execute_input":"2022-05-25T21:13:11.382627Z","iopub.status.idle":"2022-05-25T21:13:11.413551Z","shell.execute_reply.started":"2022-05-25T21:13:11.382534Z","shell.execute_reply":"2022-05-25T21:13:11.412891Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Imports","metadata":{"id":"cZoSOL9Qm-Yr","papermill":{"duration":0.023644,"end_time":"2022-03-24T14:00:54.696898","exception":false,"start_time":"2022-03-24T14:00:54.673254","status":"completed"},"tags":[]}},{"cell_type":"code","source":"import numpy as np\nimport pandas as pd\nimport random\nimport os\nimport math","metadata":{"_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","executionInfo":{"elapsed":14459,"status":"ok","timestamp":1619310548121,"user":{"displayName":"Jeom Jin-Ho","photoUrl":"","userId":"00155613517919499503"},"user_tz":-120},"id":"expired-matter","papermill":{"duration":0.030271,"end_time":"2022-03-24T14:00:54.751131","exception":false,"start_time":"2022-03-24T14:00:54.72086","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2022-05-25T21:13:11.415262Z","iopub.execute_input":"2022-05-25T21:13:11.415762Z","iopub.status.idle":"2022-05-25T21:13:11.420249Z","shell.execute_reply.started":"2022-05-25T21:13:11.415724Z","shell.execute_reply":"2022-05-25T21:13:11.419228Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from PIL import Image as pil_image\nfrom tqdm import tqdm","metadata":{"executionInfo":{"elapsed":16003,"status":"ok","timestamp":1619310550014,"user":{"displayName":"Jeom Jin-Ho","photoUrl":"","userId":"00155613517919499503"},"user_tz":-120},"id":"extreme-problem","papermill":{"duration":3.220402,"end_time":"2022-03-24T14:00:57.995239","exception":false,"start_time":"2022-03-24T14:00:54.774837","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2022-05-25T21:13:11.424302Z","iopub.execute_input":"2022-05-25T21:13:11.426078Z","iopub.status.idle":"2022-05-25T21:13:11.430548Z","shell.execute_reply.started":"2022-05-25T21:13:11.426049Z","shell.execute_reply":"2022-05-25T21:13:11.429714Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import torch\nimport torch.nn as nn\nfrom torch.utils.data import DataLoader\n\nimport timm\nfrom sklearn.metrics.pairwise import cosine_similarity","metadata":{"executionInfo":{"elapsed":19672,"status":"ok","timestamp":1619310554099,"user":{"displayName":"Jeom Jin-Ho","photoUrl":"","userId":"00155613517919499503"},"user_tz":-120},"id":"angry-domain","papermill":{"duration":2.727834,"end_time":"2022-03-24T14:01:00.766951","exception":false,"start_time":"2022-03-24T14:00:58.039117","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2022-05-25T21:13:11.434502Z","iopub.execute_input":"2022-05-25T21:13:11.435013Z","iopub.status.idle":"2022-05-25T21:13:16.275673Z","shell.execute_reply.started":"2022-05-25T21:13:11.434983Z","shell.execute_reply":"2022-05-25T21:13:16.274924Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Global","metadata":{"id":"0B00pe7mnBTj","papermill":{"duration":0.023573,"end_time":"2022-03-24T14:01:00.814976","exception":false,"start_time":"2022-03-24T14:01:00.791403","status":"completed"},"tags":[]}},{"cell_type":"code","source":"SEED = 42\nIMG_SIZE = 512\nN_MATCHES = 5\n\nPROJECT_FOLDER = \"../input/hotel-id-to-combat-human-trafficking-2022-fgvc9/\"\nTRAIN_DATA_FOLDER = \"../input/hotelid-2022-train-images-256x256/images/\"\nTEST_DATA_FOLDER = PROJECT_FOLDER + \"test_images/\"","metadata":{"executionInfo":{"elapsed":589,"status":"ok","timestamp":1619310979015,"user":{"displayName":"Jeom Jin-Ho","photoUrl":"","userId":"00155613517919499503"},"user_tz":-120},"id":"contained-brief","papermill":{"duration":0.03175,"end_time":"2022-03-24T14:01:00.871686","exception":false,"start_time":"2022-03-24T14:01:00.839936","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2022-05-25T21:13:16.280766Z","iopub.execute_input":"2022-05-25T21:13:16.282732Z","iopub.status.idle":"2022-05-25T21:13:16.288379Z","shell.execute_reply.started":"2022-05-25T21:13:16.282694Z","shell.execute_reply":"2022-05-25T21:13:16.28784Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print(os.listdir(PROJECT_FOLDER))","metadata":{"executionInfo":{"elapsed":879,"status":"ok","timestamp":1619310979515,"user":{"displayName":"Jeom Jin-Ho","photoUrl":"","userId":"00155613517919499503"},"user_tz":-120},"id":"PZvmFng7ctO3","outputId":"dce0cc91-8e70-4acc-a0b8-6763ffffd5ca","papermill":{"duration":0.031651,"end_time":"2022-03-24T14:01:00.927239","exception":false,"start_time":"2022-03-24T14:01:00.895588","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2022-05-25T21:13:16.291806Z","iopub.execute_input":"2022-05-25T21:13:16.293619Z","iopub.status.idle":"2022-05-25T21:13:16.318052Z","shell.execute_reply.started":"2022-05-25T21:13:16.293583Z","shell.execute_reply":"2022-05-25T21:13:16.317223Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def seed_everything(seed):\n    random.seed(seed)\n    os.environ['PYTHONHASHSEED'] = str(seed)\n    np.random.seed(seed)\n    torch.manual_seed(seed)\n    torch.cuda.manual_seed(seed)\n    torch.backends.cudnn.deterministic = True","metadata":{"executionInfo":{"elapsed":600,"status":"ok","timestamp":1619310981653,"user":{"displayName":"Jeom Jin-Ho","photoUrl":"","userId":"00155613517919499503"},"user_tz":-120},"id":"eastern-content","papermill":{"duration":0.032105,"end_time":"2022-03-24T14:01:01.031949","exception":false,"start_time":"2022-03-24T14:01:00.999844","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2022-05-25T21:13:16.320499Z","iopub.execute_input":"2022-05-25T21:13:16.320873Z","iopub.status.idle":"2022-05-25T21:13:16.328164Z","shell.execute_reply.started":"2022-05-25T21:13:16.32081Z","shell.execute_reply":"2022-05-25T21:13:16.327411Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Dataset and transformations","metadata":{"id":"xaJKvvuKnW4k","papermill":{"duration":0.023988,"end_time":"2022-03-24T14:01:01.080488","exception":false,"start_time":"2022-03-24T14:01:01.0565","status":"completed"},"tags":[]}},{"cell_type":"code","source":"import albumentations as A\nimport albumentations.pytorch as APT\nimport cv2 \n\nbase_transform = A.Compose([\n    A.ToFloat(),\n    APT.transforms.ToTensorV2(),\n])","metadata":{"executionInfo":{"elapsed":1519,"status":"ok","timestamp":1619310984075,"user":{"displayName":"Jeom Jin-Ho","photoUrl":"","userId":"00155613517919499503"},"user_tz":-120},"id":"revolutionary-membership","papermill":{"duration":0.747421,"end_time":"2022-03-24T14:01:01.852072","exception":false,"start_time":"2022-03-24T14:01:01.104651","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2022-05-25T21:13:16.329185Z","iopub.execute_input":"2022-05-25T21:13:16.329384Z","iopub.status.idle":"2022-05-25T21:13:17.552325Z","shell.execute_reply.started":"2022-05-25T21:13:16.329348Z","shell.execute_reply":"2022-05-25T21:13:17.551596Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def pad_image(img):\n    w, h, c = np.shape(img)\n    if w > h:\n        pad = int((w - h) / 2)\n        img = cv2.copyMakeBorder(img, 0, 0, pad, pad, cv2.BORDER_CONSTANT, value=0)\n    else:\n        pad = int((h - w) / 2)\n        img = cv2.copyMakeBorder(img, pad, pad, 0, 0, cv2.BORDER_CONSTANT, value=0)\n        \n    return img\n\n\ndef open_and_preprocess_image(image_path):\n    img = cv2.imread(image_path)\n    img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)\n    img = pad_image(img)\n    return cv2.resize(img, (IMG_SIZE, IMG_SIZE))","metadata":{"execution":{"iopub.status.busy":"2022-05-25T21:13:17.553571Z","iopub.execute_input":"2022-05-25T21:13:17.553818Z","iopub.status.idle":"2022-05-25T21:13:17.562588Z","shell.execute_reply.started":"2022-05-25T21:13:17.553785Z","shell.execute_reply":"2022-05-25T21:13:17.561787Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"class HotelImageDataset:\n    def __init__(self, data, transform=None, data_folder=\"train_images/\"):\n        self.data = data\n        self.data_folder = data_folder\n        self.transform = transform\n\n    def __len__(self):\n        return len(self.data)\n    \n    def __getitem__(self, idx):\n        record = self.data.iloc[idx]\n        image_path = self.data_folder + record[\"image_id\"]\n        \n        image = np.array(open_and_preprocess_image(image_path)).astype(np.uint8)\n\n        if self.transform:\n            transformed = self.transform(image=image)\n            image = transformed[\"image\"]\n        \n        return {\n            \"image\" : image,\n        }","metadata":{"executionInfo":{"elapsed":1058,"status":"ok","timestamp":1619310984077,"user":{"displayName":"Jeom Jin-Ho","photoUrl":"","userId":"00155613517919499503"},"user_tz":-120},"id":"found-mouth","papermill":{"duration":0.037507,"end_time":"2022-03-24T14:01:01.914352","exception":false,"start_time":"2022-03-24T14:01:01.876845","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2022-05-25T21:13:17.563649Z","iopub.execute_input":"2022-05-25T21:13:17.565005Z","iopub.status.idle":"2022-05-25T21:13:17.575204Z","shell.execute_reply.started":"2022-05-25T21:13:17.564963Z","shell.execute_reply":"2022-05-25T21:13:17.574471Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Model","metadata":{"id":"NMDM4PwPnced","papermill":{"duration":0.023902,"end_time":"2022-03-24T14:01:01.962307","exception":false,"start_time":"2022-03-24T14:01:01.938405","status":"completed"},"tags":[]}},{"cell_type":"code","source":"# from https://github.com/ronghuaiyang/arcface-pytorch\nimport math\nimport torch.nn.functional as F\n\nclass ArcMarginProduct(nn.Module):\n    r\"\"\"Implement of large margin arc distance: :\n        Args:\n            in_features: size of each input sample\n            out_features: size of each output sample\n            s: norm of input feature\n            m: margin\n            cos(theta + m)\n        \"\"\"\n    def __init__(self, in_features, out_features, s=30.0, m=0.50, easy_margin=False):\n        super(ArcMarginProduct, self).__init__()\n        self.in_features = in_features\n        self.out_features = out_features\n        self.s = s\n        self.m = m\n        self.weight = nn.Parameter(torch.FloatTensor(out_features, in_features))\n        nn.init.xavier_uniform_(self.weight)\n\n        self.easy_margin = easy_margin\n        self.cos_m = math.cos(m)\n        self.sin_m = math.sin(m)\n        self.th = math.cos(math.pi - m)\n        self.mm = math.sin(math.pi - m) * m\n\n    def forward(self, input, label):\n        # --------------------------- cos(theta) & phi(theta) ---------------------------\n        cosine = F.linear(F.normalize(input), F.normalize(self.weight))\n        sine = torch.sqrt((1.0 - torch.pow(cosine, 2)).clamp(0, 1))\n        phi = cosine * self.cos_m - sine * self.sin_m\n        if self.easy_margin:\n            phi = torch.where(cosine > 0, phi, cosine)\n        else:\n            phi = torch.where(cosine > self.th, phi, cosine - self.mm)\n        # --------------------------- convert label to one-hot ---------------------------\n        # one_hot = torch.zeros(cosine.size(), requires_grad=True, device='cuda')\n        one_hot = torch.zeros(cosine.size(), device='cuda')\n        one_hot.scatter_(1, label.view(-1, 1).long(), 1)\n        # -------------torch.where(out_i = {x_i if condition_i else y_i) -------------\n        output = (one_hot * phi) + ((1.0 - one_hot) * cosine)  # you can use torch.where if your torch.__version__ is 0.4\n        output *= self.s\n        # print(output)\n\n        return output","metadata":{"execution":{"iopub.status.busy":"2022-05-25T21:13:17.577219Z","iopub.execute_input":"2022-05-25T21:13:17.577561Z","iopub.status.idle":"2022-05-25T21:13:17.593127Z","shell.execute_reply.started":"2022-05-25T21:13:17.577524Z","shell.execute_reply":"2022-05-25T21:13:17.592346Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"class EmbeddingModel(nn.Module):\n    def __init__(self, n_classes=100, embedding_size=64, backbone_name=\"efficientnet_b0\"):\n        super(EmbeddingModel, self).__init__()\n        self.embed_size = embedding_size\n        self.backbone = timm.create_model(backbone_name, num_classes=0, pretrained=False)\n        o = self.backbone(torch.randn(1, 3, IMG_SIZE, IMG_SIZE))\n        in_features = o.shape[1]\n        \n        self.arcface = ArcMarginProduct(embedding_size, n_classes)\n       \n        self.post = nn.Sequential(\n            nn.utils.weight_norm(nn.Linear(in_features, self.embed_size*2), dim=None),\n            nn.BatchNorm1d(self.embed_size*2),\n            nn.Dropout(0.2),\n            nn.utils.weight_norm(nn.Linear(self.embed_size*2, self.embed_size)),\n            nn.BatchNorm1d(self.embed_size),\n        )\n        \n    def forward(self, x, targets = None):\n        x = self.backbone(x)\n        x = x.view(x.size(0), -1)\n        x = self.post(x)\n        if targets is not None:\n            x = self.arcface(x, targets)\n        return x","metadata":{"execution":{"iopub.status.busy":"2022-05-25T21:13:17.595743Z","iopub.execute_input":"2022-05-25T21:13:17.596063Z","iopub.status.idle":"2022-05-25T21:13:17.607694Z","shell.execute_reply.started":"2022-05-25T21:13:17.596036Z","shell.execute_reply":"2022-05-25T21:13:17.606996Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Model helper functions","metadata":{"id":"YMZYKhUSneMY","papermill":{"duration":0.024153,"end_time":"2022-03-24T14:01:02.067537","exception":false,"start_time":"2022-03-24T14:01:02.043384","status":"completed"},"tags":[]}},{"cell_type":"code","source":"def generate_embeddings(args, loader, model, bar_desc=\"Generating embeds\"):\n    outputs_all = []\n    \n    model.eval()\n    with torch.no_grad():\n        t = tqdm(loader, desc=bar_desc)\n        for i, sample in enumerate(t):\n            input = sample['image'].to(args.device)\n            output = model(input)\n            outputs_all.extend(output.detach().cpu().numpy())\n            \n    return outputs_all","metadata":{"execution":{"iopub.status.busy":"2022-05-25T21:13:17.610782Z","iopub.execute_input":"2022-05-25T21:13:17.61105Z","iopub.status.idle":"2022-05-25T21:13:17.618781Z","shell.execute_reply.started":"2022-05-25T21:13:17.611019Z","shell.execute_reply":"2022-05-25T21:13:17.618149Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def find_matches(query, base_embeds, base_targets, k=N_MATCHES):\n    distance_df = pd.DataFrame(index=np.arange(len(base_targets)), data={\"hotel_id\": base_targets})\n    # calculate cosine distance of query embeds to all base embeds\n    distance_df[\"distance\"] = cosine_similarity([query], list(base_embeds))[0]\n    # sort by distance and hotel_id\n    distance_df = distance_df.sort_values(by=[\"distance\", \"hotel_id\"], ascending=False).reset_index(drop=True)\n    # return first 5 different hotel_id_codes\n    return distance_df[\"hotel_id\"].unique()[:N_MATCHES]\n\n\ndef predict(args, base_embeddings_df, test_loader, model):\n    test_embeds = generate_embeddings(args, test_loader, model, \"Generate test embeddings\")\n    \n    preds = []\n    for query_embeds in tqdm(test_embeds, desc=\"Similarity - match finding\"):\n        tmp = find_matches(query_embeds, \n                           base_embeddings_df[\"embeddings\"].values, \n                           base_embeddings_df[\"hotel_id\"].values)\n        preds.extend([tmp])\n        \n    return preds","metadata":{"papermill":{"duration":0.034692,"end_time":"2022-03-24T14:01:02.127372","exception":false,"start_time":"2022-03-24T14:01:02.09268","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2022-05-25T21:13:17.619832Z","iopub.execute_input":"2022-05-25T21:13:17.620527Z","iopub.status.idle":"2022-05-25T21:13:17.629761Z","shell.execute_reply.started":"2022-05-25T21:13:17.62049Z","shell.execute_reply":"2022-05-25T21:13:17.628968Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Prepare data","metadata":{"id":"AwShW1wXniD6","papermill":{"duration":0.023807,"end_time":"2022-03-24T14:01:02.175822","exception":false,"start_time":"2022-03-24T14:01:02.152015","status":"completed"},"tags":[]}},{"cell_type":"code","source":"test_df = pd.DataFrame(data={\"image_id\": os.listdir(TEST_DATA_FOLDER), \"hotel_id\": \"\"}).sort_values(by=\"image_id\")","metadata":{"executionInfo":{"elapsed":3742,"status":"ok","timestamp":1619311036476,"user":{"displayName":"Jeom Jin-Ho","photoUrl":"","userId":"00155613517919499503"},"user_tz":-120},"id":"discrete-right","outputId":"c21ed589-3139-4919-b5d5-07bcf6f1df15","papermill":{"duration":0.103381,"end_time":"2022-03-24T14:01:02.453866","exception":false,"start_time":"2022-03-24T14:01:02.350485","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2022-05-25T21:13:17.630902Z","iopub.execute_input":"2022-05-25T21:13:17.631305Z","iopub.status.idle":"2022-05-25T21:13:17.649763Z","shell.execute_reply.started":"2022-05-25T21:13:17.631267Z","shell.execute_reply":"2022-05-25T21:13:17.649145Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Prepare model","metadata":{"id":"5JPdD2bpnniP","papermill":{"duration":0.023835,"end_time":"2022-03-24T14:01:02.502786","exception":false,"start_time":"2022-03-24T14:01:02.478951","status":"completed"},"tags":[]}},{"cell_type":"code","source":"def get_model(backbone_name, checkpoint_path, args):\n    model = EmbeddingModel(args.n_classes, args.embedding_size, backbone_name)\n        \n    checkpoint = torch.load(checkpoint_path)\n    model.load_state_dict(checkpoint[\"model\"])\n    model = model.to(args.device)\n    \n    return model","metadata":{"papermill":{"duration":0.031082,"end_time":"2022-03-24T14:01:02.557921","exception":false,"start_time":"2022-03-24T14:01:02.526839","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2022-05-25T21:13:17.651068Z","iopub.execute_input":"2022-05-25T21:13:17.651316Z","iopub.status.idle":"2022-05-25T21:13:17.656941Z","shell.execute_reply.started":"2022-05-25T21:13:17.651285Z","shell.execute_reply":"2022-05-25T21:13:17.655904Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"class args:\n    batch_size = 64\n    num_workers = 2\n    embedding_size = 128\n    device = ('cuda' if torch.cuda.is_available() else 'cpu')\n    \n    \nseed_everything(seed=SEED)\n\ntest_dataset = HotelImageDataset(test_df, base_transform, data_folder=TEST_DATA_FOLDER)\ntest_loader  = DataLoader(test_dataset, num_workers=args.num_workers, batch_size=args.batch_size, shuffle=False)","metadata":{"executionInfo":{"elapsed":450,"status":"ok","timestamp":1619311064188,"user":{"displayName":"Jeom Jin-Ho","photoUrl":"","userId":"00155613517919499503"},"user_tz":-120},"id":"appointed-machinery","papermill":{"duration":0.069839,"end_time":"2022-03-24T14:01:02.65177","exception":false,"start_time":"2022-03-24T14:01:02.581931","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2022-05-25T21:13:17.658549Z","iopub.execute_input":"2022-05-25T21:13:17.659779Z","iopub.status.idle":"2022-05-25T21:13:17.722767Z","shell.execute_reply.started":"2022-05-25T21:13:17.659745Z","shell.execute_reply":"2022-05-25T21:13:17.721923Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"base_embeddings_df = pd.read_pickle('../input/hotel-id-starter-similarity-training/embedding-model-eca_nfnet_l0-512x512_image-embeddings.pkl')\ndisplay(base_embeddings_df.head())","metadata":{"execution":{"iopub.status.busy":"2022-05-25T21:13:17.724392Z","iopub.execute_input":"2022-05-25T21:13:17.724944Z","iopub.status.idle":"2022-05-25T21:13:20.672402Z","shell.execute_reply.started":"2022-05-25T21:13:17.724902Z","shell.execute_reply":"2022-05-25T21:13:20.671705Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"args.n_classes = base_embeddings_df[\"hotel_id\"].nunique()\nargs.embedding_size = 1800\n\nmodel = get_model(\"eca_nfnet_l0\",\n                  \"../input/hotel-id-starter-similarity-training/checkpoint-embedding-model-eca_nfnet_l0-512x512-last.pt\", \n                  args)","metadata":{"papermill":{"duration":5.553999,"end_time":"2022-03-24T14:01:08.229948","exception":false,"start_time":"2022-03-24T14:01:02.675949","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2022-05-25T21:13:20.673768Z","iopub.execute_input":"2022-05-25T21:13:20.674037Z","iopub.status.idle":"2022-05-25T21:13:30.931684Z","shell.execute_reply.started":"2022-05-25T21:13:20.674004Z","shell.execute_reply":"2022-05-25T21:13:30.930898Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Submission","metadata":{"papermill":{"duration":0.024227,"end_time":"2022-03-24T14:01:08.278753","exception":false,"start_time":"2022-03-24T14:01:08.254526","status":"completed"},"tags":[]}},{"cell_type":"code","source":"%%time\n\npreds = predict(args, base_embeddings_df, test_loader, model)\n# transform array of hotel_ids into string\ntest_df[\"hotel_id\"] = [str(list(l)).strip(\"[]\").replace(\",\", \"\") for l in preds]\n\ntest_df.to_csv(\"submission.csv\", index=False)\ntest_df.head()","metadata":{"papermill":{"duration":0.047156,"end_time":"2022-03-24T14:01:08.414557","exception":false,"start_time":"2022-03-24T14:01:08.367401","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2022-05-25T21:13:30.932979Z","iopub.execute_input":"2022-05-25T21:13:30.933212Z","iopub.status.idle":"2022-05-25T21:13:36.665426Z","shell.execute_reply.started":"2022-05-25T21:13:30.933181Z","shell.execute_reply":"2022-05-25T21:13:36.664696Z"},"trusted":true},"execution_count":null,"outputs":[]}]}