{"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":"# Imports","metadata":{"id":"cZoSOL9Qm-Yr"}},{"cell_type":"code","source":"!pip install timm","metadata":{"papermill":{"duration":22.050076,"end_time":"2021-04-17T11:04:51.928845","exception":false,"start_time":"2021-04-17T11:04:29.878769","status":"completed"},"tags":[],"id":"alleged-legislation","outputId":"2abe0aa6-4c55-4eb7-9279-0e214d2e92e0","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"!pip install pytorch-metric-learning","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import numpy as np \nimport pandas as pd\nimport random\nimport os\nimport math\nimport time","metadata":{"_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","papermill":{"duration":0.030593,"end_time":"2021-04-17T11:04:51.983376","exception":false,"start_time":"2021-04-17T11:04:51.952783","status":"completed"},"tags":[],"id":"expired-matter","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from sklearn.metrics import accuracy_score\nfrom sklearn.utils import class_weight\nfrom PIL import Image as pil_image\nfrom tqdm import tqdm\nimport scipy\n\nimport matplotlib\nimport matplotlib.pyplot as plt\nimport plotly.express as px\nimport plotly.graph_objects as go","metadata":{"papermill":{"duration":4.287352,"end_time":"2021-04-17T11:04:56.353165","exception":false,"start_time":"2021-04-17T11:04:52.065813","status":"completed"},"tags":[],"id":"extreme-problem","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import torch\nimport torch.nn as nn\nimport torch.nn.functional as F\nfrom torch.utils.data import DataLoader\n\nimport timm\nfrom timm.optim import Lookahead, RAdam\nfrom pytorch_metric_learning import miners, losses, samplers , distances, regularizers ","metadata":{"papermill":{"duration":1.641769,"end_time":"2021-04-17T11:04:58.018871","exception":false,"start_time":"2021-04-17T11:04:56.377102","status":"completed"},"tags":[],"id":"angry-domain","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Global","metadata":{"id":"0B00pe7mnBTj"}},{"cell_type":"code","source":"IMG_SIZE = 256\nSEED = 42\nN_MATCHES = 5\n\nPROJECT_FOLDER = \"../input/hotel-id-to-combat-human-trafficking-2022-fgvc9/\"\nDATA_FOLDER = \"../input/nopadding256/\"\nIMAGE_FOLDER = DATA_FOLDER + \"images/\"\nOUTPUT_FOLDER = \"\"\n\ntrain_df = pd.read_csv(os.path.join(DATA_FOLDER, 'train_no_padding_256.csv'))","metadata":{"id":"JPRRC5jpF4nx","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print(os.listdir(PROJECT_FOLDER))\nprint(len(os.listdir(IMAGE_FOLDER)))","metadata":{"id":"PZvmFng7ctO3","outputId":"59062bb2-fe5f-4ede-940e-29d38c86e20d","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Helper functions - seed and metric calculator","metadata":{"id":"9p7EE95ZnNpK"}},{"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":{"papermill":{"duration":0.031291,"end_time":"2021-04-17T11:04:58.424933","exception":false,"start_time":"2021-04-17T11:04:58.393642","status":"completed"},"tags":[],"id":"eastern-content","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Dataset and transformations","metadata":{"id":"xaJKvvuKnW4k"}},{"cell_type":"code","source":"import albumentations as A\nimport albumentations.pytorch as APT\nimport cv2 \n\n# used for training dataset - augmentations and occlusions\ntrain_transform = A.Compose([\n    A.Transpose(p=0.5),\n    A.HorizontalFlip(p=0.5),\n    A.VerticalFlip(p=0.5),\n    A.RandomBrightnessContrast(p=0.75),\n    A.ShiftScaleRotate(shift_limit=0.1, scale_limit=0.1, rotate_limit=15, border_mode=0, p=0.85),\n    \n    A.CoarseDropout(p=1., max_holes=1, \n                    min_height=IMG_SIZE//4, max_height=IMG_SIZE//2,\n                    min_width=IMG_SIZE//4,  max_width=IMG_SIZE//2, \n                    fill_value=(255,0,0)),# simulating occlusions in test data\n\n    A.ToFloat(),\n    APT.transforms.ToTensorV2(),\n])\n\n# used for validation dataset - only occlusions\nval_transform = A.Compose([\n    A.CoarseDropout(p=1., max_holes=1, \n                    min_height=IMG_SIZE//4, max_height=IMG_SIZE//2,\n                    min_width=IMG_SIZE//4,  max_width=IMG_SIZE//2, \n                    fill_value=(255,0,0)),# simulating occlusions\n    A.ToFloat(),\n    APT.transforms.ToTensorV2(),\n])\n\n# no augmentations\nbase_transform = A.Compose([\n    A.ToFloat(),\n    APT.transforms.ToTensorV2(),\n])","metadata":{"papermill":{"duration":0.033385,"end_time":"2021-04-17T11:04:58.538926","exception":false,"start_time":"2021-04-17T11:04:58.505541","status":"completed"},"tags":[],"id":"revolutionary-membership","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"class HotelTrainDataset:\n    def __init__(self, data, transform=None, data_path=\"train_images/\"):\n        self.data = data\n        self.data_path = data_path\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_path + record[\"image_id\"]\n        image = np.array(pil_image.open(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            \"target\" : record['hotel_id_code'],\n        }","metadata":{"papermill":{"duration":0.032811,"end_time":"2021-04-17T11:04:58.595928","exception":false,"start_time":"2021-04-17T11:04:58.563117","status":"completed"},"tags":[],"id":"found-mouth","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Model","metadata":{"id":"NMDM4PwPnced"}},{"cell_type":"code","source":"class EmbeddingNet(nn.Module):\n    def __init__(self, n_classes=100, embed_size=64, backbone_name=\"efficientnet_b0\"):\n        super(EmbeddingNet, self).__init__()\n        \n        self.embed_size = embed_size\n        self.backbone = timm.create_model(backbone_name, pretrained=True)\n        in_features = self.backbone.get_classifier().in_features\n\n        fc_name, _ = list(self.backbone.named_modules())[-1]\n        if fc_name == 'classifier':\n            self.backbone.classifier = nn.Identity()\n        elif fc_name == 'head.flatten':\n            self.backbone.head.fc = nn.Identity()\n        elif fc_name == 'fc':\n            self.backbone.fc = nn.Identity()\n        elif fc_name == 'head':\n            self.backbone.head = nn.Identity()\n        else:\n            raise Exception(\"unknown classifier layer: \" + fc_name)\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        )\n\n        self.classifier = nn.Sequential(\n            nn.BatchNorm1d(self.embed_size),\n            nn.Dropout(0.2),\n            nn.Linear(self.embed_size, n_classes),\n        )\n        \n    def embed_and_classify(self, x):\n        x = self.forward(x)\n        return x, self.classifier(x)\n\n    def forward(self, x):\n        x = self.backbone(x)\n        x = x.view(x.size(0), -1)\n        x = self.post(x)\n        return x","metadata":{"id":"GuAfw_a4m3PK","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Model helper functions","metadata":{"id":"YMZYKhUSneMY"}},{"cell_type":"code","source":"def get_embeds(loader, model, bar_desc=\"Generating embeds\"):\n    targets_all = []\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            target = sample['target'].to(args.device)\n            output = model(input)\n\n            targets_all.extend(target.cpu().numpy())\n            outputs_all.extend(output.detach().cpu().numpy())\n            \n    return targets_all, outputs_all\n\ndef get_prediction(loader, model, bar_desc=\"Generating predictions\"):\n    targets_all = []\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            target = sample['target'].to(args.device)\n            _, output = model.embed_and_classify(input)\n            output = torch.argsort(torch.sigmoid(output), descending=True)\n\n            targets_all.extend(target.cpu().numpy())\n            outputs_all.extend(output.detach().cpu().numpy())\n            \n    return targets_all, outputs_all","metadata":{"papermill":{"duration":0.032565,"end_time":"2021-04-17T11:04:58.652672","exception":false,"start_time":"2021-04-17T11:04:58.620107","status":"completed"},"tags":[],"id":"massive-makeup","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def get_distance_matrix(embeds, base_embeds, distance_func):\n    distance_matrix = []\n    base_embeds = torch.Tensor(base_embeds)\n    embeds_dataset = torch.utils.data.TensorDataset(torch.Tensor(embeds))\n    embeds_dataloader = DataLoader(embeds_dataset, num_workers=2, batch_size=1024, shuffle=False)\n    \n    t = tqdm(embeds_dataloader)\n    for i, sample in enumerate(t): \n        distances = distance_func(sample[0], base_embeds)\n        distance_matrix.extend(distances.numpy())\n        \n    return np.array(distance_matrix)","metadata":{"id":"0CIJPX2mGzZw","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def save_checkpoint(model, scheduler, optimizer, epoch, name, loss=None, score=None):\n    checkpoint = {\"epoch\": epoch,\n                  \"model\": model.state_dict(),\n                  \"scheduler\": scheduler.state_dict(),\n                  \"optimizer\": optimizer.state_dict(),\n                  \"loss\": loss,\n                  \"score\": score,\n                  }\n\n    torch.save(checkpoint, f\"{OUTPUT_FOLDER}checkpoint-{name}.pt\")\n\n\ndef load_checkpoint(model, scheduler, optimizer, name):\n    checkpoint = torch.load(f\"{OUTPUT_FOLDER}checkpoint-{name}.pt\")\n\n    model.load_state_dict(checkpoint[\"model\"])\n    scheduler.load_state_dict(checkpoint[\"scheduler\"])\n    # optimizer.load_state_dict(checkpoint[\"optimizer\"])\n\n    return model, scheduler, optimizer, checkpoint[\"epoch\"]","metadata":{"id":"T85MXS1lHUKI","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def iterate_loader(loader, epochs):\n    loader.dataset.fake_load = True\n    with torch.no_grad():\n        for i in range(epochs):\n            t = tqdm(loader, desc=f\"Iterating loader {i+1}/{epochs}\")\n            for j, sample in enumerate(t):\n                images = sample['image']\n                targets = sample['target']\n\n    loader.dataset.fake_load = False","metadata":{"id":"w8y9MjFEuFPU","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def train_epoch(args, model, loader, criterion, optimizer, scheduler, epoch):\n    losses = []\n    targets_all = []\n    outputs_all = []\n    \n    model.train()\n    t = tqdm(loader)\n    \n    for i, sample in enumerate(t):\n        optimizer.zero_grad()\n        \n        images = sample['image'].to(args.device)\n        targets = sample['target'].to(args.device)\n        \n        embeds, outputs = model.embed_and_classify(images)\n        loss = criterion(outputs, targets)\n        \n        loss.backward()\n        optimizer.step()\n        \n        if scheduler:\n            scheduler.step()\n                \n        losses.append(loss.item())\n        targets_all.extend(targets.cpu().numpy())\n        outputs_all.extend(torch.sigmoid(outputs).detach().cpu().numpy())\n\n        score = np.mean(targets_all == np.argmax(outputs_all, axis=1))\n        desc = f\"Epoch {epoch}/{args.epochs} - Train loss:{loss:0.4f}, score: {score:0.4f}\"\n        t.set_description(desc)\n        \n    return np.mean(losses), score\n\n\ndef test_closest_match(base_df, base_embeds, valid_targets, valid_embeds, model, distance_func, closest, n_matches=5):\n    distance_matrix = get_distance_matrix(valid_embeds, base_embeds, distance_func)\n\n    preds = []\n    N_val = len(valid_embeds)\n    for i in tqdm(range(N_val), total=N_val, desc=\"Getting closest match\"):\n        tmp_df = base_df.copy()\n        tmp_df[\"distance\"] = distance_matrix[i]\n        tmp_df = tmp_df.sort_values(by=[\"distance\", \"hotel_id\"], ascending=closest).reset_index(drop=True)\n        preds.extend([tmp_df[\"hotel_id_code\"].unique()[:n_matches]])\n\n    y = np.repeat([valid_targets], repeats=n_matches, axis=0).T\n    preds = np.array(preds)\n    acc_top_1 = (preds[:, 0] == valid_targets).mean()\n    acc_top_5 = (preds == y).any(axis=1).mean()\n    print(f\"Accuracy: {acc_top_1:0.4f}, top 5 accuracy: {acc_top_5:0.4f}\")\n    return preds, distance_matrix\n\n\ndef test(base_loader, valid_loader, model, distance_func, closest):\n    base_targets, base_embeds = get_embeds(base_loader, model, \"Generating embeds for train\")\n    valid_targets, valid_embeds = get_embeds(valid_loader, model, \"Generating embeds for test\")\n    val_preds, distance_matrix = test_closest_match(base_loader.dataset.data, base_embeds, valid_targets, valid_embeds, model, distance_func, closest)\n\n    return base_embeds, valid_embeds, base_targets, valid_targets, val_preds, distance_matrix","metadata":{"papermill":{"duration":0.036549,"end_time":"2021-04-17T11:04:58.713386","exception":false,"start_time":"2021-04-17T11:04:58.676837","status":"completed"},"tags":[],"id":"flying-bottle","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Prepare data","metadata":{"id":"AwShW1wXniD6"}},{"cell_type":"code","source":"def sample_data(n_hotels, min_images, max_images):\n    data_df = pd.read_csv(PROJECT_FOLDER + \"train.csv\", parse_dates=[\"timestamp\"])\n    sample_df = data_df.groupby(\"hotel_id\").filter(lambda x: (x[\"image\"].nunique() > min_images) & (x[\"image\"].nunique() < max_images))\n    sample_df[\"hotel_id_code\"] = sample_df[\"hotel_id\"].astype('category').cat.codes.values.astype(np.int64)\n    sample_df = sample_df[sample_df[\"hotel_id_code\"] < n_hotels]\n\n    print(f\"Subsample with {len(sample_df.hotel_id.unique())} hotels out of {len(data_df.hotel_id.unique())}\" + \n          f\" with total {len(sample_df)} images ({len(sample_df) / len(data_df) * 100:0.2f} %)\")\n    \n    return sample_df","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"data_df = pd.read_csv(DATA_FOLDER + \"train_no_padding_256.csv\")\n# encode hotel ids\ndata_df[\"hotel_id_code\"] = data_df[\"hotel_id\"].astype('category').cat.codes.values.astype(np.int64)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"fig = go.Figure()\nfig.add_trace(go.Histogram(x=data_df[\"hotel_id_code\"]))\nfig.update_xaxes(type=\"category\")\nfig.show()","metadata":{"papermill":{"duration":2.790179,"end_time":"2021-04-17T11:05:01.702988","exception":false,"start_time":"2021-04-17T11:04:58.912809","status":"completed"},"tags":[],"id":"discrete-right","outputId":"ef000115-70a9-419d-8882-83e228ebc131","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Train and evaluate","metadata":{"id":"5JPdD2bpnniP"}},{"cell_type":"code","source":"data_df","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"hotel_image_count = data_df.groupby(\"hotel_id\")[\"image_id\"].count()\n    # hotels that have more images than samples for validation\nvalid_hotels = hotel_image_count[hotel_image_count > 1]\n    # data that can be split into train and val set\nvalid_data = data_df[data_df[\"hotel_id\"].isin(valid_hotels.index)]\n    # if hotel had less than required val_samples it will be only in the train set\nvalid_df = valid_data.groupby(\"hotel_id\").sample(1, random_state=SEED)\ntrain_df = data_df[~data_df[\"image_id\"].isin(valid_df[\"image_id\"])]","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_df","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def train_and_validate(args, data_df):\n    model_name = f\"classification-model-{args.backbone_name}-{IMG_SIZE}x{IMG_SIZE}-{args.embed_size}embeds-{args.n_classes}hotels\"\n    print(model_name)\n    # SEED and split\n    seed_everything(seed=SEED)\n    hotel_image_count = data_df.groupby(\"hotel_id\")[\"image_id\"].count()\n    # hotels that have more images than samples for validation\n    valid_hotels = hotel_image_count[hotel_image_count > 1]\n    # data that can be split into train and val set\n    valid_data = data_df[data_df[\"hotel_id\"].isin(valid_hotels.index)]\n    # if hotel had less than required val_samples it will be only in the train set\n    valid_df = valid_data.groupby(\"hotel_id\").sample(1, random_state=SEED)\n    train_df = data_df[~data_df[\"image_id\"].isin(valid_df[\"image_id\"])]\n\n    # create model\n    model = EmbeddingNet(args.n_classes, args.embed_size, args.backbone_name)\n    model = model.to(args.device)\n\n    train_dataset = HotelTrainDataset(train_df, train_transform, data_path=IMAGE_FOLDER)\n    train_loader  = DataLoader(train_dataset, num_workers=args.num_workers, batch_size=args.batch_size, shuffle=True, drop_last=True)\n    valid_dataset = HotelTrainDataset(valid_df, val_transform, data_path=IMAGE_FOLDER)\n    valid_loader  = DataLoader(valid_dataset, num_workers=args.num_workers, batch_size=args.batch_size, shuffle=False)\n    # base dataset for image similarity search\n    base_dataset  = HotelTrainDataset(train_df, base_transform, data_path=IMAGE_FOLDER)\n    base_loader   = DataLoader(base_dataset, num_workers=args.num_workers, batch_size=args.batch_size*4, shuffle=False)\n    print(f\"Base: {len(base_dataset)}\\nValidation: {len(valid_dataset)}\")\n\n    distance = distances.CosineSimilarity()\n    criterion = nn.CrossEntropyLoss()\n    optimizer = Lookahead(torch.optim.AdamW(model.parameters(), lr=args.lr), k=3)\n\n    scheduler = torch.optim.lr_scheduler.OneCycleLR(\n                    optimizer,\n                    max_lr=args.lr,\n                    epochs=args.epochs,\n                    steps_per_epoch=len(train_loader),\n                    div_factor=10,\n                    final_div_factor=1,\n                    pct_start=0.1,\n                    anneal_strategy=\"cos\",\n                )\n    \n    start_epoch = 1\n\n    if args.continue_from_checkpoint:\n        model, scheduler, optimizer, last_epoch = load_checkpoint(model, scheduler, optimizer, model_name)\n        iterate_loader(train_loader, last_epoch)\n        start_epoch = start_epoch + last_epoch\n\n    torch.cuda.empty_cache()\n\n    for epoch in range(start_epoch, args.epochs+1):\n        train_loss, train_score = train_epoch(args, model, train_loader, criterion, optimizer, scheduler, epoch)\n        save_checkpoint(model, scheduler, optimizer, epoch, model_name, train_loss, train_score)\n        if (epoch == 1):\n            _ = test(base_loader, valid_loader, model, distance, closest=False)\n\n    base_embeds, valid_embeds, base_targets, valid_targets, val_preds, distance_matrix = test(base_loader, valid_loader, model, distance, closest=False)","metadata":{"id":"SYoTOYmYdjwy","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"class args:\n    epochs = 10\n    lr = 1e-3\n    batch_size = 32\n    num_workers = 2\n    embed_size = 2048\n    val_samples = 1\n    backbone_name=\"densenet161\"\n    n_classes = data_df[\"hotel_id_code\"].nunique()\n    device = ('cuda' if torch.cuda.is_available() else 'cpu')\n    continue_from_checkpoint = False\n\ntrain_and_validate(args, data_df)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}